--- schema_version: 3 rubric_version: "0.3" canonical_url: "https://podium.do/compare/agents/codex-vs-paseo/" data_url: "https://podium.do/compare/agents/codex-vs-paseo/data.json" generated_at: 2026-09-30 last_checked_at: 2026-09-23 last_cross_checked_at: 2026-09-23 next_check_at: 2026-10-07 publisher: "Podium" --- # OpenAI Codex vs Paseo > Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. The same evidence rules apply to Podium and its competitors, but they do not remove this conflict of interest. This comparison has 6 criteria with sourced findings for both products, including 6 that a second agent cross-checked for both. 17 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. Humans approve the rubric, templates and prototype; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent. - OpenAI Codex source checks: 2026-09-23. - Paseo source checks: 2026-09-23. - Canonical HTML: https://podium.do/compare/agents/codex-vs-paseo/ - Machine-readable JSON: https://podium.do/compare/agents/codex-vs-paseo/data.json - Methodology: https://podium.do/compare/agents/methodology/ ## Access and agent choice ### ACC-01: Client access Judgment rule: List desktop OS and minimum versions, iOS, Android, browser, mobile browser, CLI and editor extensions separately. For each client, record start, steer, approve, review and resume actions, notifications and plan restrictions. Test moving the same task from desktop to phone; distinguish an installable mobile app from a mobile website and from status-only monitoring. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial Codex documents terminal, IDE, desktop and cloud web surfaces. Availability: unknown Delivery: native Scope: surfaces=Codex CLI, Codex IDE extension, Codex in ChatGPT desktop, Codex cloud; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - desktop_os — Desktop os [unknown]: Desktop os: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - mobile_apps — Mobile apps [unknown]: Mobile apps: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - browser — Browser [supported]: Codex cloud web. Sources: codex:cli, codex:cloud, codex:auth. - mobile_browser — Mobile browser [unknown]: Mobile browser: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - cli — Cli [supported]: CLI installers for macOS/Linux/Windows. Sources: codex:cli, codex:cloud, codex:auth. - editor_extensions — Editor extensions [supported]: Codex IDE extension; editor compatibility uncollected. Sources: codex:cli, codex:cloud, codex:auth. - task_actions — Task actions [unknown]: Task actions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - notifications — Notifications [unknown]: Notifications: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - cross_device_continuity — Cross device continuity [unknown]: Cross device continuity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: codex:cli, codex:cloud, codex:auth #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paseo advertises desktop, mobile and web clients to the same daemon. Availability: unknown Delivery: native Scope: surfaces=Paseo desktop, Paseo mobile, Paseo web, Paseo daemon and APIs, Paseo Hub; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - desktop_os — Desktop os [unknown]: Desktop os: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - mobile_apps — Mobile apps [supported]: Dedicated mobile app advertised; exact OS/minimum versions not checked. Sources: paseo:website. - browser — Browser [supported]: Web client. Sources: paseo:website. - mobile_browser — Mobile browser [unknown]: Mobile browser: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - cli — Cli [unknown]: Cli: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - editor_extensions — Editor extensions [unknown]: Editor extensions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - task_actions — Task actions [unknown]: Task actions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - notifications — Notifications [unknown]: Notifications: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - cross_device_continuity — Cross device continuity [partial]: Same workspaces from different clients advertised; no transition test. Sources: paseo:website. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:website ### ACC-02: Agent and model choice Judgment rule: List supported harnesses and model providers separately, including custom adapters. Record whether the product embeds a harness, controls its sessions through an API, or only launches its terminal command. Verify at least two different harnesses before describing mixed-harness operation as observed. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### ACC-03: Subscriptions, API keys and vendor credits Judgment rule: Record bring-your-own agent subscription, bring-your-own API account, vendor credits and local models as separate routes. List supported plans, models/modes, multiple-account switching and what works without a vendor account or token purchase. Existing subscription support cannot be inferred from API-key support. Record required extra payments and documented provider restrictions. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local clients accept subscriptions or API keys; cloud requires ChatGPT sign-in. Availability: unknown Delivery: native Scope: surfaces=Codex CLI, Codex IDE extension, Codex in ChatGPT desktop, Codex cloud; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - agent_subscriptions — Agent subscriptions [supported]: ChatGPT subscription. Sources: codex:auth. - api_accounts — Api accounts [supported]: API-key local access. Sources: codex:auth. - vendor_credits — Vendor credits [unknown]: Vendor credits: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - local_models — Local models [unknown]: Local models: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - account_switching — Account switching [unknown]: Account switching: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - vendor_account_requirement — Vendor account requirement [unknown]: Vendor account requirement: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provider_restrictions — Provider restrictions [supported]: Cloud requires ChatGPT authentication. Sources: codex:auth. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: codex:auth #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paseo advertises reuse of installed-provider credentials and subscriptions. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - agent_subscriptions — Agent subscriptions [supported]: Bring existing subscriptions and provider configuration. Sources: paseo:website. - api_accounts — Api accounts [unknown]: Api accounts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - vendor_credits — Vendor credits [unknown]: Vendor credits: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - local_models — Local models [unknown]: Local models: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - account_switching — Account switching [unknown]: Account switching: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - vendor_account_requirement — Vendor account requirement [unknown]: Vendor account requirement: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provider_restrictions — Provider restrictions [unknown]: Provider restrictions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:website ### ACC-04: Onboarding and project prerequisites Judgment rule: Measure fresh install to first successful task, with manual steps and failures. Test a local directory without Git, a local Git repo without a remote, and a GitHub-backed repo separately. Record whether account, project, host, credential and permission prerequisites are explained before accepting an unusable prompt. Evaluate managed-cloud setup and first-class BYO VPS installer/onboarding independently of hidden settings or a DIY shell recipe. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paseo explicitly documents use outside Git repositories. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - first_task_setup — First task setup [unknown]: First task setup: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - no_git — No git [supported]: FAQ says it works in any directory; worktrees are optional. Sources: paseo:website. - local_git_without_remote — Local git without remote [partial]: GitHub is not required according to FAQ; local remote-less fixture not run. Sources: paseo:website. - hosted_git — Hosted git [unknown]: Hosted git: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - prerequisite_guidance — Prerequisite guidance [unknown]: Prerequisite guidance: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - managed_cloud_setup — Managed cloud setup [unknown]: Managed cloud setup: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - byo_vps_onboarding — Byo vps onboarding [unknown]: Byo vps onboarding: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:website ### ACC-05: Programmable access Judgment rule: Inventory actual CLI, API, SDK, MCP and webhook operations for create, inspect, steer, stop and review. Record authentication and API stability. Having an MCP client that uses external tools is different from exposing the product to other agents over MCP. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial CLI supports non-interactive automation. Availability: unknown Delivery: native Scope: surfaces=Codex CLI; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - cli — Cli [supported]: codex exec for scripts and pipelines. Sources: codex:cli. - api — Api [unknown]: Api: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - sdk — Sdk [unknown]: Sdk: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - mcp_server — Mcp server [unknown]: Mcp server: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - webhooks — Webhooks [unknown]: Webhooks: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - operations — Operations [unknown]: Operations: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - authentication — Authentication [unknown]: Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - stability — Stability [unknown]: Stability: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cli #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paseo exposes orchestration through injected MCP tools or CLI. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - cli — Cli [supported]: paseo run, ls and remote-host operations. Sources: paseo:orchestration. - api — Api [unknown]: Api: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - sdk — Sdk [unknown]: Sdk: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - mcp_server — Mcp server [supported]: Built-in Paseo tools let agents manage their host. Sources: paseo:orchestration. - webhooks — Webhooks [unknown]: Webhooks: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - operations — Operations [supported]: Create agents/workspaces, send prompts, inspect and stop. Sources: paseo:orchestration. - authentication — Authentication [unknown]: Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - stability — Stability [unknown]: Stability: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:orchestration ### ACC-06: External tools and extensions Judgment rule: Record MCP client support, plugins, custom tools, skill/instruction import, integration authentication and permission scope. Name which component provides each connection and whether setup is product-managed or inherited from the underlying harness. Verify one external-tool call and its access boundary where available. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial CLI supports MCP and packaged extensions. Availability: unknown Delivery: native Scope: surfaces=Codex CLI; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - mcp_client — Mcp client [supported]: Local/remote MCP. Sources: codex:cli. - plugins — Plugins [supported]: Plugins and skills. Sources: codex:cli. - custom_tools — Custom tools [unknown]: Custom tools: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - instructions_import — Instructions import [unknown]: Instructions import: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - authentication — Authentication [unknown]: Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - permission_scope — Permission scope [unknown]: Permission scope: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - integration_owner — Integration owner [unknown]: Integration owner: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cli #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### ACC-07: Client implementation Judgment rule: For each desktop/mobile client, record native platform UI, Electron, Tauri, React Native, web/PWA or unknown, plus hybrids. Require official technical docs or pinned source/build evidence. Tauri is not synonymous with fully native UI. Keep implementation choice separate from measured responsiveness and usability. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paseo desktop uses Electron; mobile app source uses Expo/React Native. Availability: source-only Delivery: native Scope: surfaces=Paseo desktop, Paseo mobile; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - desktop_implementation — Desktop implementation [supported]: Electron. Sources: paseo:desktop-package, paseo:mobile-package. - mobile_implementation — Mobile implementation [supported]: Expo/React Native. Sources: paseo:desktop-package, paseo:mobile-package. - hybrids — Hybrids [unknown]: Hybrids: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - implementation_evidence — Implementation evidence [supported]: Pinned client package manifests. Sources: paseo:desktop-package, paseo:mobile-package. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-12-22. Sources: paseo:desktop-package, paseo:mobile-package ## Planning and context ### PLAN-01: Intake and external tracker relationship Judgment rule: Record local creation, prompt intake, issue import and chat/Git triggers. Identify the authoritative tracker, stable issue IDs, one-way or two-way sync, supported edits and operations requiring a trip back to Linear/GitHub/Jira. Importing or attaching a ticket is not native issue management. Answer PLAN-06 and PLAN-07 separately. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-02: Durable task plans Judgment rule: Record task plans and acceptance criteria, editors, revision history and links to implementation. Test amending a task while work is running, restarting and revisiting it later. A task-specific starting brief, reusable memory and a persistent product specification are different objects; product specs are judged in PLAN-08. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-03: Hierarchy, dependencies and evolving scope Judgment rule: Record epics, arbitrary parent/child depth, blockers, readiness, dependency enforcement and state propagation. Start with a simple interactive task, grow it into an epic and retain its identity, discussion, history and outputs. Verify blockers actually prevent dispatch. Record whether a rigid preselected workflow is required, and whether changing scope requires recreating work. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-04: Shared context and memory Judgment rule: List repository instructions, skills, project docs and cross-session/cross-harness memory. Record scope, provenance, citation, correction/deletion and stale-context controls. Test what survives a new session or colleague takeover. A notes page or shared file is not automatically a maintained spec or managed memory. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-05: Architecture and API awareness Judgment rule: Record code search, repository indexing, external knowledge and multimodal inputs, with source freshness and access scope. Ask an agent to use an existing API under a documented architecture rule, then propose a conflicting change. Check retrieval, citation, conflict detection and review-time enforcement separately. A large context window or an instruction file alone does not prove architectural consistency. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-06: Native issue management and idea backlog Judgment rule: Enumerate create, edit, discuss, prioritize, label, assign, search, filter, archive, reopen and project/epic views within the product. Save an idea without creating a running agent, refine it with another person, and explicitly mark it ready or dispatch it later. Record separate task/session entities, metadata depth, multiple sessions per task, durable state transitions and whether an external tracker remains necessary. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-07: Agent-native issue operations Judgment rule: Verify an agent can read/create/update the same durable issue IDs and fields humans use, claim/assign work, change state, create dependencies/children and report blockers/results through documented CLI/API/MCP. Check that human views reflect actual writes with attribution, permissions and conflict handling. Distinguish shared authoritative records, synchronized external records, agent-private metadata and prompt-only conventions. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### PLAN-08: Living product specifications Judgment rule: Record persistent requirements across tasks/releases, editable by humans and agents with attributable revisions and approval rules. Verify requirement-to-task/implementation links, retrieval during later tasks, drift detection and consideration during review/quality control. Amend a requirement after one task ships, then implement another. A one-time spec-to-plan workflow, per-task brief, memory store or unreferenced document does not establish a living product spec. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ## Coordination and automation ### COORD-01: Parallel work Judgment rule: Record independently running sessions and tasks, documented quotas and observed concurrency. Describe how a user sees running, waiting, failed and finished work. Several chat tabs are not proof that runs execute concurrently. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cloud supports parallel tasks in separate environments. Availability: unknown Delivery: native Scope: surfaces=Codex cloud; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - concurrent_sessions — Concurrent sessions [unknown]: Concurrent sessions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - concurrent_tasks — Concurrent tasks [supported]: Parallel cloud work. Sources: codex:cloud. - quotas — Quotas [unknown]: Quotas: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - observed_concurrency — Observed concurrency [unknown]: Observed concurrency: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - status_visibility — Status visibility [unknown]: Status visibility: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cloud #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Parallel research and separate-worktree changes are documented recipes. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - concurrent_sessions — Concurrent sessions [supported]: Documented multi-worker fan-out. Sources: paseo:workflows. - concurrent_tasks — Concurrent tasks [supported]: Independent changes can receive separate worktrees. Sources: paseo:workflows. - quotas — Quotas [unknown]: Quotas: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - observed_concurrency — Observed concurrency [unknown]: Observed concurrency: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - status_visibility — Status visibility [unknown]: Status visibility: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:workflows ### COORD-02: Ownership and dispatch Judgment rule: Record assignment to humans or agents, claims, queues, routing and duplicate-work prevention. Test two workers attempting the same task. Distinguish a display label, an advisory lock and enforced exclusive ownership. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### COORD-03: Inspectable delegation and communication Judgment rule: Record parent/child roles, model/harness/effort choice, messages, result return and cross-harness teams. Distinguish product orchestration, provider-native subagents, installed orchestration skills and scripts. Record activation, auth and experimental flags. Verify actual child identity, live progress, retained results and ability to reopen or follow up after completion. A final sentence claiming two reviewers ran is not proof. Test the documented invocation as well as the shared natural-language request. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial CLI can delegate focused work to subagents. Availability: unknown Delivery: native Scope: surfaces=Codex CLI; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - roles — Roles [unknown]: Roles: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - model_harness_effort — Model harness effort [unknown]: Model harness effort: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - messages — Messages [unknown]: Messages: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - results_return — Results return [supported]: Findings return to main session. Sources: codex:cli. - cross_harness — Cross harness [unknown]: Cross harness: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - orchestration_owner — Orchestration owner [supported]: Codex harness. Sources: codex:cli. - activation — Activation [unknown]: Activation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - authentication — Authentication [unknown]: Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - live_progress — Live progress [unknown]: Live progress: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - retained_results — Retained results [unknown]: Retained results: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - followup — Followup [unknown]: Followup: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - invocation — Invocation [unknown]: Invocation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cli #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Documented Paseo workers can be inspected and prompted after delegation. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs, Paseo desktop, Paseo mobile, Paseo web; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - roles — Roles [unknown]: Roles: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - model_harness_effort — Model harness effort [supported]: Profiles store provider/model/thinking/mode. Sources: paseo:orchestration. - messages — Messages [supported]: send_agent_prompt addresses agent IDs. Sources: paseo:workflows. - results_return — Results return [supported]: Main agent receives completion notification. Sources: paseo:orchestration. - cross_harness — Cross harness [unknown]: Cross harness: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - orchestration_owner — Orchestration owner [supported]: Paseo creates full worker sessions. Sources: paseo:orchestration. - activation — Activation [supported]: MCP tool injection is off by default; enable then start/reload agent. CLI does not require injection. Sources: paseo:orchestration. - authentication — Authentication [unknown]: Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - live_progress — Live progress [supported]: Subagents track opens worker conversation. Sources: paseo:orchestration. - retained_results — Retained results [supported]: Worker session persists for follow-up/archive/detach. Sources: paseo:workflows. - followup — Followup [supported]: Paseo worker conversations permit follow-up; provider-native subagents have read-only timelines. Sources: paseo:workflows. - invocation — Invocation [unknown]: Invocation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:orchestration, paseo:workflows ### COORD-04: Unattended triggers Judgment rule: Record schedules, event triggers, recurring tasks and completion conditions. Name where the scheduler runs, overlap handling, retries and whether closing the client stops it. A desktop cron recipe is a manual integration unless the product owns it. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Schedules create new agents and heartbeats revisit existing sessions. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - schedules — Schedules [supported]: Scheduled prompts and heartbeats. Sources: paseo:workflows. - events — Events [unknown]: Events: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - recurring_tasks — Recurring tasks [supported]: Heartbeat retains the same conversation. Sources: paseo:workflows. - completion_conditions — Completion conditions [partial]: Example asks for heartbeat deletion at completion and explicit expiry; autonomous enforcement not tested. Sources: paseo:workflows. - scheduler_location — Scheduler location [unknown]: Scheduler location: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - overlaps — Overlaps [unknown]: Overlaps: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - retries — Retries [unknown]: Retries: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - client_independence — Client independence [unknown]: Client independence: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:workflows ### COORD-05: Intervention and attention Judgment rule: Record pause, stop, resume, steering, notifications, pending decisions and escalation. Test an in-run amendment and a harmless approval prompt in both chat and terminal modes. Record silent waits, hidden CLI-only questions and whether stop terminates execution while preserving history. Require discoverable errors rather than inferring success from silence. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Existing workers can receive amendments or have a turn cancelled. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - pause — Pause [unknown]: Pause: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - stop — Stop [supported]: Cancel current turn while retaining agent. Sources: paseo:workflows. - resume — Resume [unknown]: Resume: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - steer — Steer [supported]: Send follow-up to an existing worker. Sources: paseo:workflows. - notifications — Notifications [unknown]: Notifications: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - pending_decisions — Pending decisions [unknown]: Pending decisions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - escalation — Escalation [unknown]: Escalation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - visible_errors — Visible errors [unknown]: Visible errors: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - chat_terminal_parity — Chat terminal parity [unknown]: Chat terminal parity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - retained_history — Retained history [supported]: Worker remains available for a later prompt. Sources: paseo:workflows. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:workflows ### COORD-06: Fleet and epic management UI Judgment rule: Use a disclosed fixture of 12 task/agent states across several epics, including blocked, failed, awaiting input, reviewing and completed work. Locate parent/child relationships, dependencies, attention needs, history and workload without reading every transcript. Record navigation steps and errors. Boards, graphs, waterfalls, timelines or another interface can qualify; no required visual form. State whether the fixture was simulated or used live agents. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### COORD-07: Workflow flexibility and orchestration visibility Judgment rule: Compare a quick interactive change with a growing epic. Record mandatory workflow/preset selection, natural-language configuration, per-agent model/effort control, changes during execution and whether the UI exposes what actually ran. Test a coordinator with two reviewer children; capture roles, relationships and results during work and after completion. Document discoverability and auth friction without judging an unsupported magic prompt as proof of missing capability. