[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M754SRHHH98FE4CFWG64ZJMA":3,"skill-same:01M754SRHHH98FE4CFWG64ZJMA":106},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M754SRHHH98FE4CFWG64ZJMA","codex-workflow-autopilot",null,"Use after intent is known to route build, fix, review, debug, docs, or Scrum requests into ordered workflow steps with exit criteria.","Bang-isme\u002FAgencyCLI","Bang-isme","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F179383529?v=4","01M754NDM8K05SAX2V31R63WEE","01M754NDMV48ECFT4HY6X2CKQ0",2,"MIT","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: codex-workflow-autopilot\ndescription: Use after intent is known to route build, fix, review, debug, docs, or Scrum requests into ordered workflow steps with exit criteria.\nload_priority: on-demand\n---\n\n## TL;DR\nRoute tasks by complexity: complex -> Thinking Partner + Devil's Advocate, teaching -> Teaching Mode + explain_code.py, simple -> direct execution. Map intent to workflow (build\u002Ffix\u002Freview\u002Fdebug\u002Fdocs). Use BMAD 4-phase for complex. Always end with Phase X quality gate.\n\n# Workflow Autopilot\n\n## Activation\n\n1. Activate after intent analysis is confirmed.\n2. Activate on explicit `$codex-workflow-autopilot` or `$route`.\n3. Activate teaching mode on `$teach`, \"explain\", or \"walk me through\".\n4. Activate Scrum overlay on backlog, story, sprint, review, retrospective, release-readiness, or shorthand commands such as `$sprint-plan`, `$story-ready-check`, `$retro`, and `$release-readiness`.\n5. Activate reasoning rigor on `$codex-reasoning-rigor`, `$rigor`, \"don't be generic\", \"go deeper\", \"make it specific\", or \"use the repo, not generic advice\".\n6. Activate on alias triggers: `$plan`, `$debug`, `$create`, `$prototype`, `$review`, `$deploy`, `$handoff`, `$refactor`.\n7. When activated via alias, load the corresponding `.workflows\u002F\u003Cname>.md` file before executing the flow.\n8. Activate brainstorm mode on `$brainstorm`, \"brainstorm\", \"think through options\", or \"explore approaches\".\n9. Activate review-feedback routing on `$review-feedback`, \"address review feedback\", or \"respond to code review\".\n10. Route \"prototype\", \"MVP\", \"fullstack\", \"from scratch\", or \"build whole app\" to `$prototype` and require `codex-spec-driven-development` before implementation.\n11. Activate project pulse on `$today`, `$pulse`, `$daily`, `$status`, `$brief`, \"hôm nay thế nào?\", \"what's next?\", \"what should I work on?\", or \"project status\". Route to `codex-project-pulse`.\n\n## Behavioral Protocol Decision Tree\n\n```\nAgent context loaded?\n    |- Yes -> apply agent behavioral rules + file_ownership boundaries\n    |   `- Then route to the matching workflow mode or alias file\n    |\n    `- No -> fallback to existing keyword-based mode detection\n        |\n        `- Task complexity?\n            |- Complex (architecture\u002Fdesign\u002Fmulti-file) -> activate Thinking Partner mode\n            |   `- Before presenting solution -> activate Devil's Advocate mode\n            |\n            |- Teaching request -> activate Teaching Mode + explain_code.py\n            |\n            `- Simple (single file fix) -> direct execution\n```\n\n## Behavioral Modes\n\n| Signals | Mode | Behavior |\n| --- | --- | --- |\n| what if, ideas, options | brainstorm | ask clarifying questions and present alternatives, no code |\n| think with me, compare options, help me decide | thinking-partner | co-think with tradeoff-first framing and explicit decision criteria |\n| build, create, implement | implement | execute quickly with production-focused output, enforce TDD |\n| prototype, MVP, fullstack, from scratch | prototype | run `$hook` -> `$init-profile` if needed -> `$genome`\u002F`$init-docs` -> `$spec` -> `$plan` -> implementation -> `$check-full` |\n| test first, TDD, red-green, failing test | tdd | enforce RED-GREEN-REFACTOR cycle via `$tdd`, no production code without failing test |\n| error, bug, broken | debug | 4-phase