Phase 1 - Planning: Create an implementation plan from the spec
- Architect (Opus): Create plan (direct mode, no interview)
- Critic (Opus): Validate plan
- Output:
.omc/plans/autopilot-impl.md
Phase 2 - Execution: Implement the plan using Ralph + Ultrawork
- Executor-low (Haiku): Simple tasks
- Executor (Sonnet): Standard tasks
- Executor-high (Opus): Complex tasks
- Run independent tasks in parallel
Phase 3 - QA: Cycle until all tests pass (UltraQA mode)
- Build, lint, test, fix failures
- Repeat up to 5 cycles
- Stop early if the same error repeats 3 times (indicates a fundamental issue)
Phase 4 - Validation: Multi-perspective review in parallel
- Architect: Functional completeness
- Security-reviewer: Vulnerability check
- Code-reviewer: Quality review
- All must approve; fix and re-validate on rejection
Phase 5 - Cleanup: Delete all state files on successful completion
- Remove
.omc/state/autopilot-state.json, ralph-state.json, ultrawork-state.json, ultraqa-state.json
- Run
/oh-my-codex:cancel for clean exit
Optional settings in .codex/settings.json:
{
"omc": {
"autopilot": {
"maxIterations": 10,
"maxQaCycles": 5,
"maxValidationRounds": 3,
"pauseAfterExpansion": false,
"pauseAfterPlanning": false,
"skipQa": false,
"skipValidation": false
}
}
}
Resume
If autopilot was cancelled or failed, run /oh-my-codex:autopilot again to resume from where it stopped.
Best Practices for Input
- Be specific about the domain -- "bookstore" not "store"
- Mention key features -- "with CRUD", "with authentication"
- Specify constraints -- "using TypeScript", "with PostgreSQL"
- Let it run -- avoid interrupting unless truly needed
Troubleshooting
Stuck in a phase? Check TODO list for blocked tasks, review .omc/autopilot-state.json, or cancel and resume.
QA cycles exhausted? The same error 3 times indicates a fundamental issue. Review the error pattern; manual intervention may be needed.
Validation keeps failing? Review the specific issues. Requirements may have been too vague -- cancel and provide more detail.
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: autopilot3description: Full autonomous execution from idea to working code Use when this capability is needed.4---56<Purpose>7Autopilot takes a brief product idea and autonomously handles the full lifecycle: requirements analysis, technical design, planning, parallel implementation, QA cycling, and multi-perspective validation. It produces working, verified code from a 2-3 line description.8</Purpose>910<Use_When>11- User wants end-to-end autonomous execution from an idea to working code12- User says "autopilot", "auto pilot", "autonomous", "build me", "create me", "make me", "full auto", "handle it all", or "I want a/an..."13- Task requires multiple phases: planning, coding, testing, and validation14- User wants hands-off execution and is willing to let the system run to completion15</Use_When>1617<Do_Not_Use_When>18- User wants to explore options or brainstorm -- use `plan` skill instead19- User says "just explain", "draft only", or "what would you suggest" -- respond conversationally20- User wants a single focused code change -- use `ralph` or delegate to an executor agent21- User wants to review or critique an existing plan -- use `plan --review`22- Task is a quick fix or small bug -- use direct executor delegation23</Do_Not_Use_When>2425<Why_This_Exists>26Most non-trivial software tasks require coordinated phases: understanding requirements, designing a solution, implementing in parallel, testing, and validating quality. Autopilot orchestrates all of these phases automatically so the user can describe what they want and receive working code without managing each step.27</Why_This_Exists>2829<Execution_Policy>30- Each phase must complete before the next begins31- Parallel execution is used within phases where possible (Phase 2 and Phase 4)32- QA cycles repeat up to 5 times; if the same error persists 3 times, stop and report the fundamental issue33- Validation requires approval from all reviewers; rejected items get fixed and re-validated34- Cancel with `/oh-my-codex:cancel` at any time; progress is preserved for resume35</Execution_Policy>3637<Steps>381. **Phase 0 - Expansion**: Turn the user's idea into a detailed spec39 - Analyst (Opus): Extract requirements40 - Architect (Opus): Create technical specification41 - Output: `.omc/autopilot/spec.md`42432. **Phase 1 - Planning**: Create an implementation plan from the spec44 - Architect (Opus): Create plan (direct mode, no interview)45 - Critic (Opus): Validate plan46 - Output: `.omc/plans/autopilot-impl.md`47483. **Phase 2 - Execution**: Implement the plan using Ralph + Ultrawork49 - Executor-low (Haiku): Simple tasks50 - Executor (Sonnet): Standard tasks51 - Executor-high (Opus): Complex tasks52 - Run independent tasks in parallel53544. **Phase 3 - QA**: Cycle until all tests pass (UltraQA mode)55 - Build, lint, test, fix failures56 - Repeat up to 5 cycles57 - Stop early if the same error repeats 3 times (indicates a fundamental issue)58595. **Phase 4 - Validation**: Multi-perspective review in parallel60 - Architect: Functional completeness61 - Security-reviewer: Vulnerability check62 - Code-reviewer: Quality review63 - All must approve; fix and re-validate on rejection64656. **Phase 5 - Cleanup**: Delete all state files on successful completion66 - Remove `.omc/state/autopilot-state.json`, `ralph-state.json`, `ultrawork-state.json`, `ultraqa-state.json`67 - Run `/oh-my-codex:cancel` for clean exit68</Steps>6970<Tool_Usage>71- Before first MCP tool use, call `ToolSearch("mcp")` to discover deferred MCP tools72- Use `ask_codex` with `agent_role: "architect"` for Phase 4 architecture validation73- Use `ask_codex` with `agent_role: "security-reviewer"` for Phase 4 security review74- Use `ask_codex` with `agent_role: "code-reviewer"` for Phase 4 quality review75- Agents form their own analysis first, then consult Codex for cross-validation76- If ToolSearch finds no MCP tools or Codex is unavailable, proceed without it -- never block on external tools77</Tool_Usage>7879<Examples>80<Good>81User: "autopilot A REST API for a bookstore inventory with CRUD operations using TypeScript"82Why good: Specific domain (bookstore), clear features (CRUD), technology constraint (TypeScript). Autopilot has enough context to expand into a full spec.83</Good>8485<Good>86User: "build me a CLI tool that tracks daily habits with streak counting"87Why good: Clear product concept with a specific feature. The "build me" trigger activates autopilot.88</Good>8990<Bad>91User: "fix the bug in the login page"92Why bad: This is a single focused fix, not a multi-phase project. Use direct executor delegation or ralph instead.93</Bad>9495<Bad>96User: "what are some good approaches for adding caching?"97Why bad: This is an exploration/brainstorming request. Respond conversationally or use the plan skill.98</Bad>99</Examples>100101<Escalation_And_Stop_Conditions>102- Stop and report when the same QA error persists across 3 cycles (fundamental issue requiring human input)103- Stop and report when validation keeps failing after 3 re-validation rounds104- Stop when the user says "stop", "cancel", or "abort"105- If requirements were too vague and expansion produces an unclear spec, pause and ask the user for clarification before proceeding106</Escalation_And_Stop_Conditions>107108<Final_Checklist>109- [ ] All 5 phases completed (Expansion, Planning, Execution, QA, Validation)110- [ ] All validators approved in Phase 4111- [ ] Tests pass (verified with fresh test run output)112- [ ] Build succeeds (verified with fresh build output)113- [ ] State files cleaned up114- [ ] User informed of completion with summary of what was built115</Final_Checklist>116117<Advanced>118## Configuration119120Optional settings in `.codex/settings.json`:121122```json123{124 "omc": {125 "autopilot": {126 "maxIterations": 10,127 "maxQaCycles": 5,128 "maxValidationRounds": 3,129 "pauseAfterExpansion": false,130 "pauseAfterPlanning": false,131 "skipQa": false,132 "skipValidation": false133 }134 }135}136```137138## Resume139140If autopilot was cancelled or failed, run `/oh-my-codex:autopilot` again to resume from where it stopped.141142## Best Practices for Input1431441. Be specific about the domain -- "bookstore" not "store"1452. Mention key features -- "with CRUD", "with authentication"1463. Specify constraints -- "using TypeScript", "with PostgreSQL"1474. Let it run -- avoid interrupting unless truly needed148149## Troubleshooting150151**Stuck in a phase?** Check TODO list for blocked tasks, review `.omc/autopilot-state.json`, or cancel and resume.152153**QA cycles exhausted?** The same error 3 times indicates a fundamental issue. Review the error pattern; manual intervention may be needed.154155**Validation keeps failing?** Review the specific issues. Requirements may have been too vague -- cancel and provide more detail.156</Advanced>157158---159> Converted and distributed by [TomeVault](https://tomevault.io/claim/sigridjineth) — claim your Tome and manage your conversions.160<!-- tomevault:4.0:skill_md:2026-04-13 -->
