cookys

cookys/autopilot

Plugin Claude Code

Plugin marketplace listing 1 plugin: autopilot.

cookys/autopilot

Plugin Claude Code

Development autopilot — 29 lifecycle skills + 3 methodology agents + 26 hooks (10 default-on, 16 opt-in) enforcing Three Red Lines discipline. Standalone-capable orchestration that coexists with Superpowers.

cookys/autopilot

Settings file Claude Code

Agent settings configuring env.

cookys/autopilot

Skill Claude CodeCodex

A procedure for updating profile hash records after changing the text of two autopilot workflow files.

cookys/autopilot

Instructions file CodexOpenCode

Instructions for cookys/autopilot, covering autopilot — agent instructions, project structure (spec), coding conventions (spec), change policy (autopilot-added) and testing (spec).

cookys/autopilot

Instructions file

Instructions for cookys/autopilot, covering autopilot — project conventions (claude code), what this repo is, scripts inventory (prefer over llm judgment), when adding a new script and language choice (sh vs js vs py).

cookys/autopilot

Agent

Use when encountering any bug, service outage, test failure, flaky test, or unexpected runtime behavior — applies autopilot's evidence-first methodology (gather → narrow → hypothesize → verify → propose-fix). Never guesses from memory. Triggers PUA mode after 2+ failed attempts. Read-only diagnostic — produces fix…

cookys/autopilot

Agent

Use when breaking fuzzy requirements into parallelizable subtasks, decomposing L-size work, or producing structured Task Breakdowns — applies autopilot's six-element Task Prompt contract (goal / scope / input / output / acceptance / boundaries). Read-only — does not write code or apply edits. Dispatched by…

cookys/autopilot

Agent

Use when performing pre-commit / pre-merge review, security audit, or plan critique — applies autopilot's Three Red Lines (closure / fact-driven / exhaustiveness). Every finding cites file:line. Default-assumes everything is broken until verified. Dispatched primarily via autopilot:quality-pipeline.

cookys/autopilot

Skill Claude CodeCodex

Closing sequence forcing function — use at the END of any dev-flow workflow (L, H, Fix, S) to guarantee no step in the closing sequence gets silently compressed or skipped. On invocation, creates size-appropriate sub-tasks via TaskCreate so each step is individually trackable. MANDATORY for L-size (invoked at L-5) and…

cookys/autopilot

Skill Claude CodeCodex

Save a hard-won lesson or surprising fix so future sessions benefit. Boundary: learn records facts/gotchas; distill produces reusable multi-step procedures from conversation history. Use when: "save this to knowledge", "record this", "remember for next time", "/learn", "記下來", "存到 knowledge", "記住這個", user shares a…

cookys/autopilot

Skill Claude CodeCodex

Run pre-commit or pre-merge quality checks: tests, completeness scan (no stubs/TODOs/mocks), code review. Use when: "quality gate", "quality checks", "run tests before merge", "check for stubs", "scan for completeness", "is this ready to commit?", "pre-merge review", "品質檢查", "準備好可以 commit 了嗎", "跑一下檢查". Not for…

cookys/autopilot

Skill Claude CodeCodex

Start here before writing any code — sizes task (S/L/H/Fix), sets up branch and session rules. Use when: "I'm starting on X", "quick fix for Y", "continuing from yesterday", "hotfix needed", "let's implement X", "skip to coding", "我要開始做 X", "快速修一下", "接續昨天的進度", resuming a feature branch, or any task that touches code.…

cookys/autopilot

Skill Claude CodeCodex

Start here before writing any code — sizes task (S/L/H/Fix), sets up branch and session rules. Use when: "I'm starting on X", "quick fix for Y", "continuing from yesterday", "hotfix needed", "let's implement X", "skip to coding", "我要開始做 X", "快速修一下", "接續昨天的進度", resuming a feature branch, or any task that touches code.…

cookys/autopilot

Hook

Runs before the context is compacted, executing state-checkpoint.js via node. From cookys/autopilot.

cookys/autopilot

Hook

Runs when a session starts on startup, clear and compact, executing session-start.js and version-drift-check.js via node (2 commands). From cookys/autopilot.

cookys/autopilot

Hook

Runs when a session ends, executing session-handoff.js via node. From cookys/autopilot.

cookys/autopilot

Hook

Runs before the agent uses a tool, executing opt-in-multiplexer.js via node. From cookys/autopilot.

cookys/autopilot

Hook

Runs after a tool call finishes for Write and Edit tool calls, executing intent-capture.js, reload-watch.js, audit-log.js, log-error.js, failure-escalation.js, opt-in-multiplexer.js and suggest-compact.js via node (7 commands). From cookys/autopilot.

cookys/autopilot

Hook

Runs when a tool call fails, executing opt-in-multiplexer.js via node. From cookys/autopilot.

cookys/autopilot

Hook

Runs when the agent finishes a response, executing opt-in-multiplexer.js via node. From cookys/autopilot.

cookys/autopilot

Skill Claude CodeCodex

Contact an already-running persistent coding-agent session by exact name. Prefer Claude native messaging when it can address the target; otherwise use the installed Agent Call CLI. Never use this route to create temporary workers.

cookys/autopilot

Skill Claude CodeCodex

Compare two existing implementations and find every difference. Use when: "compare X with Y", "check X against Y", "verify X matches Y", "flag anything missing", "比對 X 和 Y", "檢查有沒有漏掉", "驗證是否一致", feature parity review between old and new systems, an existing spec against an implemented target, or cross-system…

cookys/autopilot

Skill Claude CodeCodex

Pre-code Socratic design exploration — when the options don't exist yet. Use when: "I haven't figured out the approach", "help me think through X", "what should this even be / 還沒想清楚", "explore how to do X before we build", "我不確定要怎麼做", "尚未成形 / 沒有方向". DISCOVERS the options, surfaces 2-3 genuinely different approaches…