systematic debugging via `$root-cause`: root cause → pattern → hypothesis → fix |\n| review, audit, check | review | inspect and report findings by severity |\n| challenge this, poke holes, red team, counterargument | devils-advocate | stress-test assumptions, expose risks, and propose mitigations |\n| explain, teach, learn | teach | explain progressively with examples |\n| deploy, release, ship | ship | prioritize stability and complete checks |\n\n## Scrum Overlay Trigger\n\nTrigger Scrum overlay when the request mentions:\n\n- backlog, user story, acceptance criteria, refinement\n- sprint planning, sprint backlog, sprint goal, daily scrum\n- sprint review, retrospective, release readiness\n- product owner, scrum master, cross-functional handoff\n- Scrum shorthand aliases such as `$scrum-install`, `$scrum-update`, `$sprint-plan`, `$story-ready-check`, `$story-delivery`, `$retro`, and `$release-readiness`\n\nLoad and apply: `references\u002Fworkflow-scrum.md`.\nKeep the routing contract in sync with `references\u002Fworkflow-routing-contract.json`.\n\nRules:\n\n- keep the base workflow (`build`, `fix`, `debug`, `review`, or `deploy`) for the actual engineering work\n- add a Scrum coordination layer when the request depends on ceremony output or multi-role handoffs\n- recommend `codex-scrum-subagents` when the project needs a local `.agent` kit for repeatable role briefs and workflows\n- if a story is not ready, route back to refinement instead of coding immediately\n\n## Reasoning Rigor Trigger\n\nTrigger this overlay when the user asks for:\n\n- deeper thinking or stronger tradeoffs\n- less generic output\n- more evidence, monitoring, or explicit risks\n- repo-grounded recommendations instead of generic best practices\n\nLoad and apply: `codex-reasoning-rigor`.\n\nRules:\n\n- force a task contract before solutioning\n- compare at least 2 options when tradeoffs are non-trivial\n- add evidence, risks, and next-step contract to the output\n- recommend `$output-guard` before finalizing high-stakes written deliverables\n\n## Thinking-Partner Trigger\n\nTrigger this mode when user asks for collaborative reasoning rather than immediate implementation.\n\n- Signal examples: \"think with me\", \"compare options\", \"which approach is better\", \"help me decide\".\n- Load and apply: `references\u002Fthinking-partner-mode.md`.\n- Ask focused clarifying questions before proposing workflow.\n- Present option matrix with tradeoffs, risks, and recommended path.\n- Convert selected path back to workflow steps and exit criteria.\n\n## Devil's Advocate Trigger\n\nTrigger this mode when user asks for challenge, risk probing, or plan hardening.\n\n- Signal examples: \"be critical\", \"find blind spots\", \"red team this plan\", \"play devil's advocate\".\n- Load and apply: `references\u002Fdevils-advocate-mode.md`.\n- Attack assumptions explicitly and rank findings by impact\u002Flikelihood.\n- Provide mitigation actions and clear stop\u002Fship criteria.\n- Return to normal workflow mode only after key risks are addressed or explicitly accepted.\n\n## Teaching Mode Trigger\n\nTrigger this mode when user asks to understand project code, not to modify it.\n\n- Signal examples: `$teach`, \"explain this\", \"teach me\", \"how does this work\", \"walk me through\".\n- Load and apply: `references\u002Fteaching-mode-spec.md`.\n- Prefer project-specific explanation over generic language\u002Fframework theory.\n- Use `scripts\u002Fexplain_code.py` as optional context helper for functions\u002Fimports\u002Fimported-by mapping.\n- Output in four layers: what, how, why, connections, then gotchas.\n- Keep scope tight to user request (function\u002Ffile\u002Fmodule) and avoid unnecessary full-file dumps.