49 of 51 criteria have a sourced finding; 45 were also cross-checked by a second agent. Every comparison that includes SuperPlane links here for scope, limitations, atomic answers and sources.
Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.
SuperPlane primarily uses the hosted web/phone-browser app, with a companion CLI and a first-party hardware badge client. The bounded public source and release inventory contains no desktop GUI or native phone app.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server, Factory Remote badge client · Version: Targeted first-party source check 2026-11-13. New implementation findings are pinned to eaa40c84cbf7b5e9852043d8a8f0d0b2b6461ce4. Unchanged atomic answers retain the individual source dates and revisions in their cited evidence. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
Not separately cross-checked
This source pass establishes only the named atomic answers. Other parts retain their documented source gaps; no hands-on test was performed.
9 atomic answers
Desktop os [unsupported] No desktop GUI in the scoped superplane core/release targets or Remote_Control client. Hosted web app; companion CLI only. Sources: superplane:gaps41-native-inventory.
Mobile apps [unsupported] No native iOS or Android app is distributed; phone access is the mobile web board layout, with no store listing or native build documented. Sources: superplane:mobileboard, superplane:cli.
Browser [supported] The hosted web app at app.superplane.com is the primary client: board with Backlog/Implement/Verify/Done, task detail with prompt input, Start control and review links. Sources: superplane:boardimg, superplane:overview, superplane:quickstart.
Mobile browser [supported] The React web app ships a dedicated mobile board layout (column carousel, bottom bar, mobile task creation), usable from a phone browser. Sources: superplane:mobileboard.
Cli [supported] Product CLI (@superplane/cli, macOS/Linux x64/arm64) authenticates by API token and inspects workspaces/tasks, with task create/close/dispatch/assign/artifact operations in the command tree. Sources: superplane:cli, superplane:agenttools.
Editor extensions [unsupported] No editor extension is distributed; editors connect by configuring the workspace MCP server in Cursor/Claude Code, which is client configuration rather than a SuperPlane extension. Sources: superplane:mcp.
Workspace agents run Claude Code, Codex (ChatGPT subscriptions), Cursor cloud agents and OpenAI/CustomLLM/OpenRouter/Perplexity components with managed models across seven providers; the product sequences agent sessions through runner components. Joint multi-harness operation in one factory is unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Each workspace uses one model source; joint multi-harness operation is unestablished.
Model providers [supported] Managed models cover OpenAI, Anthropic, Gemini, xAI Grok, DeepSeek, Qwen and Kimi; workspaces may instead use own Claude/OpenAI/OpenRouter keys or ChatGPT subscriptions. Sources: superplane:modelsrc, superplane:byok, superplane:byos, superplane:pricing.
Custom adapters [partial] Customprovider and OpenRouter components allow custom model backends; a documented general adapter SDK is unverified. Sources: superplane:components.
Session integration [supported] The factory owns the run sequence: canvases launch agent nodes with injected credentials, pass task context, collect outputs as checks/artifacts and route failures. Sources: superplane:implement-auto, superplane:agenttools, superplane:claudespec.
Mixed harness operation [unsupported] No factory combining two harnesses is established: searched the runner component registry (claude, codex, cursor, openrouter, customllm), canvas templates and docs found components coexisting in the catalog but no joint multi-harness operation. Sources: superplane:components, superplane:claudespec, superplane:codexspec.
Codex runs on members’ ChatGPT subscriptions (BYOS) and Claude/OpenAI/OpenRouter API keys (BYOK) with provider-side billing and no SuperPlane token markup; otherwise managed models bill provider rate plus 10% from the credit balance with auto-purchase. No local-model route, trial or allowance exists.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Trial and allowance specifics are absent from current pages.
7 atomic answers
Agent subscriptions [supported] Bring-your-own-subscription runs Codex on each task owner's personal ChatGPT subscription; the plan covers model use while SuperPlane bills machine time. Sources: superplane:byos.
Api accounts [supported] Bring-your-own-key runs workspace agents on Claude, OpenAI or OpenRouter API keys with provider-side billing and no platform fee. Sources: superplane:byok, superplane:modelsrc.
Vendor credits [partial] Managed model use bills provider rate plus 10% from the credit balance with auto-purchase; trial credits and usage allowances are absent from current pages. Sources: superplane:pricing, superplane:billing, superplane:costs.
Local models [unsupported] The three documented model sources are SuperPlane-managed, own API key and ChatGPT subscription; no local-model execution route is documented after checking model, billing and self-hosting sources. Sources: superplane:modelsrc, superplane:byok, superplane:selfhost.
Account switching [partial] Members connect one ChatGPT account per organization usable in every workspace; per-member multi-account switching is unverified. Sources: superplane:byos.
Vendor account requirement [partial] Cloud use requires a SuperPlane account, workspace access and an API token/OAuth grant; self-hosting instead requires own infrastructure plus model keys. Sources: superplane:quickstart, superplane:cli, superplane:mcp, superplane:selfhost.
Provider restrictions [partial] One model source per workspace; pay-as-you-go requires a payment card; Team or higher is needed for API keys; Enterprise-only providers (Bedrock) and SSO-gated access apply. Sources: superplane:modelsrc, superplane:pricing, superplane:byok.
First task completes in under 5 minutes via signup, GitHub connection with automatic issue import and board Start on a small task; hosted-Git, prerequisite, managed-cloud and BYO server onboarding are first-class. Local directories and local-only repos have no intake path.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Folder-without-Git and local-Git-without-remote have no implementation.
7 atomic answers
First task setup [supported] Onboarding guides account creation, repo connection, workspace preparation and the first board Start inside 5 minutes with small-task selection guidance. Sources: superplane:quickstart, superplane:how.
No git [unsupported] Checkout clones provider remote URLs over HTTPS with idempotent bootstrap; no local-directory intake path exists in code or docs. Sources: superplane:checkout, superplane:quickstart.
Local git without remote [unsupported] Intake and checkout require a connected hosted repository; searched intake, checkout and self-hosting sources found no local-only-Git path. Sources: superplane:checkout, superplane:intakes, superplane:selfhost.
Prerequisite guidance [supported] Prerequisites (account, repo access, integration permission, issues, existing tests/CI) and good/bad first-task lists are stated before the first run. Sources: superplane:quickstart.
Managed cloud setup [supported] Cloud setup is account signup plus repository connection through onboarding with no separate machine provisioning. Sources: superplane:quickstart.
Byo vps onboarding [supported] Self-hosting offers a Docker Compose single-Linux-VM path and an Enterprise Terraform/Kubernetes path for AWS/Azure/GCP with owner setup and Fleet Manager runner provisioning. Sources: superplane:selfhost, superplane:selfinstall.
Product CLI (inspect plus task/run/fleet/member/secret/integration ops), OpenAPI 3 API from protobuf v1.0.0-rc7, and an OAuth MCP server with shared-permission task/member/check/artifact tools provide programmable access; inbound webhooks start automations. No shipped SDK or outbound webhooks exist.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server, SuperPlane API (OpenAPI) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. No shipped SDK, no outbound webhooks and no published stability policy exist. The runner Bash task CLI has different commands from the product CLI.
8 atomic answers
Cli [supported] The product CLI authenticates by API token, manages contexts and operates tasks, runs, fleets, members, secrets, integrations, organizations, workspaces, automations, runners and OIDC verification; task operations include create, describe, list, dispatch, assign, close, checks and five artifact operations. Sources: superplane:cli, superplane:clitree.
Api [supported] The OpenAPI 3 specification (protobuf-generated, v1.0.0-rc7) documents endpoints for client generation; requests require workspace credentials and permissions. Sources: superplane:api-ref.
Sdk [unsupported] Repo-wide *sdk* filename search and the api/ tree show no published SDK; programmatic access is the CLI, the OpenAPI spec (for client generation) and the MCP server. Sources: superplane:api-ref, superplane:cli.
Mcp server [supported] The workspace MCP server exposes task, member, check and artifact tools to editors/agents over Streamable HTTP with OAuth and per-connection revocation. Sources: superplane:mcp, superplane:agenttools.
Webhooks [partial] The inbound webhook trigger gives external systems a URL that starts an automation with authentication and payload validation; outbound delivery webhooks are not documented. Sources: superplane:custom.
Stability [partial] The spec is versioned from protobuf definitions and validated at website build; a published stability/deprecation policy is unverified. Sources: superplane:api-ref, superplane:releases.
Agents gain custom capabilities through Bash/Python/JavaScript steps, Daytona sandboxes, custom HTTP/GraphQL/SSH integrations and administrator-configured MCP servers consumed via workspace_mcp.json; repo instructions and inline skills shape them; integration secrets with minimum scope and org RBAC bound access. Third-party skill packages and plugins have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. The MCP client sits behind the experimental workspace_mcp flag; third-party skill packages, external plugin APIs and per-component setup burden beyond the documented flows are unestablished.
7 atomic answers
Mcp client [partial] Workspace agents consume administrator-configured MCP servers (mcp_server kind, up to 20 enabled per factory, public-HTTPS URL validation, headers-or-OAuth with browser-completed OAuth, tool listing and defaults) via workspace_mcp.json in Claude and Codex runs; the capability sits behind the experimental workspace_mcp flag and third-party skill packages remain follow-on. Sources: superplane:mcpmodel, superplane:mcpapi, superplane:mcprun, superplane:mcpprd.
Plugins [unsupported] No plugin API, registry or loader exists in code or docs; searched plugin across the repository. Sources: superplane:components, superplane:automations.
Instructions import [partial] Implement automations feed repository instructions such as AGENTS.md plus commands and boundaries to agents, and workspaces support inline SKILL.md skills; first-party operating skills ship alongside, while third-party skill packages stay follow-on. Sources: superplane:implement-auto, superplane:skillsrepo, superplane:mcpprd.
Authentication [supported] Integration secrets, per-run injected credentials and OAuth grants authenticate connections; credentials are never placed in prompts or canvas values. Sources: superplane:agenttools, superplane:automations, superplane:security.
Integration owner [partial] Components are product-managed while model execution inherits the connected provider CLI/subscription; setup burden varies by integration and is only partly documented. Sources: superplane:components, superplane:byok, superplane:byos.
No desktop client of any implementation exists; the product is a React web app at app.superplane.com with a dedicated mobile-web board layout. No native, Electron, Tauri or React Native client is distributed.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Desktop absence rests on a bounded whole-catalog source and code inspection.