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ## Execution and reliability ### RUN-01: Laptop-independent execution Judgment rule: List local, user-owned VPS/remote host, self-hosted service, vendor cloud and hybrid modes. Record provisioning, payer, compute resources, region, idle/max lifetime and disconnection rules. Close/disconnect the originating client and continue from another device. A hosted UI or keep-awake setting is not evidence of remote execution. Record managed-cloud convenience separately from BYO setup effort in ACC-04. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local CLI and managed cloud execution are separate modes. Availability: unknown Delivery: native Scope: surfaces=Codex CLI, Codex cloud; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - local — Local [supported]: CLI uses host repository/tools. Sources: codex:cli, codex:cloud. - byo_remote — Byo remote [unknown]: Byo remote: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - self_hosted — Self hosted [unknown]: Self hosted: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - managed_cloud — Managed cloud [supported]: Isolated cloud environments. Sources: codex:cli, codex:cloud. - hybrid — Hybrid [unknown]: Hybrid: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provisioning — Provisioning [unknown]: Provisioning: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - payer — Payer [unknown]: Payer: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - resources — Resources [unknown]: Resources: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - region — Region [unknown]: Region: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - expiry — Expiry [unknown]: Expiry: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - client_disconnect — Client disconnect [unknown]: Client disconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - other_device_continuation — Other device continuation [unknown]: Other device continuation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cli, codex:cloud #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial A headless daemon can run on the user remote machine; client availability is not managed compute. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - local — Local [supported]: Local daemon. Sources: paseo:website. - byo_remote — Byo remote [supported]: Home-lab/cloud machine daemon. Sources: paseo:website. - self_hosted — Self hosted [unknown]: Self hosted: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - managed_cloud — Managed cloud [unknown]: Managed cloud: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - hybrid — Hybrid [unknown]: Hybrid: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provisioning — Provisioning [partial]: User supplies a reachable host; no managed-host setup was tested. Sources: paseo:website. - payer — Payer [unknown]: Payer: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - resources — Resources [unknown]: Resources: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - region — Region [unknown]: Region: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - expiry — Expiry [unknown]: Expiry: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - client_disconnect — Client disconnect [unknown]: Client disconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - other_device_continuation — Other device continuation [unknown]: Other device continuation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:website ### RUN-02: Workspace and process isolation Judgment rule: Record shared checkout, branch, worktree, container, VM and OS sandbox separately. Name filesystem, process, network and secret boundaries. Validate code separation with two changes; do not claim hostile-code containment without separate security evidence. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Parallel changes can use separate worktrees; research workers may share files. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - checkout — Checkout [unknown]: Checkout: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - branch — Branch [unknown]: Branch: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - worktree — Worktree [supported]: Separate worktree per independent change documented. Sources: paseo:workflows. - container — Container [unknown]: Container: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - vm — Vm [unknown]: Vm: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - os_sandbox — Os sandbox [unknown]: Os sandbox: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - filesystem — Filesystem [unknown]: Filesystem: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - process — Process [unknown]: Process: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - network — Network [unknown]: Network: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - secrets — Secrets [unknown]: Secrets: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - code_separation — Code separation [partial]: Research fan-out may share a workspace; isolation must be explicitly selected. Sources: paseo:workflows. - security_boundary — Security boundary [unknown]: Security boundary: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:workflows ### RUN-03: Recovery, expiry and continuity Judgment rule: Test client disconnect, worker crash, service restart and documented sandbox expiry safely. Separate transcript reload, process reconnection, task resumption and state reconstruction. Record lost context, duplicated actions, manual repair and ability to continue a multi-day epic after compute replacement. Short sandbox lifetimes are reported with their continuity behavior, not automatically treated as failure. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial CLI documents saved chat resumption. Availability: unknown Delivery: native Scope: surfaces=Codex CLI; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - client_disconnect — Client disconnect [unknown]: Client disconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - worker_crash — Worker crash [unknown]: Worker crash: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - service_restart — Service restart [unknown]: Service restart: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - expiry — Expiry [unknown]: Expiry: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - transcript_reload — Transcript reload [supported]: codex resume reopens saved local chats. Sources: codex:cli. - process_reconnect — Process reconnect [unknown]: Process reconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - task_resume — Task resume [unknown]: Task resume: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - state_reconstruction — State reconstruction [unknown]: State reconstruction: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - context_loss — Context loss [unknown]: Context loss: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - duplicate_actions — Duplicate actions [unknown]: Duplicate actions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - manual_repair — Manual repair [unknown]: Manual repair: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - multi_day_continuity — Multi day continuity [unknown]: Multi day continuity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cli #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### RUN-04: Development environment reliability Judgment rule: Record dependency setup, node_modules/cache handling, snapshots, services, port allocation and secret injection. Start two workspaces with the same service requirements; note installation duplication, port collisions and repair steps. Repeat on a clean remote host. Record which problems the product handles automatically and which the user must diagnose. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### RUN-05: Limits and failure handling Judgment rule: Record time, turn, token and spend limits; timeout, retry and provider-failure behavior. Test one controlled failure and a small safe budget. Record whether limits are warnings, enforced stops, or external billing controls. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### RUN-06: Truthful status and operational statistics Judgment rule: Record logs, traces, failure reasons, usage exports and statistics by task, agent, project and time. Induce a worker failure and an approval wait: check agent, task and board state agree and remain correct after reconnect. Distinguish working, blocked, failed, idle, ready for review and delivered. For speed/success claims disclose fixture, model, hardware, attempts and failures. UI responsiveness needs observed interaction timings; never infer a framework from lag. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### RUN-07: Per-task API and compute cost Judgment rule: Record visible model/API spend per task, session, child and epic, including aggregation across harness changes. Distinguish billed charges, estimates, tokens, subscription allowance and unavailable amounts; never render unknown subscription marginal cost as zero. Reconcile totals with provider evidence where available. Record compute fees separately, refresh delay, budget alerts, export and drill-down from summary statistics. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### RUN-08: Compute-aware scheduling and verification Judgment rule: Record concurrency limits, queues, CPU/RAM limits, backpressure, per-host resource awareness and reuse/deduplication of checks. Queue multiple browser end-to-end tests under a declared safe capacity; verify excess work queues or throttles rather than overloading the host. Inspect cancellation, fairness, recovery and whether overlapping epics share limits. Do not run an uncontrolled load test. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ## Human collaboration and control ### TEAM-01: Live human collaboration Judgment rule: Record shared visibility, issue discussion, comments, presence and simultaneous co-prompting as independent capabilities. Use two named accounts to steer the same agent and record input ordering/conflict handling, attribution and permission controls. Read-only links and shared issues do not establish co-steering. Record team/free-tier restrictions and whether the original owner must stay online. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Paseo Hub team access is a vendor claim separate from local workspace use. Availability: unknown Delivery: native Scope: surfaces=Paseo Hub; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Do not inherit Hub collaboration into every local/free configuration. No two-human scenario was run. - visibility — Visibility [partial]: Homepage advertises shared access through Paseo Hub; co-prompting and permissions unverified. Sources: paseo:website. - discussion — Discussion [unknown]: Discussion: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - comments — Comments [unknown]: Comments: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - presence — Presence [unknown]: Presence: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - coprompting — Coprompting [unknown]: Coprompting: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - ordering — Ordering [unknown]: Ordering: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - conflicts — Conflicts [unknown]: Conflicts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - attribution — Attribution [unknown]: Attribution: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - permissions — Permissions [unknown]: Permissions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - plan_restrictions — Plan restrictions [unknown]: Plan restrictions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - owner_online — Owner online [unknown]: Owner online: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: paseo:website ### TEAM-02: Roles and access boundaries Judgment rule: Record organization/project/task roles, membership lifecycle, SSO and provisioning where offered. Test unauthorized access and revocation with consenting test accounts. Describe documented versus observed enforcement, including which plan provides it. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### TEAM-03: Approvals and temporary access Judgment rule: Record command, tool, network, secret and delivery approvals, approver identity and scope lifetime. Demonstrate allow, deny and revocation, including temporary tunnels or shared access after its thread/session ends. Separate default full access, available safer modes and product-enforced policy from instructions the model is expected to follow. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### TEAM-04: Decision and activity history Judgment rule: Record attributed actions, approvals, edits, discussion and decision links. Check whether history persists across users and sessions, can be exported, and can be altered. Use the word audit only with a defined retention and integrity model. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### TEAM-05: Review experience and guidance Judgment rule: Evaluate locating pending reviews, understanding a change, navigating evidence, commenting, requesting changes and finding the next shipping action. Measure steps/time and missed evidence on a shared fixture. Record keyboard/narrow-screen usability, context switching, clarity of agent roles and preservation of review context. Generic diff/PR access and a guided review workflow are different capabilities. Link high-volume review findings to SHIP-06. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### TEAM-06: Colleague takeover and continuity Judgment rule: Have a second authorized person take over ongoing work with the same task, session history, decisions, artifacts, permissions and runtime context. Test after the first person disconnects. Record ownership transfer, attribution and lost context. Separately record transferring to another model/harness; a forked transcript or shared link alone is not full human takeover. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ## Verification and delivery ### SHIP-01: Retained artifacts and outputs Judgment rule: Record diffs, documents, screenshots, recordings, previews and test/reviewer outputs. Check for a searchable/browsable artifact gallery or equivalent retrieval, linked to task and exact revision, usable after sessions end. Reopen a completed child reviewer and retrieve its full findings. Check whether internal prompts or tool metadata unintentionally appear in the produced application or other user-facing output. In-chat attachments, persistent review evidence and a cross-task gallery get distinct answers. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### SHIP-02: Verification and spec gates Judgment rule: Record tests, lint, types, CI, independent review and persistent-spec conformance checks as required versus optional. Cause a failed test and a conflict with an existing product requirement. Verify review catches the conflict and delivery blocks where claimed. An agent saying checks passed is not a passing gate; record configured and enforced policy separately. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### SHIP-03: Git and pull request workflow Judgment rule: Record branches/worktrees, commits, PR creation, review comments, CI response, rebase and conflict handling. Complete one fixture change through a draft PR. Distinguish an integrated workflow from the agent running Git commands without product state. #### OpenAI Codex Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cloud review can lead to a pull request. Availability: unknown Delivery: native Scope: surfaces=Codex cloud; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - branches — Branches [unknown]: Branches: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - worktrees — Worktrees [unknown]: Worktrees: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - commits — Commits [unknown]: Commits: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - pull_requests — Pull requests [supported]: Review result and open PR. Sources: codex:cloud. - comments — Comments [supported]: Request follow-up changes. Sources: codex:cloud. - ci_response — Ci response [unknown]: Ci response: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - rebase — Rebase [unknown]: Rebase: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - conflicts — Conflicts [unknown]: Conflicts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - product_state — Product state [unknown]: Product state: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: codex:cloud #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### SHIP-04: Merge and deployment authority Judgment rule: Record who can approve, merge, release and deploy, plus checks against the exact revision. Verify the documented authority boundary without publishing real changes. PR creation, merge and production deployment are separate capabilities. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### SHIP-05: Completion evidence and rollback Judgment rule: Record task-to-commit/PR/build/deployment links, delivery status, retained evidence and rollback or revert support. Change the candidate revision after review and examine whether approval/evidence is invalidated. Agent exit alone does not prove delivery. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### SHIP-06: Batch review and high-volume shipping Judgment rule: Return to a queue of at least six completed fixture tasks and review a subset. Record summaries, grouping, risk/size filters, retained reviewer findings, artifact navigation, request-changes flow, approval of exact revisions, dependency-aware merge/release queues and clear next actions. Check stale approvals invalidate after edits and duplicate checks respect RUN-08. Distinguish basic diff/PR actions from a coordinated review-and-delivery queue; do not require Podium terminology. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ## Ownership, privacy and economics ### OWN-01: Source and license Judgment rule: Record license and revision per component, including client, server and hosted extensions. Distinguish open source, source-available and closed components. Repository visibility is not a license classification or proof of hosted parity. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public repository carries Apache-2.0; hosted extensions and parity remain unverified. Availability: unknown Delivery: native Scope: surfaces=Paseo desktop, Paseo mobile, Paseo web, Paseo daemon and APIs, Paseo Hub; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - client_license — Client license [supported]: Root Apache-2.0 license, subject to component notices. Sources: paseo:license. - server_license — Server license [unknown]: Server license: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - hosted_extensions — Hosted extensions [unknown]: Hosted extensions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - source_visibility — Source visibility [supported]: Public repository. Sources: paseo:license. - source_revision — Source revision [supported]: 0f20e6dfe4c2573e203dea2aae00aa5983ce4d62 Sources: paseo:license. - hosted_parity — Hosted parity [unknown]: Hosted parity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-12-22. Sources: paseo:license ### OWN-02: Hosting and exit Judgment rule: Record self-hosting scope, required vendor services, data export/import, standard formats and account cancellation behavior. Verify what remains usable without the vendor account. Exported code alone does not mean tasks, context and history are portable. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### OWN-03: Data handling and telemetry Judgment rule: Record where code, prompts, credentials, logs and artifacts go, retention/deletion, training use, residency and subprocessors. Separately record telemetry disclosure, collection defaults, opt-in/opt-out controls and observed first-run prompts. No consent dialog is an observation, not proof of no telemetry, secret telemetry or unlawful processing. Separate orchestration-vendor and model-provider policies. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### OWN-04: Price and included usage Judgment rule: Record currency, billing interval, seats/seat minimums, workspace charges, included usage, credits, trial conditions, overages, taxes treatment and separate model/compute costs. Map billing routes to ACC-03. Cite public prices or dated quotes. Per-seat versus pooled billing is a fact, not a universal quality judgment. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### OWN-05: Scenario cost and controls Judgment rule: Price stated workloads for one, two and five developers, with fixed tasks, concurrency, tokens and compute-hours. The two-person scenario models Till and Michael collaborating. Include subscription, platform, model and compute charges; separate fixed, variable, included and unknown costs. No invented average task cost. Link cost visibility and reconciliation to RUN-07. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### OWN-06: Availability and support Judgment rule: Record GA/beta/access restrictions, support channels, documented response commitments, release activity, status history and deprecation/export options. Funding, stars and popularity can be context but are not reliability scores. An archived repository does not prove the hosted service is discontinued. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### OWN-07: Enterprise assurance Judgment rule: Record each claimed assurance separately: ISO standard/certificate scope, issuer and validity; SOC 2 report type, covered service and audit period; report/certificate access and verification date. Distinguish public documentation, vendor assertion, independently accessible evidence and unavailable evidence. A logo, enterprise pricing tier, SSO or a provider certification does not prove this product is certified or audited. Report controls in TEAM-02 separately; no legal-compliance verdict. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ### OWN-08: Useful free tier and evaluation access Judgment rule: Distinguish an ongoing free tier, time-limited trial, credits-only trial, open-source self-hosting costs, paid-only access and gated early access. Map which shared scenarios work for free, especially two-person collaboration, BYO subscriptions, remote compute, mobile, issue management and review. Record card requirement, usage caps and whether meaningful evaluation needs payment or sales approval. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: Agent cross-checked (agent-cross-checked) Support: partial Core app is advertised as free with user-provided credentials. Availability: unknown Delivery: native Scope: surfaces=Paseo daemon and APIs, Paseo desktop, Paseo mobile, Paseo web; version=0f20e6dfe4c2573e203dea2aae00aa5983ce4d62; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - ongoing_free — Ongoing free [supported]: Free core application advertised. Sources: paseo:website. - trial — Trial [unknown]: Trial: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - credits_trial — Credits trial [unknown]: Credits trial: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - self_host_cost — Self host cost [partial]: Agent provider and machine costs are separate. Sources: paseo:website. - paid_only — Paid only [unknown]: Paid only: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - early_access — Early access [unknown]: Early access: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - free_scenarios — Free scenarios [unknown]: Free scenarios: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - card_required — Card required [unknown]: Card required: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - usage_caps — Usage caps [unknown]: Usage caps: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - paid_evaluation — Paid evaluation [unknown]: Paid evaluation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: paseo:website ### OWN-09: Pricing transparency Judgment rule: Record publicly stated units, included limits, overage rates, compute/model pass-through or markup, minimum commitment, cancellation and sales-only unknowns. Use transparent, partially specified, quote-only or unknown, with named missing fields. A quote-only enterprise price is a disclosed procurement constraint, not proof of dishonesty. #### OpenAI Codex Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. #### Paseo Verification status: No sourced public finding (not-published) Support: not-published No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability. ## Sources ### codex:cli Codex CLI. CLI runs local tools, resumes chats, delegates subagents and supports scripted execution. - URL: https://learn.chatgpt.com/docs/codex/cli.md - Locator: Capabilities and installation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### codex:auth Authentication. Desktop, CLI and IDE local work support subscription or API authentication; cloud requires ChatGPT sign-in. - URL: https://learn.chatgpt.com/docs/auth.md - Locator: OpenAI authentication - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### codex:cloud Codex cloud. Repository-linked cloud environments run parallel tasks and return summaries, diffs and PRs. - URL: https://learn.chatgpt.com/docs/cloud.md - Locator: Setup and review - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### paseo:website Paseo homepage. Advertises desktop/mobile/web, user-owned remote machines, free app with own agent credentials, optional relay, optional worktrees and Hub team access. - URL: https://paseo.sh/ - Locator: Run it anywhere; automation; FAQ - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-09-23 ### paseo:orchestration Paseo: public-docs/orchestration.md. Documents cross-provider agents, MCP tool injection off by default, CLI launch, subagent track and completion notifications. - URL: https://github.com/getpaseo/paseo/blob/0f20e6dfe4c2573e203dea2aae00aa5983ce4d62/public-docs/orchestration.md - Locator: public-docs/orchestration.md - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### paseo:desktop-package Paseo: packages/desktop/package.json. Desktop package declares Electron 44.2.0. - URL: https://github.com/getpaseo/paseo/blob/0f20e6dfe4c2573e203dea2aae00aa5983ce4d62/packages/desktop/package.json - Locator: packages/desktop/package.json - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-09-23 - Commit: 0f20e6dfe4c2573e203dea2aae00aa5983ce4d62 - Path: packages/desktop/package.json ### paseo:mobile-package Paseo: packages/app/package.json. App manifest declares Expo and React Native. - URL: https://github.com/getpaseo/paseo/blob/0f20e6dfe4c2573e203dea2aae00aa5983ce4d62/packages/app/package.json - Locator: packages/app/package.json - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-09-23 - Commit: 0f20e6dfe4c2573e203dea2aae00aa5983ce4d62 - Path: packages/app/package.json ### paseo:workflows Paseo: public-docs/orchestration-workflows.md. Documents ID-addressed follow-up, parallel worktrees, parentage, remote CLI and heartbeat workflows. Distinguishes interactive Paseo subagents from read-only provider subagent timelines. - URL: https://github.com/getpaseo/paseo/blob/0f20e6dfe4c2573e203dea2aae00aa5983ce4d62/public-docs/orchestration-workflows.md - Locator: public-docs/orchestration-workflows.md - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### paseo:license Paseo: LICENSE. Repository root license is Apache-2.0; component-specific exceptions and hosted parity were not audited. - URL: https://github.com/getpaseo/paseo/blob/0f20e6dfe4c2573e203dea2aae00aa5983ce4d62/LICENSE - Locator: LICENSE - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23