\n\n## Intent to Workflow\n\n| Intent | Steps | Exit Criteria |\n| --- | --- | --- |\n| build | analyze → plan ($plan) → isolate ($worktree) → TDD implement ($tdd) → test → gate | tests pass, TDD verified, gate pass |\n| prototype | preflight ($hook) -> profile\u002Fcontext\u002Fdocs -> spec ($spec) -> plan ($plan) -> TDD implementation -> role-doc\u002Fknowledge update -> full gate | spec exists, acceptance criteria pass, full gate pass or advisory warnings listed |\n| fix | systematic debug ($root-cause) → root-cause → regression test ($tdd) → fix → gate | root cause found, regression test pass, gate pass |\n| review | inspect → categorize findings → recommend actions | findings documented with severity |\n| debug | systematic debug ($root-cause) → Phase 1-4 → test → gate | verified fix with evidence, gate pass |\n| docs | scope change → update docs → verify links\u002Faccuracy → gate | docs updated and verified |\n\n## Scrum Ceremony Routing\n\n| Scrum Signal | Suggested Ceremony | Base Workflow | Recommended Roles |\n| --- | --- | --- | --- |\n| vague backlog item, user story, acceptance criteria | backlog refinement | build | product-owner -> scrum-master |\n| sprint planning, sprint goal, forecast | sprint planning | build | scrum-master -> product-owner -> delivery leads |\n| blocker, dependency, daily sync | daily scrum | debug | scrum-master |\n| ready story in sprint | story delivery | build or fix | scrum-orchestrator + delivery roles + qa-engineer |\n| sprint demo, stakeholder feedback | sprint review | review | product-owner + scrum-master + qa-engineer |\n| process issue, improvement experiment | retrospective | review | scrum-master + squad |\n| ship decision, rollback, release gate | release readiness | deploy | scrum-master + qa-engineer + security-engineer + devops-engineer |\n\n## BMAD for Complex Requests\n\nUse BMAD when intent analysis marks `complexity: complex`.\n\n### Phase 1: Analysis (no code)\n\n- confirm requirements and constraints\n- inspect existing patterns\n- capture key decisions\n\n### Phase 2: Planning (no code)\n\n- create plan via `$codex-plan-writer` or `$plan`\n- define task-level input\u002Foutput\u002Fverify\n\nCheckpoint: wait for explicit user approval before Phase 3.\n\n### Phase 3: Solutioning (no code)\n\n- finalize architecture and data flow decisions\n- identify cross-file impacts\n\n### Phase 4: Implementation (code)\n\n- **For complex tasks:** Set up isolated workspace via `$worktree`\n- **For plan with independent tasks:** Use subagent execution via `$sdd`\n- **For all code changes:** Follow TDD cycle via `$tdd`\n- implement task by task\n- run tests\u002Fdocs as workflow requires\n\n### Phase X: Verification (always last)\n\n1. Run `$codex-execution-quality-gate` or `$gate`.\n2. If gate fails, fix blockers and rerun.\n3. Do not declare completion before gate decision.\n4. Use `$finish` to handle branch completion if using worktree.\n\n## Reference Files\n\n- `references\u002Fworkflow-routing-contract.json`: machine-checkable routing contract for modes, overlays, and output fields.\n- `references\u002Fthinking-partner-mode.md`: use only when collaborative option analysis is requested.\n- `references\u002Fdevils-advocate-mode.md`: use only when explicit challenge\u002Frisk probing is requested.\n- `references\u002Fteaching-mode-spec.md`: use when user asks for code walkthrough, explanation, or teaching.\n- `references\u002Fworkflow-scrum.md`: use when the request maps to Scrum ceremonies, story readiness, or release readiness.\n- `references\u002Fworkflow-create.md`: execution template for new feature workflows.\n- `..\u002F.workflows\u002Fprototype.md`: alias workflow for MVP\u002Ffullstack prototype execution.\n- `references\u002Fworkflow-debug.md`: execution template for debugging workflows.\n- `references\u002Fworkflow-review.md`: execution template for review workflows.\n- `references\u002Fworkflow-refactor.md`: execution template for refactoring workflows.\n- `references\u002Fworkflow-deploy.md`: execution template for deployment workflows.\n- `references\u002Fworkflow-handoff.md`: execution template for session handoff workflows.\n- `references\u002Fworkflow-plan.md`: execution template for planning and BMAD Phase 1-2 workflows.\n- `..\u002F.workflows\u002Fplan.md`: alias workflow for planning and BMAD Phase 1-2.