4 atomic answers
Desktop implementation [unsupported] No desktop client exists in any implementation: distribution is web-only with CLI/MCP/API access, and no desktop installer or wrapper is documented in the site, docs, releases or repository. Sources: superplane:overview, superplane:cli, superplane:releases, superplane:mobileboard.
Mobile implementation [partial] No native mobile client exists; phone access is a dedicated mobile-web board layout inside the React web app. Sources: superplane:mobileboard.
Implementation evidence [supported] Docs and repository establish a React single-page web app served from app.superplane.com; the mobile board page pins the web implementation in source. Sources: superplane:mcp, superplane:cli, superplane:mobileboard.
Work enters from GitHub/Jira/Linear/Sentry intakes or board-created tasks, plus agent-proposed drafts and schedule/chat triggers; the SuperPlane task (stable SUPER-*/NEWWB-* key) is the working record with its source attached, closing when PRs merge. Full two-way field sync and label/priority edits are unverified.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Two-way field sync, labels, priorities, archive and reopen are unverified.
Prompt intake [supported] Agents propose tasks via the MCP/Bash create_task tool (e.g. splitting complex work into drafts) and scheduled-intake agents file proposals from repository inspection. Sources: superplane:agenttools, superplane:schedintake, superplane:schedtmpl.
Authoritative tracker [partial] The SuperPlane task is the authoritative working record (state, checks, artifacts, history) with the source issue/PR attached; the provider tracker still owns code and review. Sources: superplane:intake, superplane:done, superplane:boardimg.
Stable ids [supported] Tasks carry stable human-readable keys (SUPER-123, NEWWB-261) used across CLI, MCP, board and checks. Sources: superplane:agenttools, superplane:boardimg.
Supported edits [partial] Create, edit, comment, assign, check-report and close operations are tooled; labels, priorities, archive and reopen flows are unverified. Sources: superplane:agenttools, superplane:boardimg.
Tasks carry refinement plans with confidence analysis, descriptions with acceptance expectations and branch/PR implementation links; board and agent prompts edit them and durable execution preserves them across restarts. Revision history and formal mid-run amendment semantics are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Revision history and formal mid-run amendment semantics are unestablished.
7 atomic answers
Plans [supported] Backlog analysis records a structured plan (outcome, code area, missing info, confidence, start recommendation) attached as a task artifact. Sources: superplane:backlog-auto, superplane:intake.
Acceptance criteria [partial] Tasks state expected behavior and confirming tests/checks; a formal acceptance-criteria field distinct from description is unverified. Sources: superplane:intake, superplane:agenttools.
Editors [supported] The board task view and the agent prompt input edit task content; agents amend drafts through the task tools. Sources: superplane:boardimg, superplane:agenttools.
Revisions [unsupported] Work orders carry CreatedAt/UpdatedAt but no version or revision history table; searched models and migrations for revision/history. Sources: superplane:wotrans.
Implementation links [supported] Branch and pull-request artifacts attach to the task so Verify receives durable links rather than prose. Sources: superplane:implement-auto, superplane:done.
Restart persistence [supported] Durable execution records state between steps so runs resume from a known boundary after transient failures. Sources: superplane:implement.
Confidence scoring plus the Start gate control readiness; tasks retain identity, discussion, history and outputs; approval pauses stop the line; canvases stay customizable with no mandatory preset. Epics, enforced hierarchies, dependency enforcement and state propagation have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Epics, hierarchies, dependency enforcement and propagation have no implementation.
9 atomic answers
Epics [unsupported] No epic object exists in the work-order models; searched epic, parent and child terms across models and actions. Sources: superplane:wotrans.
Hierarchy [unsupported] FactoryWorkOrder has no parent/child fields; agent draft breakdown is prompt convention without enforced hierarchy. Searched models and migrations. Sources: superplane:wotrans, superplane:agenttools.
Readiness [supported] Confidence scores with reasons route ready versus needs-clarification work, and Start authorizes execution only after team rules are met. Sources: superplane:intake, superplane:backlog-auto.
Enforcement [partial] The Start gate and approval pauses are enforced by the workflow; automatic dependency enforcement is unverified. Sources: superplane:intake, superplane:core.
Task to epic [unsupported] No task-to-epic growth object exists; searched models and actions. Sources: superplane:wotrans.
Identity retention [supported] Tasks keep source, discussion, checks, artifacts, retries and timestamps from intake through Done. Sources: superplane:done, superplane:intake.
Workflow constraints [partial] Defaults are suggested for first runs but every stage canvas is customizable; no rigid mandatory preset is imposed. Sources: superplane:automations, superplane:quickstart.
Repository instructions, per-task attachments and canvas memories with node/manual source, timestamps and add/update/delete components carry context; the shared task record plus owner transfer survives sessions and colleagues. Cross-harness continuity and staleness enforcement are unverified.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Freshness enforcement and cross-harness continuity are unverified.
10 atomic answers
Instructions [supported] Implement automations feed repository instructions, conventions, commands and off-limit paths to the agent as contributor context. Sources: superplane:implement-auto.
Project docs [partial] Per-task artifacts and attachments persist docs with the work; repository-level project-doc management is unverified. Sources: superplane:agenttools, superplane:done.
Memory [partial] Canvas add/update memory components keep workflow memory; managed cross-session or cross-harness memory is unverified. Sources: superplane:components, superplane:custom.
Scope [partial] Memories are canvas-scoped and task context is workspace-scoped; broader scope guarantees are unverified. Sources: superplane:components, superplane:agenttools.
Provenance [partial] Memories record node-or-manual source, timestamps and namespace; human identity granularity is unverified. Sources: superplane:canvasmem.
Correction [supported] Canvas memories support correction through the update-memory component with node/manual source tracking. Sources: superplane:canvasmem.
Deletion [supported] Canvas memories support deletion through the delete-memory component. Sources: superplane:canvasmem.
Freshness [partial] Memory timestamps exist; staleness or freshness enforcement is unverified. Sources: superplane:canvasmem.
Takeover continuity [partial] The shared task record (source, discussion, checks, artifacts, history) plus owner transfer survive colleague takeover; runtime memory transfer is unverified. Sources: superplane:done, superplane:agenttools.
Agents inspect repositories at runtime with image/video inputs and external tracker signals, but the product provides no code search, indexing, retrieval, citation or conflict-detection machinery; review gates enforce checks, not architecture rules.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server, SuperPlane API (OpenAPI) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Retrieval, citation, conflict and architecture-enforcement machinery have no implementation.
10 atomic answers
Code search [unsupported] No product code-search service exists; agents inspect repositories at runtime. Searched index, embedding and code-search terms (only an unrelated DigitalOcean knowledge-base integration matched). Sources: superplane:components, superplane:implement-auto.
Indexing [unsupported] No repository indexing exists; searched models, components and integrations for index stores. Sources: superplane:components.
External knowledge [partial] Tracker and observability integrations (GitHub, Jira, Linear, Sentry, Datadog) feed external signals into work; API-awareness retrieval is unverified. Sources: superplane:observability, superplane:intakes.
The board is a native issue system: create, edit, discuss, assign, search/filter, project views, draft parking, explicit Start dispatch, separate task/run entities, rich metadata and durable draft/open/closed states with archive and reopen transitions in the state model. Priorities and user labels have no implementation; the provider tracker still owns code.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Priorities and user labels have no implementation; archive/reopen surfacing beyond the model is unverified.
Discuss [supported] Tasks carry discussion and comments visible to the team alongside checks and artifacts. Sources: superplane:agenttools, superplane:done.
Prioritize [unsupported] No priority field exists on FactoryWorkOrder; searched models and migrations. Sources: superplane:wotrans.
Label [unsupported] OriginLabel is source-derived (tracker/URL), with no user label or tag fields on the model. Sources: superplane:wotrans.
Assign [supported] Owner assignment with reasons and only-if-unassigned guard; members listed with roles and open counts. Sources: superplane:agenttools.
Archive [partial] Archived is a first-class close result with IsArchived transitions for draft and open tasks; the CLI close command only accepts completed/rejected/failed. Sources: superplane:wotrans, superplane:cli.
Reopen [partial] The state model allows closed-to-open reopen and closed-to-draft send-to-backlog with transition enforcement; the surfaced UI/CLI path is unverified beyond the model. Sources: superplane:wotrans.
Project epic views [supported] The factory board shows Backlog/Implement/Verify/Done stages with task states, confidence and ownership. Sources: superplane:boardimg, superplane:overview.
Explicit dispatch [supported] The Start action dispatches approved work to the line; automated start requires narrow trusted rules. Sources: superplane:intake, superplane:backlog-auto.
Task session separation [supported] Tasks persist separately from runs; the run inspector shows inputs, outputs and paths per execution. Sources: superplane:automations, superplane:done.
Durable states [supported] Draft, open and closed states with completed/rejected/failed results persist through Done. Sources: superplane:agenttools, superplane:done.
External tracker requirement [partial] Trackers supply intake but execution, state and evidence live in SuperPlane; code and review still reside in the provider. Sources: superplane:intake, superplane:done, superplane:sourcecontrol.
Agents read, create, update and close the same durable task IDs humans use, claim/assign owners, change state with results and report scored checks through CLI, MCP and Bash with attribution and shared permissions. Dependencies, children and conflict handling have no implementation.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Dependencies, children, conflict handling and exclusive claim enforcement have no implementation.
14 atomic answers
Shared ids [supported] Agents operate on the same task IDs and keys humans see on the board. Sources: superplane:agenttools.
Read [supported] list_tasks, list_checks, list_members and artifact reads expose workspace tasks to agents. Sources: superplane:agenttools.
Create [supported] Agents create draft tasks with titles and descriptions, e.g. splitting complex work. Sources: superplane:agenttools.
Update [supported] Agents edit tasks, assign owners and report checks/artifacts on the current task. Sources: superplane:agenttools.
Claim [partial] Owner assignment with only-if-unassigned guard exists; exclusive claim enforcement against concurrent workers is unverified. Sources: superplane:agenttools.
Assign [supported] Agents assign owners from member IDs or GitHub logins with a visible reason. Sources: superplane:agenttools.
State changes [supported] Agents close tasks as completed, rejected or failed; drafts are rejected rather than completed. Sources: superplane:agenttools.
Dependencies [unsupported] No dependency or blocked-by fields exist on work orders; searched models and actions. Sources: superplane:wotrans.
Results [supported] Agents return results as scored checks with reasons and artifacts on the task. Sources: superplane:agenttools.
