feature-implement

Codex compatibility note:

• Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. Author .claude/**; mirrors are generated.
• Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
• Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, merge steps without explicit user approval. Inside a workflow run, $start-workflow → Workflow-step mode bounds this rule. [BLOCKING] Before each step or sub-skill call, update todo tracking: in_progress on start, completed on end. [BLOCKING] Every completed/skipped step MUST include evidence or explicit skip reason. [BLOCKING] If Task tools unavailable, maintain equivalent step-by-step plan tracker with same status transitions.

Work tracking: Keep the project's tracked work current in the same change, as its root instructions (CLAUDE.md or AGENTS.md) say. When the project uses the portable tracker (taskTracking.mode is observe or linked), read the linked work integration guide at capture, start, saved-work, verification, handoff and close-out checkpoints. Use the actual linked producer and exact items; retain the primary outcome and record optional upkeep once through the common owner. Continue untracked when no link exists; acceptance remains explicit.

Quick Summary

Goal: Ship a correct, fully-verified feature that satisfies the saved Goal Contract — implemented with deep research, comprehensive planning, and maximum quality verification (planned, reviewed, tested, documented) — with no skipped quality gate on any non-trivial change.

Summary: Resolve the saved goal and spec contract, research and trace the feature, obtain an approved plan, implement every phase with its tests written together, review statically, verify once with a mutation check (SYNC:verify-last-order), reconcile specs and docs, and close with evidence; use fast mode only when every trivial-task condition is satisfied.

Workflow:

1. Research — Deep investigation, multiple researcher subagents
2. Plan — Detailed plan via $plan; user approval required
3. Implement — Execute with full code review + SRE review
4. Review, then verify once — static review fix-loop over the whole changeset, then run all tests once with a mutation check (fix and re-run to green; re-review only if that edited anything), update docs

Key Rules:

• Maximum thoroughness: research → plan → implement → review → test → docs
• User approval required at plan stage
• Break work into todo tasks; add final self-review task

feature-implement vs plan --mode=execute: feature-implement takes an idea/feature description and goes idea → research → plan (created here) → shipped. Use $plan --mode=execute instead when a plan file already exists and you only need disciplined phase-by-phase execution + commit. feature-implement owns the front of the pipeline (research + planning); plan --mode=execute owns the back (phase gates + auto-commit + --parallel/--approval/--tests flags).