\n- `..\u002F.workflows\u002Fdebug.md`: alias workflow for 4-phase debugging.\n- `..\u002F.workflows\u002Fcreate.md`: alias workflow for build-mode execution.\n- `..\u002F.workflows\u002Freview.md`: alias workflow for review plus written-output quality checks.\n- `..\u002F.workflows\u002Fdeploy.md`: alias workflow for ship preparation and full gate.\n- `..\u002F.workflows\u002Fhandoff.md`: alias workflow for session transfer and summary generation.\n- `..\u002F.workflows\u002Frefactor.md`: alias workflow for restructuring and simplifying code.\n\n## Helper Script\n\n- `scripts\u002Fexplain_code.py`: optional context helper for functions, imports, and imported-by mapping.\n- See `skills\u002F.system\u002FREGISTRY.md` for full script paths.\n\n## Script Invocation Discipline\n\n1. Always run `--help` before invoking a script.\n2. Treat scripts as black-box helpers and prefer direct execution over source inspection.\n3. Read script source only when customization or bug fixing is required.\n\n## Overrides\n\n- \"skip test\": remove test step and warn quality confidence is reduced.\n- \"no docs\": remove docs step and warn maintainability confidence is reduced.\n- \"just do it\": default to build workflow and still show brief step plan.\n- \"skip plan\": allow for simple scope; for complex scope warn and reconfirm.\n\n## Scope Heuristic\n\n- small: 1-3 files, single concern\n- medium: 4-10 files, multiple concerns\n- large: 10+ files or architectural impact\n\n## Output Contract\n\nReturn fenced JSON in conversation:\n\n```json\n{\n  \"mode\": \"brainstorm | thinking-partner | implement | tdd | debug | review | devils-advocate | teach | ship\",\n  \"workflow_type\": \"build | fix | review | debug | docs | refactor | deploy | handoff\",\n  \"steps\": [\"step1\", \"step2\"],\n  \"exit_criteria\": [\"criterion1\"],\n  \"estimated_scope\": \"small | medium | large\",\n  \"phase\": \"analysis | planning | solutioning | implementation | verification\",\n  \"coordination_overlay\": \"none | scrum\",\n  \"ceremony\": \"none | backlog-refinement | sprint-planning | daily-scrum | story-delivery | sprint-review | retrospective | release-readiness\"\n}\n```\n\nPrimary execution remains sequential by default. Native Codex custom agents can participate when they are installed and explicitly selected.\n","## TL;DR\nRoute tasks by complexity: complex -> Thinking Partner + Devil's Advocate, teaching -> Teaching Mode + explain_code.py, simple -> direct execution. Map intent to workflow (build\u002Ffix\u002Freview\u002Fdebug\u002Fdocs). Use BMAD 4-phase for complex. Always end with Phase X quality gate.\n\n# Workflow Autopilot\n\n## Activation\n\n1. Activate after intent analysis is confirmed.\n2. Activate on explicit `$codex-workflow-autopilot` or `$route`.\n3. Activate teaching mode on `$teach`, \"explain\", or \"walk me through\".\n4. Activate Scrum overlay on backlog, story, sprint, review, retrospective, release-readiness, or shorthand commands such as `$sprint-plan`, `$story-ready-check`, `$retro`, and `$release-readiness`.\n5. Activate reasoning rigor on `$codex-reasoning-rigor`, `$rigor`, \"don't be generic\", \"go deeper\", \"make it specific\", or \"use the repo, not generic advice\".\n6. Activate on alias triggers: `$plan`, `$debug`, `$create`, `$prototype`, `$review`, `$deploy`, `$handoff`, `$refactor`.\n7. When activated via alias, load the corresponding `.workflows\u002F\u003Cname>.md` file before executing the flow.\n8. Activate brainstorm mode on `$brainstorm`, \"brainstorm\", \"think through options\", or \"explore approaches\".\n9. Activate review-feedback routing on `$review-feedback`, \"address review feedback\", or \"respond to code review\".\n10. Route \"prototype\", \"MVP\", \"fullstack\", \"from scratch\", or \"build whole app\" to `$prototype` and require `codex-spec-driven-development` before implementation.\n11. Activate project pulse on `$today`, `$pulse`, `$daily`, `$status`, `$brief`, \"hôm nay thế nào?\", \"what's next?\", \"what should I work on?