Human visibility [partial] Board, checks and artifacts reflect agent writes; live step-level visibility is inspector-mediated and unexercised beyond source. Sources: superplane:boardimg, superplane:automations.
Attribution [partial] Owner changes carry reasons; per-action agent attribution in shared views is unverified. Sources: superplane:agenttools.
Living product specifications have no implementation: no persistent cross-task requirements with attributable revisions, approvals, links, retrieval, drift detection or review integration exist; memories are workflow-scoped.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server, SuperPlane API (OpenAPI) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
9 atomic answers
Persistent requirements [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Human edits [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Agent edits [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Revisions [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Approvals [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Implementation links [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Later retrieval [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Drift detection [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Review integration [unsupported] No persistent product-specification object exists; planning-session analyses are per-session and memories are canvas-scoped. Searched models for requirement/specification objects (only unrelated fleet and session matches). Sources: superplane:canvasmem, superplane:automations.
Independent tasks run concurrently with plan caps (5 pay-as-you-go, unlimited paid) and a default per-step parallelism cap of 10 with slot queueing; the board shows running, waiting, failed and finished work by stage.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Concurrent tasks [supported] Parallel tasks are plan-gated (5 pay-as-you-go, unlimited Starter/Team) with conservative-concurrency guidance per line. Sources: superplane:pricing, superplane:automations.
Quotas [supported] Plan task caps and per-step MaxParallelism bound concurrency; waiters queue for released slots. Sources: superplane:pricing, superplane:maxpar.
Observed concurrency [supported] Concurrent sessions are established by plan quotas, per-step parallelism caps with slot queueing and org scheduling in docs and code; this catalog runs Sources: superplane:pricing, superplane:maxpar, superplane:dispatch.
Status visibility [supported] The board exposes stage, state badges (Agent question, Review, Mergeable, Merged, Closed), confidence and ownership per task. Sources: superplane:boardimg.
Tasks assign to human owners and to stage agents with a default subscription owner; routing follows named result channels and queues hold excess runs with admission locks. Duplicate-work prevention is partial and contention handling unverified.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Contention handling and hard exclusive ownership are unverified.
7 atomic answers
Human assignment [supported] Tasks assign to members by user ID or GitHub login with a visible reason. Sources: superplane:agenttools.
Agent assignment [supported] Automations assign agents per stage; Codex runs use the configured default task owner. Sources: superplane:implement-auto, superplane:byos.
Claims [partial] Only-if-unassigned assignment avoids clobbering owners; contention between two workers is unverified. Sources: superplane:agenttools.
Queues [partial] Parallelism slots with waiters queue excess runs; ordering and fairness semantics are unverified. Sources: superplane:maxpar.
Duplicate prevention [partial] Only-if-unassigned assignment guards plus dispatch admission locks and close-time queue drops that keep zombies from blocking re-dispatch; contention outcomes between live workers are unverified. Sources: superplane:agenttools, superplane:dispatch.
Ownership enforcement [partial] Ownership display plus advisory guards exist; enforced exclusive ownership is unverified. Sources: superplane:agenttools.
SuperPlane canvases sequence staged agent runs and retain their results. The injected agent tool inventory has no product-owned coordinator role that delegates to and inspects/messages other agent sessions; creating a backlog task is separate from dispatch.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Targeted first-party source check 2026-11-13. New implementation findings are pinned to eaa40c84cbf7b5e9852043d8a8f0d0b2b6461ce4. Unchanged atomic answers retain the individual source dates and revisions in their cited evidence. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
Not separately cross-checked
This source pass establishes only the named atomic answers. Other parts retain their documented source gaps; no hands-on test was performed.
Messages [partial] Agent questions surface on tasks and activity streams record runs; cross-agent messaging history is unverified. Sources: superplane:boardimg, superplane:automations.
Cross harness [unsupported] No cross-harness delegation is established: runner components coexist in the catalog but no canvas, template or doc combines harnesses with product-owned delegation tooling. Sources: superplane:components, superplane:schedtmpl.
Orchestration owner [partial] Deterministic factory canvases own stage sequencing. Runner agents receive task/check/artifact tools, without a coordinator agent role or delegation/session messaging tools. The official skill bundle covers CLI operation, canvas building and execution monitoring. Sources: superplane:gaps41-coordinator-tools, superplane:gaps41-official-skills.
Live progress [supported] The run inspector shows inputs, outputs, paths and step states with follow mode during execution. Sources: superplane:automations, superplane:boardimg.
Retained results [supported] Run records, checks, artifacts and branch/PR links persist on completed tasks. Sources: superplane:done, superplane:agenttools.
Followup [partial] Bounded correction loops return failures with context and update existing PRs; reopening finished work is unverified. Sources: superplane:verify, superplane:implement-auto.
Schedule (minutes-to-cron with timezones), issue/PR, Sentry and webhook triggers start work, including recurring scheduled-intake proposals and completion-conditioned Done rules. Scheduler server-side placement, overlap handling, retry policies and close-client behavior are only partly established.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Scheduler placement, overlaps, retry policies and close-client independence are partly verified.
8 atomic answers
Schedules [supported] Schedule triggers fire on minute/hour/day/week/month/cron patterns with timezone support. Sources: superplane:core, superplane:schedtmpl.
Scheduler location [partial] Scheduling is product-run (server-side templates and triggers); survival of trigger delivery across client closure is implied by durability but not stated. Sources: superplane:schedintake, superplane:implement.
Overlaps [partial] Bounded-retry and stop-when-stuck guidance exists; overlap/coalescing semantics are unverified. Sources: superplane:automations, superplane:implement.
Client independence [partial] Runs execute on managed or self-hosted infrastructure rather than the triggering client; explicit close-client trigger tests are unverified. Sources: superplane:implement, superplane:selfhost, superplane:costs.
Stop/cancel terminates runs with history preserved; steering via task prompts and follow-up loops, approval/agent-question decisions, escalation routes, recorded run errors and notifications are documented; resume continues from durable boundaries. Explicit pause, post-allow revocation and chat/terminal parity are unverified.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Pause semantics, revocation after allow, terminal parity and resume fidelity are unverified.
10 atomic answers
Pause [partial] Approval nodes pause for humans; a general user pause control distinct from cancel is unverified. Sources: superplane:core, superplane:approvalgo.
Stop [supported] Cancel-execution and cancel-run operations stop active runs asynchronously while tasks and history remain. Sources: superplane:cancelrun, superplane:releasenotes.
Resume [partial] Durable execution resumes from a known boundary after transient failures; mid-step resume fidelity is unverified. Sources: superplane:implement.
Chat terminal parity [partial] The CLI inspects and operates tasks but offers no conversational steering parity with the board prompt input. Sources: superplane:cli, superplane:agenttools.
Retained history [supported] Stopped work keeps task, run, check, artifact and decision history through Done. Sources: superplane:done, superplane:implement-auto.
The live production board shows work across Backlog/Implement/Verify/Done with failed, reviewing, mergeable, merged and closed states, attention badges and retained history; per-member load and performance views cover workload. Parent/child, dependency and error-navigation views have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Hierarchy, dependency and navigation-error views have no implementation.
8 atomic answers
Fleet fixture [partial] The production SuperPlane Prod board shows real backlog, running, verify-review and done states with failed, review, mergeable, merged and closed items; it is live data, not a constructed fixture. Sources: superplane:boardimg.
Parent child [unsupported] No parent/child relationships exist in the task model, so none can be shown. Sources: superplane:wotrans.
Dependencies [unsupported] No dependency objects exist to display. Sources: superplane:wotrans.
Attention [partial] Agent-question badges, approval waits, confidence bars and Review badges surface attention needs on the board. Sources: superplane:boardimg.
History [supported] Task records preserve source, discussion, checks, artifacts, retries and timestamps through Done. Sources: superplane:done.
Workload [partial] Member open-task counts and factory performance views show load; per-agent workload allocation views are unverified. Sources: superplane:agenttools, superplane:perfvel.
Navigation errors [unsupported] No navigation-error behavior is documented or implemented for fleet views. Sources: superplane:boardimg, superplane:overview.
Fixture mode [supported] Evidence shown is live production board data, not a simulated fixture. Sources: superplane:boardimg.
Quick fixes and growing lines share one canvas model with non-mandatory templates, natural-language automation edits and per-agent model/effort/machine/timeout config; live roles and retained relationships show in inspection. In-run editing, multi-reviewer capture and measured discovery/friction are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. In-run changes, reviewer multiplicities and measured discovery/friction are unestablished.
10 atomic answers
Quick task [supported] Small bounded tasks (bug, test fix, doc update, dependency bump) run the same line as larger work. Sources: superplane:quickstart.
Growing epic [supported] Lines grow from one task to multi-stage factories by extending canvases across Backlog/Implement/Verify/Done. Sources: superplane:automations, superplane:overview.
Natural language [supported] Describing the outcome to the agent proposes canvas changes, integrations and rewiring within permissions. Sources: superplane:automations.
In run changes [partial] Canvas edits stage per user with stale-version rejection; editing live running executions is unestablished. Sources: superplane:staging.
Live roles [partial] The inspector shows the executing path and step roles during runs; a two-reviewer live capture is unverified. Sources: superplane:automations, superplane:boardimg.
Retained relationships [supported] Completed runs retain paths, roles, results and artifacts on the task record. Sources: superplane:done, superplane:automations.
Discoverability [partial] Docs navigation, quickstart and guided setup document discovery; measured discovery is outside this catalog’s source-and-code process. Sources: superplane:how, superplane:quickstart.
Auth friction [partial] Token, OAuth and secret flows are documented with revocation; measured friction is outside this catalog’s process. Sources: superplane:cli, superplane:mcp, superplane:security.
Agents execute on SuperPlane-managed Linux machines or self-hosted servers, never on the user laptop; per-node timeouts bound runs; durable execution plus web and badge clients imply laptop independence, with explicit disconnect/continuation tests unestablished. Idle and maximum lifetimes are unverified.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Run lifetimes and explicit disconnect/continuation tests are unverified.
12 atomic answers
Local [unsupported] No laptop-local execution target exists: documented targets are managed Linux machines or self-hosted servers, with no local-runner mode after checking setup, install and CLI sources. Sources: superplane:costs, superplane:selfhost, superplane:quickstart.
Byo remote [supported] Single-VM Docker Compose and Enterprise Kubernetes installs run agent work on user-owned servers with Fleet Manager runner VMs. Sources: superplane:selfhost, superplane:selfinstall.