\", or \"project status\". Route to `codex-project-pulse`.\n\n## Behavioral Protocol Decision Tree\n\n```\nAgent context loaded?\n    |- Yes -> apply agent behavioral rules + file_ownership boundaries\n    |   `- Then route to the matching workflow mode or alias file\n    |\n    `- No -> fallback to existing keyword-based mode detection\n        |\n        `- Task complexity?\n            |- Complex (architecture\u002Fdesign\u002Fmulti-file) -> activate Thinking Partner mode\n            |   `- Before presenting solution -> activate Devil's Advocate mode\n            |\n            |- Teaching request -> activate Teaching Mode + explain_code.py\n            |\n            `- Simple (single file fix) -> direct execution\n```\n\n## Behavioral Modes\n\n| Signals | Mode | Behavior |\n| --- | --- | --- |\n| what if, ideas, options | brainstorm | ask clarifying questions and present alternatives, no code |\n| think with me, compare options, help me decide | thinking-partner | co-think with tradeoff-first framing and explicit decision criteria |\n| build, create, implement | implement | execute quickly with production-focused output, enforce TDD |\n| prototype, MVP, fullstack, from scratch | prototype | run `$hook` -> `$init-profile` if needed -> `$genome`\u002F`$init-docs` -> `$spec` -> `$plan` -> implementation -> `$check-full` |\n| test first, TDD, red-green, failing test | tdd | enforce RED-GREEN-REFACTOR cycle via `$tdd`, no production code without failing test |\n| error, bug, broken | debug | 4-phase systematic debugging via `$root-cause`: root cause → pattern → hypothesis → fix |\n| review, audit, check | review | inspect and report findings by severity |\n| challenge this, poke holes, red team, counterargument | devils-advocate | stress-test assumptions, expose risks, and propose mitigations |\n| explain, teach, learn | teach | explain progressively with examples |\n| deploy, release, ship | ship | prioritize stability and complete checks |\n\n## Scrum Overlay Trigger\n\nTrigger Scrum overlay when the request mentions:\n\n- backlog, user story, acceptance criteria, refinement\n- sprint planning, sprint backlog, sprint goal, daily scrum\n- sprint review, retrospective, release readiness\n- product owner, scrum master, cross-functional handoff\n- Scrum shorthand aliases such as `$scrum-install`, `$scrum-update`, `$sprint-plan`, `$story-ready-check`, `$story-delivery`, `$retro`, and `$release-readiness`\n\nLoad and apply: `references\u002Fworkflow-scrum.md`.\nKeep the routing contract in sync with `references\u002Fworkflow-routing-contract.json`.\n\nRules:\n\n- keep the base workflow (`build`, `fix`, `debug`, `review`, or `deploy`) for the actual engineering work\n- add a Scrum coordination layer when the request depends on ceremony output or multi-role handoffs\n- recommend `codex-scrum-subagents` when the project needs a local `.agent` kit for repeatable role briefs and workflows\n- if a story is not ready, route back to refinement instead of coding immediately\n\n## Reasoning Rigor Trigger\n\nTrigger this overlay when the user asks for:\n\n- deeper thinking or stronger tradeoffs\n- less generic output\n- more evidence, monitoring, or explicit risks\n- repo-grounded recommendations instead of generic best practices\n\nLoad and apply: `codex-reasoning-rigor`.\n\nRules:\n\n- force a task contract before solutioning\n- compare at least 2 options when tradeoffs are non-trivial\n- add evidence, risks, and next-step contract to the output\n- recommend `$output-guard` before finalizing high-stakes written deliverables\n\n## Thinking-Partner Trigger\n\nTrigger this mode when user asks for collaborative reasoning rather than immediate implementation.\n\n- Signal examples: \"think with me\", \"compare options\", \"which approach is better\", \"help me decide\".\n- Load and apply: `references\u002Fthinking-partner-mode.md`.\n- Ask focused clarifying questions before proposing workflow.\n- Present option matrix with tradeoffs, risks, and recommended path.