Managed cloud [supported] SuperPlane Cloud runs agents on managed machines with sandbox time metered from credits; no usage allowance exists and managed machine sizes and rates are unpublished. Sources: superplane:billing, superplane:pricing.
Hybrid [partial] BYOK/BYOS splits model billing from SuperPlane machine billing; cloud control with self-hosted runners is unverified. Sources: superplane:byok, superplane:byos, superplane:modelsrc.
Provisioning [partial] Self-hosted runner architectures (x64/ARM64) and Terraform plans are documented; managed provisioning internals and machine sizes are unpublished. Sources: superplane:selfhost, superplane:selfinstall, superplane:billing.
Payer [supported] The organization pays subscription plus metered usage from a centralized prepaid balance; members incur no per-seat compute fee. Sources: superplane:pricing, superplane:billing.
Expiry [partial] Per-node execution timeouts bound runs and runners report idle/busy with expiring registrations; idle and maximum run lifetimes are unverified. Sources: superplane:claudespec, superplane:runneridle.
Client disconnect [partial] Durable execution resumes from known boundaries after interruptions; an explicit originating-client disconnect test is unverified. Sources: superplane:implement.
Other device continuation [partial] The web board and task records are reachable from any device; an explicit continue-from-another-device test is unverified. Sources: superplane:boardimg, superplane:done.
Runner components execute arbitrary code in dedicated isolated ephemeral VMs or containers destroyed afterwards; Daytona sandboxes isolate repo work; per-task branches separate code; secrets are AES-256 and memory-only. Worktrees and finer process/network/OS boundaries are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Worktrees, OS-sandbox machinery and boundary specifics are unestablished.
12 atomic answers
Checkout [partial] A shared default-branch clone helper exists; per-task checkout isolation semantics are unverified. Sources: superplane:schedintake.
Branch [supported] Implementation works on per-task branches and updates or creates pull requests. Sources: superplane:implement-auto.
Container [supported] Runner components run in containers and Daytona provides isolated sandbox environments. Sources: superplane:security, superplane:daytona.
Vm [supported] Arbitrary-code runners execute in dedicated isolated ephemeral virtual machines destroyed after execution. Sources: superplane:security.
Os sandbox [partial] Container and ephemeral-VM isolation serve as the sandbox boundary; a dedicated OS-sandbox mechanism is unverified. Sources: superplane:security, superplane:daytona.
Filesystem [partial] Ephemeral isolated environments separate runs; filesystem boundary specifics are unverified. Sources: superplane:security.
Process [partial] Separate ephemeral environments per run separate processes; process-boundary specifics are unverified. Sources: superplane:security.
Network [partial] Isolated execution environments are documented; network egress policy is unverified. Sources: superplane:security.
Secrets [supported] Secrets are AES-256 encrypted at rest and decrypted in memory only for the step that needs them. Sources: superplane:security.
Code separation [partial] Separate ephemeral environments per run separate code; a two-change separation test was not performed. Sources: superplane:security, superplane:daytona.
Security boundary [partial] Ephemeral isolation is documented for accidental interference, not as hostile-code containment; no separate security evidence was checked. Sources: superplane:security.
Durable execution records state between steps so transient failures resume from known boundaries with websocket refetch on reconnect; idempotency keys guard usage records; task/run/check/artifact history persists. Explicit crash, restart, expiry and multi-day tests are unrecorded.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Live recovery behaviors have no implementation-level tests recorded.
12 atomic answers
Client disconnect [partial] Durability implies survival across interruptions; a controlled disconnect test is unverified. Sources: superplane:implement.
Service restart [partial] Boundary resume covers service interruptions; a restart test is unverified. Sources: superplane:implement.
Expiry [partial] Ephemeral runners are destroyed after execution; sandbox-expiry continuity beyond boundary resume is unverified. Sources: superplane:security, superplane:implement.
Transcript reload [partial] Run history and task records persist for review; reload-after-restart semantics are unverified. Sources: superplane:done, superplane:automations.
Process reconnect [partial] Boundary resume plus websocket invalidation and refetch on reconnect re-establish state; process-level reconnection semantics are unverified. Sources: superplane:implement, superplane:wsreconnect.
Task resume [partial] Tasks resume via boundary continuation and correction loops; full state-reconstruction fidelity is unverified. Sources: superplane:implement, superplane:verify.
State reconstruction [partial] Preserved inputs/outputs/paths support reconstruction; completeness is unverified. Sources: superplane:automations, superplane:done.
Context loss [partial] Resume preserves recorded state; unrecorded-context loss modes are unlisted. Sources: superplane:implement.
Duplicate actions [partial] Usage records carry idempotency keys against double counting; action-duplication behavior is otherwise unverified. Sources: superplane:idempot, superplane:implement.
Manual repair [partial] Docs direct investigating repeated failures, narrowing scope and stopping for access or approval; observed repair is outside this catalog’s process. Sources: superplane:implement, superplane:costs, superplane:automations.
Multi day continuity [partial] Durability plus persistent history support long continuities; an explicit multi-day case is unrecorded. Sources: superplane:implement, superplane:done.
Repository cloning with idempotent bootstrap, external service integrations, preview URLs and secret injection are implemented; caches, snapshots and collision handling have no implementation; clean-host repair and automatic diagnosis are unverified.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Caches, snapshots and collisions have no implementation.
10 atomic answers
Dependencies [partial] Repo clone plus bootstrap scripts prepare dependencies; lockfile/cache handling specifics are unverified. Sources: superplane:daytona, superplane:implement-auto.
Caches [unsupported] No dependency-cache handling exists in runner specs or environment setup; only clone plus bootstrap scripts. Sources: superplane:implement-auto, superplane:daytona.
Ports [partial] Sandbox preview URLs expose ports; allocation and collision handling are unverified. Sources: superplane:daytona.
Secrets [supported] Organization secrets inject into steps and SSH hosts without touching logs or prompts. Sources: superplane:custom, superplane:security.
Duplicate installs [partial] Bootstrap scripts are idempotent over plain HTTPS URLs; duplicate-install handling is otherwise unverified. Sources: superplane:checkout.
Collisions [unsupported] No port-allocation or collision handling exists in runner or sandbox code. Sources: superplane:daytona.
Per-node execution timeouts, async cancellation, webhook retry fields, transient-vs-code failure routing and group/user/workspace budgets with maximum spend per task bound runs. Turn and token caps have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Turn/token limits and enforcement behavior have no implementation.
Spend limits [supported] Budgets per group, user or workspace plus a maximum spend per task cap consumption. Sources: superplane:pricing, superplane:costs.
Retries [partial] Transient errors retry while code failures return with context; retry counts and backoff are unverified. Sources: superplane:implement, superplane:custom.
Provider failures [partial] Execution failure (credential/runtime/provider) is distinguished from verification failure with separate routes. Sources: superplane:verify, superplane:implement.
Enforcement [partial] Limits and budgets are documented as controls; block-vs-warn enforcement behavior is unexercised beyond docs. Sources: superplane:pricing, superplane:costs.
Usage export [supported] The full task-run spend ledger exports as CSV with no window or page cap, alongside usage APIs and billing records. Sources: superplane:usageexport, superplane:billing.
Task stats [partial] Task-time and per-task cost views track delivery; statistical depth is unverified. Sources: superplane:costs, superplane:how.
Agent stats [partial] Agent runs report turns, tokens and cost per execution; aggregate agent statistics are unverified. Sources: superplane:costs, superplane:boardimg.
Project stats [partial] Factory performance views aggregate by workflow and automation; project-level exports are unverified. Sources: superplane:costs.
Time stats [partial] Timing appears across runs, stages and per-task trends; time-series exports are unverified. Sources: superplane:costs, superplane:backlog-auto.
Failure status [partial] Failed, blocked, awaiting-input, reviewing and completed states show distinctly; induced-failure agreement is unverified. Sources: superplane:boardimg, superplane:verify.
Approval status [partial] Approval and agent-question states surface pending decisions; post-reconnect agreement is unverified. Sources: superplane:boardimg, superplane:core.
Reconnect consistency [supported] The factory websocket reconnects indefinitely and invalidates plus refetches work-order queries on reconnect. Sources: superplane:wsreconnect.
Performance method [partial] Factory performance attributes its delivery, time and cost figures to 14d/30d reporting windows with sample-size caveats; this catalog measures none. Sources: superplane:perfvel.
Responsiveness [unsupported] No UI timing figures exist in docs or code; searched performance and timing terms. Sources: superplane:overview, superplane:boardimg.
Closed-task cost reporting shows token and compute spend with a per-task median trend; managed billing (provider rate plus 10%), own-key and subscription billing plus separate sandbox/machine charges and budget signals are documented. Session/child/epic granularity, refresh cadence, drill depth and hourly rates are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Finer granularity, refresh behavior, drill depth and hourly rates are unestablished.
14 atomic answers
Task cost [supported] Cost reporting attributes token and compute spend to closed tasks with a per-task median trend. Sources: superplane:costs.
Session cost [partial] Run-level inputs/outputs show per-execution spend; session aggregation semantics are unverified. Sources: superplane:costs, superplane:automations.
Child cost [unsupported] The cost ledger is per task-run; child/subagent cost granularity does not exist. Sources: superplane:costs, superplane:usageexport.
Epic cost [partial] Automation tables show average/total cost per workflow; epic-level aggregation is unverified. Sources: superplane:costs.
Harness aggregation [partial] Token use is recorded across the workspace model source; cross-harness aggregation is unverified. Sources: superplane:costs, superplane:modelsrc.
Billed vs estimated [supported] Managed tokens bill at provider rate plus 10%; own keys and subscriptions bill outside SuperPlane; machine time always bills to SuperPlane usage. Sources: superplane:billing, superplane:modelsrc, superplane:pricing.
Tokens [supported] Recorded model input/output usage underlies token cost categories. Sources: superplane:costs.
Subscription allowance [partial] ChatGPT plans cover Codex model use; allowance amounts and marginal-cost accounting are unverified. Sources: superplane:byos.
Provider reconciliation [partial] Usage snapshots are saved at sign-in and during runs; full provider-statement reconciliation is unverified. Sources: superplane:byos, superplane:billing.
Compute cost [partial] Sandbox and machine time is a separate usage charge on credits; hourly rates are unpublished on current pages. Sources: superplane:billing, superplane:pricing.