\n- Convert selected path back to workflow steps and exit criteria.\n\n## Devil's Advocate Trigger\n\nTrigger this mode when user asks for challenge, risk probing, or plan hardening.\n\n- Signal examples: \"be critical\", \"find blind spots\", \"red team this plan\", \"play devil's advocate\".\n- Load and apply: `references\u002Fdevils-advocate-mode.md`.\n- Attack assumptions explicitly and rank findings by impact\u002Flikelihood.\n- Provide mitigation actions and clear stop\u002Fship criteria.\n- Return to normal workflow mode only after key risks are addressed or explicitly accepted.\n\n## Teaching Mode Trigger\n\nTrigger this mode when user asks to understand project code, not to modify it.\n\n- Signal examples: `$teach`, \"explain this\", \"teach me\", \"how does this work\", \"walk me through\".\n- Load and apply: `references\u002Fteaching-mode-spec.md`.\n- Prefer project-specific explanation over generic language\u002Fframework theory.\n- Use `scripts\u002Fexplain_code.py` as optional context helper for functions\u002Fimports\u002Fimported-by mapping.\n- Output in four layers: what, how, why, connections, then gotchas.\n- Keep scope tight to user request (function\u002Ffile\u002Fmodule) and avoid unnecessary full-file dumps.\n\n## Intent to Workflow\n\n| Intent | Steps | Exit Criteria |\n| --- | --- | --- |\n| build | analyze → plan ($plan) → isolate ($worktree) → TDD implement ($tdd) → test → gate | tests pass, TDD verified, gate pass |\n| prototype | preflight ($hook) -> profile\u002Fcontext\u002Fdocs -> spec ($spec) -> plan ($plan) -> TDD implementation -> role-doc\u002Fknowledge update -> full gate | spec exists, acceptance criteria pass, full gate pass or advisory warnings listed |\n| fix | systematic debug ($root-cause) → root-cause → regression test ($tdd) → fix → gate | root cause found, regression test pass, gate pass |\n| review | inspect → categorize findings → recommend actions | findings documented with severity |\n| debug | systematic debug ($root-cause) → Phase 1-4 → test → gate | verified fix with evidence, gate pass |\n| docs | scope change → update docs → verify links\u002Faccuracy → gate | docs updated and verified |\n\n## Scrum Ceremony Routing\n\n| Scrum Signal | Suggested Ceremony | Base Workflow | Recommended Roles |\n| --- | --- | --- | --- |\n| vague backlog item, user story, acceptance criteria | backlog refinement | build | product-owner -> scrum-master |\n| sprint planning, sprint goal, forecast | sprint planning | build | scrum-master -> product-owner -> delivery leads |\n| blocker, dependency, daily sync | daily scrum | debug | scrum-master |\n| ready story in sprint | story delivery | build or fix | scrum-orchestrator + delivery roles + qa-engineer |\n| sprint demo, stakeholder feedback | sprint review | review | product-owner + scrum-master + qa-engineer |\n| process issue, improvement experiment | retrospective | review | scrum-master + squad |\n| ship decision, rollback, release gate | release readiness | deploy | scrum-master + qa-engineer + security-engineer + devops-engineer |\n\n## BMAD for Complex Requests\n\nUse BMAD when intent analysis marks `complexity: complex`.\n\n### Phase 1: Analysis (no code)\n\n- confirm requirements and constraints\n- inspect existing patterns\n- capture key decisions\n\n### Phase 2: Planning (no code)\n\n- create plan via `$codex-plan-writer` or `$plan`\n- define task-level input\u002Foutput\u002Fverify\n\nCheckpoint: wait for explicit user approval before Phase 3.\n\n### Phase 3: Solutioning (no code)\n\n- finalize architecture and data flow decisions\n- identify cross-file impacts\n\n### Phase 4: Implementation (code)\n\n- **For complex tasks:** Set up isolated workspace via `$worktree`\n- **For plan with independent tasks:** Use subagent execution via `$sdd`\n- **For all code changes:** Follow TDD cycle via `$tdd`\n- implement task by task\n- run tests\u002Fdocs as workflow requires\n\n### Phase X: Verification (always last)\n\n1. Run `$codex-execution-quality-gate` or `$gate`.\n2. If gate fails, fix blockers and rerun.