Refresh delay [unsupported] Cost-report refresh cadence is unpublished in docs and code. Sources: superplane:costs.
Alerts [partial] Budget signals and spending reviews are documented; threshold configuration and delivery are unverified. Sources: superplane:costs, superplane:pricing.
Per-step parallelism caps (default 10 in-flight) with slot queueing, published self-hosted runner architectures, check-dedup indexing and async cancellation implement compute-aware scheduling with per-organization demand sharing. Host awareness, fairness policy, shared limits and bounded load behavior are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Host awareness, fairness, shared limits and load tests are unestablished.
12 atomic answers
Concurrency [supported] MaxParallelism caps in-flight runs per step (default 10); lines set conservative concurrency for shared repos. Sources: superplane:maxpar, superplane:automations.
Queues [supported] Parallelism slots queue waiters that move in as runs release; queued steps show in the inspector. Sources: superplane:maxpar, superplane:automations.
Backpressure [partial] Bounded loops and stop-when-stuck rules shed load; explicit throttling signals are unverified. Sources: superplane:implement, superplane:verify.
Host awareness [unsupported] No per-host resource awareness exists in scheduler code; scheduling is org-credit gated. Sources: superplane:maxpar, superplane:orgsched.
Check reuse [partial] Workflow event checks carry a dedup-key index for pull-request checks and webhook delivery; reuse policy across verifications unverified. Sources: superplane:dedup.
Check deduplication [partial] Dedup indexing keys checks per workflow, node and pull-request identity; deduplication guarantees unverified. Sources: superplane:dedup.
Bounded tests [partial] Queue and slot mechanics that a bounded test would exercise are implemented in dispatch and scheduler code; executing a load test is outside this catalog’s source-and-code process. Sources: superplane:dispatch, superplane:maxpar.
Authorized workspace users can prompt the same product planning session. Each message retains its human user ID and participation adds the sender as a draft assignee. This establishes shared planning prompts, without claiming simultaneous keystroke presence or conflict handling.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Targeted first-party source check 2026-11-13. New implementation findings are pinned to eaa40c84cbf7b5e9852043d8a8f0d0b2b6461ce4. Unchanged atomic answers retain the individual source dates and revisions in their cited evidence. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
Not separately cross-checked
This source pass establishes only the named atomic answers. Other parts retain their documented source gaps; no hands-on test was performed.
11 atomic answers
Visibility [supported] The shared board shows tasks, states, confidence and ownership to the whole workspace. Sources: superplane:boardimg, superplane:overview.
Comments [supported] Work-order comments persist on tasks. Sources: superplane:agenttools.
Presence [unsupported] No presence or typing indicators exist; the only presence match is an unrelated fanout default in canvas code. Sources: superplane:wsreconnect, superplane:boardimg.
Coprompting [supported] The same planning-session ID accepts messages from authorized users without a creator-only restriction. Sources: superplane:gaps41-planning-sharing.
Ordering [unsupported] No input-ordering mechanism exists for shared work. Sources: superplane:agenttools.
Conflicts [unsupported] No input-conflict handling exists. Sources: superplane:agenttools.
Attribution [supported] SendUserMessage stores the human user ID; participating users are added to draft assignees. Sources: superplane:gaps41-planning-sharing.
Permissions [supported] Org roles and workspace access scope who can see and change shared work. Sources: superplane:rbac.
Plan restrictions [supported] Seat caps (10 pay-as-you-go/Starter, 50 Team) and task-parallelism caps bound team use. Sources: superplane:pricing.
Owner online [partial] Server-side durable execution implies the owner need not stay online; an explicit statement is unverified. Sources: superplane:implement.
Org roles admin/maintainer/operator with documented canvas, factory, integration, secret, member and API-key permissions plus source-visible casbin enforcement, member lifecycle management, anytime access revocation and Enterprise SSO with automated provisioning govern access.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. SSO/provisioning setup flows are documented for sales scoping only.
9 atomic answers
Organization roles [supported] Three org roles separate operator reads, maintainer configuration and admin membership control. Sources: superplane:rbac.
Membership [supported] Members are listed with roles and open counts, added/updated/removed by admins. Sources: superplane:agenttools, superplane:rbac.
Sso [supported] Enterprise plans include SSO and automated user provisioning; setup specifics live behind sales scoping. Sources: superplane:pricing.
Provisioning [partial] Automated provisioning is an Enterprise entitlement; provisioning flows are documented for sales scoping only. Sources: superplane:pricing.
Unauthorized access [supported] Casbin-backed authorization checks organization permissions per user, resource and action in source, scoped by plan-tier roles. Sources: superplane:rbac, superplane:authz.
Revocation [supported] Access can be revoked anytime from the version-control provider or third-party tool settings, and MCP connections are revocable per connection. Sources: superplane:security, superplane:mcp.
Plan scope [supported] Custom roles, groups, audit logs, SSO, retention configuration and provisioning are Enterprise-scoped; core roles span all plans. Sources: superplane:pricing.
Tool [partial] Integration actions run under secrets with minimum scopes; per-tool approval matrices are unverified. Sources: superplane:security, superplane:sourcecontrol.
Network [unsupported] No network-scoped approval exists; approval gates are generic workflow nodes. Sources: superplane:core, superplane:custom.
Secret [partial] Secrets are encrypted, memory-only and never logged; secret-scoped approval flows are unverified. Sources: superplane:security, superplane:custom.
Revoke [unsupported] No approval-revocation operation exists in the approval component. Sources: superplane:approvalgo.
Tunnels [unsupported] No temporary-access tunnels exist; only a localhost webhook dev note and Cloudflare infrastructure tunnels. Sources: superplane:custom.
Defaults [unsupported] No documented default-access posture exists; runners receive task-scoped injected credentials without a stated default model. Sources: superplane:security, superplane:agenttools.
Safer modes [unsupported] No safer execution modes are documented or implemented. Sources: superplane:security.
Enforcement [supported] The workflow pauses until required approvals arrive; gates are product-enforced, not prompt conventions. Sources: superplane:core, superplane:approvalgo.
Task records attribute actions, approvals, edits, discussion and checks with cross-user and cross-session persistence through Done plus CSV/API/CLI export; limited retention auto-deletes (Enterprise configurable) with Enterprise audit logs. Mutability controls and integrity modeling are only partly established.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Mutability controls and integrity modeling are partly established.
Mutability [partial] Checks are replaceable by key and comments append-only with mentions and run refs; full history deletion happens only through account deletion. Sources: superplane:agenttools, superplane:security.
Retention [partial] Logs and metadata are retained for a limited period then auto-deleted; Enterprise configures retention. Sources: superplane:security, superplane:pricing.
Integrity [partial] Enterprise administrative audit logs and an encryption auditor exist; a tamper-evidence model is unverified. Sources: superplane:pricing, superplane:security.
Verify columns, Review-number links, merge-confidence scoring, agent reviews, PR-feedback loops and completion-rule guidance structure review with evidence navigation; keyboard and narrow-screen support are minimal; effort, missed-evidence and context-switching measures have no implementation. The badge client adds toast-driven review with per-file diffs and merge control.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Effort, missed-evidence and context-switching measures have no implementation.
13 atomic answers
Pending reviews [supported] Verify columns and Review-number badges collect work awaiting review. Sources: superplane:boardimg, superplane:verify.
Change understanding [supported] Agent reviews assess merge confidence with remaining concerns plus PR evidence. Sources: superplane:verify, superplane:boardimg.
Missed evidence [unsupported] No missed-evidence analysis exists. Sources: superplane:verify.
Keyboard [partial] A Meta/Control+Enter send shortcut with aria-keyshortcuts is implemented in task creation; navigation shortcuts are unverified. Sources: superplane:kbd.
Narrow screen [partial] The mobile board layout serves narrow screens; an explicit narrow-screen support statement is unverified. Sources: superplane:mobileboard.
Context switching [unsupported] No context-switching measures exist. Sources: superplane:automations.
Roles [partial] Stage agents and reviewer roles show in runs and inspector; reviewer-clarity measures unverified. Sources: superplane:automations, superplane:boardimg.
Retained context [partial] Tasks bundle source, implementation and verification context for later review; preservation measures unverified. Sources: superplane:done, superplane:verify.
A second authorized person continues work through owner reassignment with the full shared task record after the first person leaves. Runtime-context fidelity and model/harness transfer have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Runtime and harness transfer have no implementation.
12 atomic answers
Ongoing takeover [partial] A second person continues work through owner reassignment with the shared task record; runtime fidelity unverified. Sources: superplane:agenttools, superplane:done.
Same task [partial] Takeover continues the same task with its history and artifacts; live runtime handoff unverified. Sources: superplane:agenttools, superplane:done.
Session history [supported] Task, run, check and decision history persists for the next person. Sources: superplane:done.
Ownership [supported] Tasks reassign to new owners with reasons and anti-clobber guards. Sources: superplane:agenttools.
Attribution [partial] New owners and prior history stay visible; per-action re-attribution unverified. Sources: superplane:agenttools, superplane:done.
Context loss [partial] The shared record limits loss; fidelity gaps unverified. Sources: superplane:done.
Harness transfer [unsupported] No model or harness transfer path exists; a forked transcript or shared link is not full takeover. Sources: superplane:agenttools, superplane:done.
Branch/commit/PR links, scored checks, file artifacts, visual evidence and sandbox preview URLs attach to tasks and persist through Done with per-task retrieval; cross-task galleries, recordings, leakage controls and reviewer reopening have no implementation.
Scope
Surfaces: SuperPlane web app (factory board), SuperPlane CLI, SuperPlane MCP server · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Galleries, recordings, leakage controls and child retrieval have no implementation.
Factories choose required checks (repo tests, lint, types, CI, task-specific checks) before execution, add independent agent review plus human approval gates, and treat agent completion as insufficient without verification. Spec-conformance checking has no living spec behind it, and block/merge enforcement details are unverified.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Enforcement depth and blocking guarantees are unverified.
11 atomic answers
Tests [partial] Required test commands run in Implement and Verify; mandatory-vs-optional is per-factory configuration. Sources: superplane:implement-auto, superplane:verify.
Lint [partial] Lint commands join the required-check set per factory; enforcement depth unverified. Sources: superplane:implement-auto.
Ci [supported] CI integrations wait for pipeline results and attach them as task checks. Sources: superplane:cicd, superplane:verify.