\n3. Do not declare completion before gate decision.\n4. Use `$finish` to handle branch completion if using worktree.\n\n## Reference Files\n\n- `references\u002Fworkflow-routing-contract.json`: machine-checkable routing contract for modes, overlays, and output fields.\n- `references\u002Fthinking-partner-mode.md`: use only when collaborative option analysis is requested.\n- `references\u002Fdevils-advocate-mode.md`: use only when explicit challenge\u002Frisk probing is requested.\n- `references\u002Fteaching-mode-spec.md`: use when user asks for code walkthrough, explanation, or teaching.\n- `references\u002Fworkflow-scrum.md`: use when the request maps to Scrum ceremonies, story readiness, or release readiness.\n- `references\u002Fworkflow-create.md`: execution template for new feature workflows.\n- `..\u002F.workflows\u002Fprototype.md`: alias workflow for MVP\u002Ffullstack prototype execution.\n- `references\u002Fworkflow-debug.md`: execution template for debugging workflows.\n- `references\u002Fworkflow-review.md`: execution template for review workflows.\n- `references\u002Fworkflow-refactor.md`: execution template for refactoring workflows.\n- `references\u002Fworkflow-deploy.md`: execution template for deployment workflows.\n- `references\u002Fworkflow-handoff.md`: execution template for session handoff workflows.\n- `references\u002Fworkflow-plan.md`: execution template for planning and BMAD Phase 1-2 workflows.\n- `..\u002F.workflows\u002Fplan.md`: alias workflow for planning and BMAD Phase 1-2.\n- `..\u002F.workflows\u002Fdebug.md`: alias workflow for 4-phase debugging.\n- `..\u002F.workflows\u002Fcreate.md`: alias workflow for build-mode execution.\n- `..\u002F.workflows\u002Freview.md`: alias workflow for review plus written-output quality checks.\n- `..\u002F.workflows\u002Fdeploy.md`: alias workflow for ship preparation and full gate.\n- `..\u002F.workflows\u002Fhandoff.md`: alias workflow for session transfer and summary generation.\n- `..\u002F.workflows\u002Frefactor.md`: alias workflow for restructuring and simplifying code.\n\n## Helper Script\n\n- `scripts\u002Fexplain_code.py`: optional context helper for functions, imports, and imported-by mapping.\n- See `skills\u002F.system\u002FREGISTRY.md` for full script paths.\n\n## Script Invocation Discipline\n\n1. Always run `--help` before invoking a script.\n2. Treat scripts as black-box helpers and prefer direct execution over source inspection.\n3. Read script source only when customization or bug fixing is required.\n\n## Overrides\n\n- \"skip test\": remove test step and warn quality confidence is reduced.\n- \"no docs\": remove docs step and warn maintainability confidence is reduced.\n- \"just do it\": default to build workflow and still show brief step plan.\n- \"skip plan\": allow for simple scope; for complex scope warn and reconfirm.\n\n## Scope Heuristic\n\n- small: 1-3 files, single concern\n- medium: 4-10 files, multiple concerns\n- large: 10+ files or architectural impact\n\n## Output Contract\n\nReturn fenced JSON in conversation:\n\n```json\n{\n  \"mode\": \"brainstorm | thinking-partner | implement | tdd | debug | review | devils-advocate | teach | ship\",\n  \"workflow_type\": \"build | fix | review | debug | docs | refactor | deploy | handoff\",\n  \"steps\": [\"step1\", \"step2\"],\n  \"exit_criteria\": [\"criterion1\"],\n  \"estimated_scope\": \"small | medium | large\",\n  \"phase\": \"analysis | planning | solutioning | implementation | verification\",\n  \"coordination_overlay\": \"none | scrum\",\n  \"ceremony\": \"none | backlog-refinement | sprint-planning | daily-scrum | story-delivery | sprint-review | retrospective | release-readiness\"\n}\n```\n\nPrimary execution remains sequential by default. Native Codex custom agents can participate when they are installed and explicitly selected.