Independent review [supported] Agent review (merge confidence with concerns) plus human approval gates stand apart from the implementing agent; an agent pass never self-certifies. Sources: superplane:verify, superplane:core.
Spec checks [partial] Task requirements are checked as task-specific evidence; no living spec exists to conform against. Sources: superplane:verify, superplane:intake.
Required checks [partial] Factories choose required checks before execution; mandatory-vs-optional is per-factory configuration. Sources: superplane:implement-auto.
Failure blocking [partial] Failed checks return work to implementation in a bounded loop; hard delivery blocking unverified. Sources: superplane:verify.
Source-control components create and update branches and pull requests with explanations, respond to review comments and CI, and offer merge/squash/rebase completion; worktrees and branch-update rebase mechanics are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Worktrees and rebase mechanics are unestablished.
9 atomic answers
Branches [supported] Implementation creates per-task branches and reuses them across correction attempts. Sources: superplane:implement-auto.
Worktrees [unsupported] No git-worktree implementation exists; searched worktree terms across pkg and cmd. Sources: superplane:implement-auto.
Pull requests [supported] Pull requests are created or updated with change explanations, checks and uncertainty notes. Sources: superplane:implement-auto.
Ci response [supported] Required pipelines are triggered, awaited and attached as checks with failure routing. Sources: superplane:cicd, superplane:verify.
Rebase [partial] The merge component offers merge, squash and rebase methods; branch-update rebasing unverified. Sources: superplane:mergepr.
Conflicts [partial] Merge-conflict awareness appears in task content and confidence review; handling mechanics unverified. Sources: superplane:boardimg, superplane:verify.
Product state [partial] Agents run git within product-owned steps with attached artifacts; step-vs-prose separation unverified. Sources: superplane:implement-auto.
Approval gates with user/group/role approvers authorize continuation, factories may include merge in completion rules or leave it to repo owners, and production deploys require approval and policy checks. Revision binding and authority tests are unestablished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Revision binding and authority tests are unestablished.
Merge [partial] Factories may include merge in the completion rule or leave it to repo owners; merge authority mechanics unverified. Sources: superplane:done.
Release [partial] Delivery components run release jobs behind approvals; release authority tests unverified. Sources: superplane:cicd, superplane:core.
Exact revision [unsupported] No exact-revision check binding exists; searched revision and approval-on-commit terms. Sources: superplane:verify, superplane:done.
Authority enforcement [partial] Roles plus approval configuration draw the boundary; a documented authority test unverified. Sources: superplane:rbac, superplane:core.
Tasks link to commits, branches and PRs with build/check evidence, Done delivery states and retained history for review; approval invalidation, rollback and revert have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Invalidation, rollback and revert have no implementation.
Pr links [supported] Pull requests link to tasks with explanations and checks. Sources: superplane:implement-auto.
Build links [partial] CI results attach as checks; build-artifact links unverified. Sources: superplane:cicd, superplane:verify.
Deployment links [partial] Delivery components run releases; deployment link persistence unverified. Sources: superplane:cicd.
Delivery status [supported] Done states record whether work is ready-for-review, approved or merged per factory rules. Sources: superplane:done, superplane:boardimg.
Retained evidence [supported] Checks, outputs, approvals, retries and timestamps persist on completed tasks. Sources: superplane:done.
Rollback [unsupported] No rollback implementation exists. Sources: superplane:done.
The live board queues reviewable work with summaries, stage grouping, retained reviewer findings, artifact navigation and request-changes loops; risk/size filters, dependency-aware queues and stale-approval invalidation have no implementation.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Filters, dependency queues and invalidation have no implementation.
12 atomic answers
Review queue [partial] Verify columns queue reviewable tasks with Review-number badges on the live board; a dedicated high-volume queue view is unverified. Sources: superplane:boardimg.
Summaries [supported] Task cards summarize work with state, confidence, owner and check badges. Sources: superplane:boardimg.
Next actions [partial] Completion rules state whether Done means ready-for-review, approved or merged; per-item next actions beyond that are unverified. Sources: superplane:done.
The public repository engine is Apache License 2.0; Enterprise-only capabilities (Kubernetes install, SSO, audit logs, configurable retention) ship under a separate commercial Enterprise Edition license requiring Terms acceptance and a valid Enterprise license.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Enterprise-only features sit outside the Apache 2.0 grant under the EE License.
Hosted extensions [partial] Enterprise-only capabilities ship under the separate commercial EE License. Sources: superplane:eelicense.
Source visibility [supported] Engine, web UI, API definitions, integrations and tests develop in public on GitHub. Sources: superplane:opensource, superplane:repo.
Community single-VM and Enterprise Kubernetes installs run the factory on user infrastructure with own model costs; code and credentials stay in-network on self-host. Required vendor services and data portability beyond usage export are only partly covered.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. Import and full portability have no implementation.
Formats [partial] CSV for usage; standard task/history formats unverified. Sources: superplane:usageexport.
Cancellation [partial] Users may terminate accounts anytime with outstanding fees due; account deletion permanently destroys data, secrets and history. No trial tier exists on current pages. Sources: superplane:terms, superplane:security.
Account independence [partial] Self-hosted factories run without a vendor account; the operator secures the environment. Sources: superplane:security, superplane:selfhost.
SuperPlane discloses cloud data handling and product analytics. Self-hosted operators can disable product analytics by leaving POSTHOG_KEY unset; both browser and server skip PostHog without a key. Hosted-user controls and operational tracing are separate.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Targeted first-party source check 2026-11-13. New implementation findings are pinned to eaa40c84cbf7b5e9852043d8a8f0d0b2b6461ce4. Unchanged atomic answers retain the individual source dates and revisions in their cited evidence. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
Not separately cross-checked
This source pass establishes only the named atomic answers. Other parts retain their documented source gaps; no hands-on test was performed.
15 atomic answers
Code data [supported] Repositories clone into ephemeral isolated environments; source is not permanently stored on vendor servers. Sources: superplane:security.
Prompts [partial] Task context including files, diffs and issue text goes to model providers via secure APIs; exact field scope unverified. Sources: superplane:security.
Credentials [supported] Secrets are AES-256 encrypted at rest and decrypted in memory only for the requiring step. Sources: superplane:security.
Logs [supported] Workflow metadata, logs, issue descriptions and PR summaries are stored for visibility and debugging. Sources: superplane:security, superplane:privacy.
Retention [supported] Logs and metadata are retained for a limited period then auto-deleted; Enterprise configures retention. Sources: superplane:security, superplane:pricing.
Deletion [supported] Account deletion permanently destroys associated data, secrets and history from active systems. Sources: superplane:security.
Training [supported] Managed models enforce Zero Data Retention through OpenRouter; own-key usage follows provider terms. Sources: superplane:security, superplane:byok.
Residency [supported] Cloud infrastructure runs on major providers (AWS/GCP) in the United States. Sources: superplane:security.
Subprocessors [partial] OpenRouter routing and an unnamed payment processor are disclosed; a full list unverified. Sources: superplane:security, superplane:privacy.
Telemetry disclosure [supported] The pinned product analytics guide documents account and factory lifecycle events and their data rules. Sources: superplane:gaps41-analytics.
Telemetry controls [supported] Leave POSTHOG_KEY unset on a self-hosted installation to prevent both server and browser product analytics initialization. Sources: superplane:gaps41-analytics.
Consent prompt [unsupported] No first-run consent or telemetry prompt exists in the web app or docs; searched consent, banner and GDPR terms. Sources: superplane:privacy.
Provider separation [partial] Orchestration-vendor and model-provider policies are separated via ZDR and own-key terms. Sources: superplane:security, superplane:byok.
Current commercial terms (billing and pricing pages, 2026-11-12): pay-as-you-go $0 per organization per month plus usage, Starter $20 per organization per month plus usage, Team $50 per user per month plus usage, Enterprise custom; credits fund sandbox time, charged separately under every model source, and SuperPlane-provided tokens at provider rate plus 10% (Enterprise custom); own keys and ChatGPT subscriptions carry no token markup. Top up or schedule automatic purchases; pay-as-you-go requires a card; budget controls live on Team and Enterprise.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Enterprise is quote-only; hourly sandbox rates and tax treatment are unpublished.
12 atomic answers
Currency [supported] USD pricing and rates; prices stated in United States dollars with usage additional to the monthly plan fee. Sources: superplane:pricing, superplane:billing.
Seats [supported] 10 seats on pay-as-you-go and Starter, up to 50 on Team, unlimited on Enterprise. Sources: superplane:pricing.
Seat minimum [supported] Plan seat caps act as tier minimums/maximums as published. Sources: superplane:pricing.
Workspace fees [supported] Per-organization subscription plus metered usage; flat-plan members add no fee. Sources: superplane:pricing, superplane:billing.
Included usage [partial] No included usage allowance; plan fees plus metered usage draw from the credit balance with auto-purchase. Sources: superplane:pricing, superplane:billing.
Credits [supported] Buy credits for sandbox time and SuperPlane-provided tokens; top up anytime or schedule automatic purchases. Sources: superplane:pricing, superplane:billing.
Trial [unsupported] No trial is offered on the current billing or pricing pages; the former 14-day Business trial description left with the page rewrite. Sources: superplane:billing, superplane:pricing.
Overages [supported] Usage beyond balances draws from prepaid credit with auto-purchase to avoid interruption. Sources: superplane:pricing, superplane:costs.
Model cost [supported] Managed models bill at provider rate plus 10% on pay-as-you-go, Starter and Team (Enterprise custom); own keys and ChatGPT subscriptions carry no token markup. Sources: superplane:pricing, superplane:modelsrc, superplane:billing.
Compute cost [partial] Sandbox and machine time is a separate usage charge on credits; hourly rates are unpublished on current pages. Sources: superplane:billing, superplane:pricing.
Generally available cloud (v1.0.0 released 2026-10-27; repository active 2026-11-12) with Discord, docs and bug-report support, Enterprise priority support and weekly-scale release activity. Response-time commitments, status history and deprecation/export options are undocumented.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. SLAs, status history and deprecation/export options are undocumented.
8 atomic answers
Release stage [supported] v1.0.0 shipped 2026-10-27 with runner/fleet releases; the cloud app and docs are live. Sources: superplane:releases, superplane:repo.
Access restrictions [partial] Enterprise Kubernetes installs need an Enterprise license; workspaces are invite/token-gated. Sources: superplane:selfhost, superplane:cli.
Response commitments [partial] Priority support is Enterprise-scoped; response-time numbers unpublished. Sources: superplane:pricing.
Release activity [supported] Release candidates through October 2026 plus latest default-branch activity on 2026-11-12 show maintenance. Sources: superplane:releases, superplane:repo.
Status history [unknown] Availability and support, status_history: hosted-service fact; no status page or history is published and the repository cannot answer for the hosted service.
Deprecation [unknown] Availability and support, deprecation: business fact; no deprecation policy is published.
Export options [unknown] Availability and support, export_options: business fact; no data-export policy beyond the usage-ledger CSV is published.
Evaluation runs on pay-as-you-go ($0 per month plus metered usage, card required) and the Apache 2.0 community self-host download (own infrastructure and model costs). No trial tier exists on current pages; seat and task caps plus plan-gated features bound each route.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the cited atomic findings are established. No trial exists on current pages and cloud evaluation always bills usage outside self-host.
10 atomic answers
Ongoing free [partial] The free Apache 2.0 community self-host download is the recurring free route; cloud pay-as-you-go carries metered usage. Sources: superplane:opensource, superplane:pricing.
Paid only [partial] Paid plans gate parallel capacity, API keys and Enterprise controls; core evaluation does not require them. Sources: superplane:pricing.
Pricing is partially specified: public per-org/per-seat prices, sandbox-time charges, model +10% markup, credit auto-purchase, minimums and account termination terms are published, but Enterprise is quote-only and hourly rates, tax treatment and termination details beyond closure are unpublished.
Scope
Surfaces: SuperPlane web app (factory board) · Version: Engine eaa40c84 (2026-11-12); cloud docs pass 2026-11-12; releases v1.0.0 (2026-10-27), fleet-manager v0.1.7 (2026-10-28) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Enterprise is quote-only; hourly rates, tax treatment and termination details beyond closure are unpublished.
9 atomic answers
Units [supported] Per-organization, per-seat, sandbox-time and provider-rate units are published. Sources: superplane:pricing, superplane:billing.
Included limits [partial] Seat caps, task-parallelism caps, plan feature matrices and credit balances state included limits; no usage allowance is included. Sources: superplane:pricing, superplane:billing.
Overages [supported] Usage beyond balances draws prepaid credit with auto-purchase; managed-model markup is fixed at 10%. Sources: superplane:pricing, superplane:costs.
Model markup [supported] Managed models pass provider rates through with a disclosed 10% fee; own keys bill outside. Sources: superplane:pricing, superplane:modelsrc.
Cancellation [supported] Users may terminate accounts anytime; rights cease and outstanding fees fall due. Sources: superplane:terms.
Sales only unknowns [partial] Enterprise price, SSO/audit/retention configuration and Bedrock providers are sales-scoped. Sources: superplane:pricing.
Transparency classification [partial] Partially specified: units, limits, overages and markups are published, but Enterprise is quote-only and hourly sandbox rates, tax treatment and termination details beyond account closure are unpublished. Sources: superplane:pricing, superplane:billing, superplane:terms.
Populated SuperPlane Prod board: Backlog holds items like GitHub-action token-refresh failure with Agent-question badges; Implement runs the Implement agent; Verify lists Dependabot fixes with Review #8887/Mergeable badges and confidence bars; Done lists merged (#8945) and closed (#8678) work with avatars.
Kind
documented
Locator
Full board: Backlog, Implement, Verify, Done columns with task cards, confidence bars, Review/Mergeable/Merged/Closed badges, filters All/My/Unassigned
Pipeline stages: Backlog (approved task with context), Implement (branch/PR with explanation), Verify (evidence or feedback), Done (completed task with preserved result/history); people and agents share the same view of work, evidence and decisions.
Kind
documented
Locator
Pipeline at a glance: Backlog, Implement, Verify, Done stage table
First run in under 5 minutes: create account, connect a GitHub repo through intake (recent issues auto-import), open the board across Backlog/Implement/Verify/Done; start with a small bug, test fix, doc update or dependency update; use defaults before changing agents, automations or verification.
Kind
documented
Locator
Prerequisites; 4 setup steps; Tips for your first run
Implement converts approved tasks to concrete changes; the factory owns sequence and guardrails while the coding agent inspects the repo, edits, runs checks and prepares review; durable execution records state between steps so runs resume from a known boundary instead of restarting; transient errors retry, failing tests return to the agent with output, product decisions pause for a person.
Kind
documented
Locator
Workflow vs agent jobs; typical run; durable execution
Workspace MCP server at https://app.superplane.com/mcp (remote Streamable HTTP) with OAuth sign-in, organization/workspace-scoped approval and per-connection revocation; documented Cursor mcp.json and Claude Code CLI registration; self-hosted installations use their own origin plus /mcp.
Product CLI via npm @superplane/cli (macOS/Linux x64/arm64; Windows not supported by npm distribution) or install script; API-token auth via SUPERPLANE_URL/SUPERPLANE_TOKEN with saved context; inspects workspaces and tasks (workspace active/list, tasks list, JSON output); connects to self-hosted origins without /api/v1 suffix.
Kind
documented
Locator
Install; API token auth; inspect workspaces/tasks; self-hosted connection
Agents manage factory work through MCP or the runner Bash superplane task CLI: list/create/close tasks with keys and states, list members with roles and open counts, assign owners (with only-if-unassigned), record/remove scored checks, attach/read/remove artifacts; SuperPlane injects per-run credentials and PATH; task queries use the current workspace; both interfaces share the same permissions.
Schedule trigger starts executions on minutes/hours/days/weeks/months/cron (5- or 6-field) schedules with timezones; Webhook trigger starts a chain when called; Approval pauses execution and waits for required approvers (users, groups or roles) with approved/rejected channels.
The React web app ships a dedicated mobile board layout (column carousel, bottom bar, mobile task creation and model selection), so the factory board is usable from a phone browser; no native iOS/Android app is present in the repository.
Kind
source-inspected
Locator
Line 87 MobileBoardPage component; sibling MobileBoardColumn/Carousel/Settings/BottomBar/CreateTask components
First-party badge client shows the same Backlog, Implement, Verify and Done lanes: hold SELECT starts tasks on Implement, Verify opens PRs with per-file diffs and hold-SELECT merges when SuperPlane reports mergeable, Done shows closing PRs; toast plus case lights signal waiting decisions.
Kind
documented
Locator
Lane table (Backlog/Implement/Verify/Done); Controls; Setup
The scoped core repository builds the hosted browser UI and Go server/companion CLI. Its public release inventory contains server, runner, fleet-manager and CLI artifacts, with no macOS/Windows/Linux desktop GUI. The first-party Remote_Control project is a hardware badge client, not a desktop GUI. No desktop-client repository appears in the checked public product inventory.
Kind
source-inspected
Locator
superplane repository entry points and release/ build targets; web_src/package.json; 20 public release tags; Remote_Control README; public organization repo inventory
Implement automation sets target repo/branch, task plus analysis, AGENTS.md-style instructions, build/test/lint commands, off-limit paths and required outputs (commit, branch, PR summary); source-control nodes attach branch/PR artifacts and update existing PRs rather than duplicating; agent failure output is recorded with logs; model/stage sizing and deterministic bookkeeping nodes control spend.
Kind
documented
Locator
Shape the agent; explicit repo actions; failure path; model spend
Maintainer/Admin connects a Claude, OpenAI or OpenRouter API key as the workspace model source; agents run on that key with provider-side billing and no 10% platform fee while machine time stays on SuperPlane usage; OpenAI API keys are separate from ChatGPT subscriptions.
Kind
documented
Locator
Connect the key; model choice; run and billing effects
Each member connects a personal ChatGPT subscription; the workspace selects ChatGPT subscriptions as its model source with a default task owner; each task runs Codex on its owner's subscription and allowed models; the plan covers model use while SuperPlane bills machine time; switching replaces the default owner on every intake including scheduled ones; Maintainer/Admin required.
Kind
documented
Locator
Connect ChatGPT; workspace source; assign work; what you pay
Each workspace runs agents on exactly one model source: SuperPlane-managed (provider rate +10%), own API key (Claude/OpenAI/OpenRouter, provider-billed), or ChatGPT subscriptions (owner plan covers Codex); the choice applies to every automation and switching replaces the agent; machine time is billed in all three routes.
Kind
documented
Locator
Compare the sources: SuperPlane, API key, ChatGPT subscriptions
Claude components run a managed agent in Anthropic's managed environment, run an autonomous coding agent against a repository that opens/updates a PR, send Messages API prompts, batch requests and fetch Claude Code usage metrics; Files API enabled per request with sessions scoped to the API key workspace.
Kind
documented
Locator
Run Managed Agent; Run Code Agent; Text Prompt; Files API
Cursor components launch cloud agents for asynchronous coding tasks and fetch team usage metrics (lines added/accepted, requests, subscription vs usage-based counts) via Cursor Admin API keys.
The Run Claude Code automation node is configured with machine type, ordered prompt/bash steps, agent credentials, model, thinking level, working directory, environment and a per-node execution timeout defaulting to the runner default; it links the canvas workflow to a Claude coding-agent run.
The Run Codex automation node mirrors the Claude node (machine type, steps, credentials, model, thinking level, timeout); companion modules manage ChatGPT-subscription credentials and token refresh, linking canvas workflows to Codex runs on owner subscriptions.
Billing overview now mirrors the pricing page: pay-as-you-go $0 plus usage (10 seats, 5 parallel tasks, card required), Starter $20 per organization plus usage (10 seats, unlimited parallel tasks), Team $50 per user plus usage (up to 50 seats, provider API keys, budget limits, priority support), Enterprise custom (SSO, audit logs, enterprise self-hosting and onboarding). Credits fund sandbox time, charged separately under every model source, and SuperPlane-provided tokens at provider rate plus 10% on pay-as-you-go, Starter and Team (Enterprise custom); own keys and ChatGPT subscriptions carry no token markup. Top up or schedule automatic purchases; budget controls live on Team and Enterprise.
Kind
documented
Locator
Choose a plan; Compare plan features; Understand usage charges (sandbox time, model use, funding); Self-hosting
Single-VM Docker Compose install on Linux or Enterprise Kubernetes (Terraform/Helm) on AWS/Azure/GCP; owner setup installs Fleet Manager which starts runner VMs from runner images; self-hosted users cover their own infrastructure and model costs; Kubernetes installs require an Enterprise license.