\n",{"name":5,"description":7,"load_priority":23},"on-demand","main","19b976c6b4f182f06d2d2e6b030549f2f8a69cc0","packages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot",0,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI","https:\u002F\u002Fgithub.com\u002FBang-isme","Hi my name is jeff","2026-07-15 19:58:17",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Bang-isme\u002FAgencyCLI --skill codex-workflow-autopilot",{"tool":38,"command":39},"bunx","bunx skills add Bang-isme\u002FAgencyCLI --skill codex-workflow-autopilot",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Bang-isme\u002FAgencyCLI --skill codex-workflow-autopilot","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002FSKILL.md",true,[46,52,56,60,64,68,72,76,80,84,88,92,96,100],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",235,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdevils-advocate-mode.md",1582,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fdevils-advocate-mode.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fteaching-mode-spec.md",1700,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fteaching-mode-spec.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fthinking-partner-mode.md",2052,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fthinking-partner-mode.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fworkflow-create.md",2852,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-create.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fworkflow-debug.md",2604,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-debug.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fworkflow-deploy.md",1795,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-deploy.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fworkflow-handoff.md",1630,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-handoff.md",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fworkflow-plan.md",2316,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-plan.md",{"path":85,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fworkflow-refactor.md",1766,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-refactor.md",{"path":89,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fworkflow-review.md",2896,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-review.md",{"path":93,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fworkflow-routing-contract.json",1576,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-routing-contract.json",{"path":97,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fworkflow-scrum.md",1740,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Freferences\u002Fworkflow-scrum.md",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fexplain_code.py","SCRIPT","脚本",13703,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-workflow-autopilot\u002Fscripts\u002Fexplain_code.py",[107,114,121,128,135,142],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M754T5CB6WCXB2AV8N0M50AC","codex-test-driven-development","Fixture stub for TDD skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-test-driven-development\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":18},"01M754T41J59TG0MJYC52TES58","codex-subagent-execution","Fixture stub for subagent execution skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-subagent-execution\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":18},"01M754T2JDSPA3YF83FK6BMNV6","codex-runtime-hook","Fixture stub for runtime hook skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-runtime-hook\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":18},"01M754T1HG4JRTJVZC2PBFTXDT","codex-plan-writer","Fixture stub for plan writer skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-plan-writer\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":18},"01M754SZJVZKGQR5PSA6YFFY09","codex-execution-quality-gate","Fixture stub for quality gate skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-execution-quality-gate\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":18},"01M754SXBJ1DE0JR6TK0XJ4SAK","codex-demo","Minimal fixture skill for Agency CLI skill-md parser tests.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-demo\u002FSKILL.md",[],[]]