Kind
documented
Locator
Single VM; cloud install; Fleet Manager runner VMs
Connects tickets, coding agents, source control, CI and review; intake automations import matching tickets and record confidence; lines give agents a controlled path; verification and failure handling precede review; people keep decision control.
Kind
documented
Locator
Steps 1-6: import, assess, track, configure, verify, human control
Intake sources: GitHub issues/events, Jira, Linear, Sentry events; filter by repo/project/label/state; each task needs requested change, repo/area, source link and a confirming test or check; backlog automation assesses confidence before implementation starts.
Kind
documented
Locator
Choose a source; define imports; assess; try one task
GitHub manages issues, branches, PRs, comments, checks and repo events; GitLab/Bitbucket react to repo events and manage resources; Jira/Linear manage issues, ServiceNow service records; guidance requires dedicated minimum-scope connections able to read the backlog and create branches/PRs.
Source cloned into ephemeral isolated environments and not permanently stored; runner components run in dedicated isolated ephemeral VMs/containers destroyed after execution; secrets AES-256 encrypted, decrypted in memory only; human approvals plus RBAC; logs retained limited period then auto-deleted, account deletion destroys data; US hosting; ZDR via OpenRouter for managed models; GitHub/GitLab granular scopes revocable anytime; SOC 2 compliance actively being worked towards, not yet attained.
Publishes an OpenAPI 3 specification generated from application protobuf definitions for v1.0.0-rc7; spec download needs no auth but API requests require workspace credentials and permissions; self-hosted installations use their own base URL.
v1.0.0 published 2026-10-27, fleet-manager/v0.1.7 on 2026-10-28, runner/v0.2.1 on 2026-10-23, preceded by v1.0.0 release candidates rc4 through rc9 from 2026-10-22 to 2026-10-27.
Server exposes cancel-execution and cancel-run operations with a run-cancellation notifier; release notes confirm active runs can be cancelled asynchronously, so stop terminates execution while the task and its history remain.
Kind
source-inspected
Locator
cancel_execution.go and cancel_run.go actions; workers/run_cancellation_notifier.go
The product CLI tree spans tasks, runs, fleets, members, secrets, integrations, organizations, workspaces, automations, runners and OIDC commands; task operations include create, describe, list, dispatch, assign, close and checks plus five artifact operations.
Automations define per-stage triggers, agents, integrations, checks, failure routes and human decisions; editable via canvas or by describing the outcome to an agent (staged graph reviewed before save); deterministic nodes handle filters/status/routing/notifications; per-stage model choice; concurrency limits where tasks share a repo; focused failure context; repeated attempts stop when access, clarification or approval is needed.
Kind
documented
Locator
Policy outside prompts; edit canvas or via agent; cost controls; per-stage customization
Daytona components create isolated sandboxes, clone a repository, run bootstrap scripts, execute code/commands and delete the environment; clone plus bootstrap run sequentially with error returns.
First-party skills (superplane-cli, superplane-app-builder, superplane-monitor) help agents operate SuperPlane via npx skills add, with regression evals that spawn Claude Code sessions to assert commands and canvas YAML.
Workspace agent resources include an mcp_server kind capped at 20 enabled servers per factory, with URL validation, headers-or-OAuth auth and a list-enabled-servers query backing the settings pages.
MCP servers are managed through list/create/update/delete actions with public-HTTPS URL validation and browser-completed OAuth whose runner receives only a Bearer token.
Kind
source-inspected
Locator
validateMCPURL at line 422 (public-HTTPS URL check); List/Create/Update/Delete resource actions; browser OAuth completion
The PRD marks workspace MCP servers Implemented behind the experimental workspace_mcp flag, with headers-or-OAuth auth and injection at task build beside the first-party superplane server.
Kind
documented
Locator
Status line and locked decisions 2-4: Implemented for MCP connections; experimental workspace_mcp flag; headers-or-OAuth; inject at task build
Factories receive work from connected trackers or board-created tasks with source attached; ready tasks state problem, expected behavior, scope, evidence and constraints; confidence score routes (ready vs needs clarification); the Start action is the authorization boundary and implementation begins only after team rules are met.
Kind
documented
Locator
Where tasks come from; readiness; confidence routing; Start authorization
Done means the factory completion rule is met (e.g. PR ready after required checks, optionally approved/merged), not that an agent stopped; the record preserves source issue, branch/commit/PR, agent output, checks, approvals, retries/failures and timestamps; factories may leave merge to repo owners or include approval and merge; timing/stage/retry/intervention signals feed task-selection improvements.
Kind
documented
Locator
Completion rules; preserved record; handoff to people; operating data
Scheduled intake adds a Backlog-column entry with a daily time or cron expression (browser-timezone offset stored); backend instantiates a bundled template resolving repo, branch, Git integration and hosted/BYOK agent; the agent writes /tmp/proposal.json and only a valid non-empty proposal creates a task; creation does not start a manual run.
Bundled template wires a daily 9:00 schedule trigger to an agent node whose proposal passes through a filter into create-task (failures into add-run-error), proving schedules can create backlog work without a human initiating each run.
Backlog automation imports/enriches/scores work; routes passed/failed/human-review outcomes; keeps the Start decision visible (automated start only via narrow trusted-repo/label/threshold rules); cost controls include filtering before agent nodes, smaller classification models and no re-analysis until task/context changes.
Kind
documented
Locator
Decide entries; analysis context; route results; start decision; cost control
Verify combines repository checks, PR state, task-specific checks, agent review and human review; failed deterministic checks return command plus failure output to implementation in a bounded correction loop; execution failure and verification failure are distinguished; human attention covers tradeoffs, sensitive dependencies, ambiguous requirements and scope calls.
Kind
documented
Locator
Evidence stack; failed-check feedback; run vs result quality; human attention
Work orders move between draft, open and closed with results completed/rejected/failed/archived/pr_closed/manual_rejected; closed may reopen to open or return to draft; no priority, label, parent, child or dependency fields exist on the model.
Kind
source-inspected
Locator
Lines 20-66: states, results, allowed transitions; IsArchived at 555
Approval nodes implement pending/approved/rejected states with per-record approve/reject operations gated by configured approvers; combined with the documented Approval trigger this enforces human gates (e.g. before merge or production deploy) inside the workflow.
Kind
source-inspected
Locator
Lines 16-18 state constants (pending/approved/rejected); Approve at line 126 and Reject at line 149
Factory line steps cap in-flight runs via MaxParallelism with a default of 10; dispatch acquires parallelism slots and waiters move in as slots release, providing the queueing behind the documented concurrency controls.
Kind
source-inspected
Locator
Lines 17-19 default (DefaultFactoryLineStepMaxParallelism = 10); line 36 MaxParallelism cap
Verify automation runs required checks and review feedback against the implementation output, preserving task context across correction attempts and recording which checks passed or failed for the task.
Kind
documented
Locator
Check/process configuration; review feedback without losing context
The injected runner tool list supports task list/create/close, current-task owner assignment, checks and artifacts, but no agent-session delegation/start/inspection or messaging tool. Agents cannot move tasks between columns; deterministic product canvases sequence the stage agents. A general automation canvas is not an agent coordinator role.
Kind
source-inspected
Locator
runner_tools.go tool list; task_cli.js command tree; official agent-tools guide: factory columns and assignment limits
The complete published skill bundle supplies CLI operation, app/canvas building and execution monitoring. These skills configure and inspect deterministic workflows rather than designate a session coordinator that starts and messages other agent sessions. This supplements the core injected-runner tool inventory.
Kind
documented
Locator
skills repository at 8a10f9cf; superplane-cli, superplane-app-builder and superplane-monitor skill definitions
Docs release-notes page tops out at v0.30.0 dated July 27, 2026 (factory-first onboarding, Linear, GitLab capabilities, Claude/Cursor structured output, sync runs with timeout, cancellable runs, scoped API keys), followed by v0.29.0/v0.28.0; it predates the v1.0.0 GitHub releases and is stale as a changelog source.
The Velocity view reports delivery, cycle time and cost over 14d/30d windows with headline metrics, warning that small samples and unmerged results limit what percentages prove.
Kind
documented
Locator
Reporting window; four headline metrics; sample-size caveats
The public repository holds the engine, web interface, API definitions, integrations, dev environment and tests under Apache 2.0 with public development; run in cloud or on own infrastructure with chosen models; open-source project plus managed cloud offering.
Kind
documented
Locator
What is Open: Apache 2.0; public development; flexible operation
The factory websocket reconnects indefinitely every 3s and invalidates plus refetches work-order queries on reconnect, keeping board state consistent after drops.
AWS, Google Cloud, Azure, OCI, DigitalOcean, Hetzner and Cloudflare components plus DockerHub, Coolify, Render, Cloudsmith and JFrog Artifactory for build/delivery; narrow credentials with recorded approvals before destructive or production actions.
Pull-request checks and webhook delivery lookups carry a dedup_key indexed per workflow, node and pull-request identity so duplicate deliveries find the original checks event without scanning history.
Kind
source-inspected
Locator
dedup_key column plus idx_workflow_events_dedup_key for pull-request checks and webhook delivery lookups
An authorized workspace user loads a planning session by organization, factory and session ID, then SendUserMessage records the current user ID in that same session. The handler does not restrict messages to a creator; participating senders are added as draft assignees. The shared planning agent can therefore receive instructions from multiple humans.
ee/ carries a separate commercial license requiring agreement to SuperPlane Terms of Service and a valid Enterprise Edition license for self-hosted deployments; enterprise-only features (Kubernetes install, SSO, audit logs, configurable retention) sit outside the Apache 2.0 grant.
Kind
source-inspected
Locator
Header: EE License; Terms of Service plus valid Enterprise license required
Users may terminate accounts anytime via contact or in-service account management; service rights cease on termination and outstanding fees become due.
Collects account, billing (via third-party processor), communications, usage (workflows, machine/model use, error logs), device/log data, PostHog/Google Analytics website data, and third-party integration data including source code, pull requests, issue descriptions and comments; shares with service providers; no sale of personal information stated.
The product analytics guide states events are sent only when POSTHOG_KEY is set. The server creates a no-op client for an empty key and the browser does not initialize PostHog without its injected key. Self-hosted operators can leave POSTHOG_KEY unset to disable product analytics; this does not establish a hosted-user opt-out or disable operational tracing.
Kind
documented
Locator
docs/product-analytics.md lines 1-10; web_src/src/posthog.ts initPostHog; pkg/productanalytics/analytics.go New