cook

ultrathink.

How cook works

Cook is an incremental loop: break work into tasks, implement one, verify it works, move to the next. The key discipline is that nothing is "done" until there's evidence it works — but how you verify adapts to the situation.

Before you start

If the request is clear, start. If it's ambiguous or multi-faceted, ask clarifying questions. If the work is large or multi-path, plan first (/give-plan). Otherwise, just start.

The loop

1. Break into tasks only when it helps

For a small single-concern request, just implement, verify, and continue.

For multi-step work or collaboration, use tasks.py to track concrete outcomes:

tasks.py --task-file <slug> add "<description>" "<expected outcome>"
tasks.py --task-file <slug> list
tasks.py --task-file <slug> verify <id> "<evidence>"
tasks.py --task-file <slug> done <id>

For other commands, run tasks.py --help. Each task needs a clear expected field — what "done" looks like, stated verifiably. Task files persist in .tasks/, so a fresh context can pick up where the last one left off.

2. Implement → Verify → Review → Next

Pick the next unblocked task, make the change, then hand off to a tester and (for risky work) a reviewer — isolated teammates that judge the change independently. See .claude/skills/test/teammate.md and .claude/skills/review-code/teammate.md for how to spawn them.

/cook owns implementation. The tester owns verification. Give the tester:

• the user-visible claim or acceptance criteria
• the files or behavior you changed
• the most likely regression surface
• any constraints that matter

You can still add durable tests, fixtures, or stable selectors when they belong to the product change itself. Do not stuff temporary verification tactics into /cook just to get through one run.

Before invoking verification, confirm the edits actually landed on disk. If the change you expect is missing from the diff, fix that first; a passing check against unchanged code is worthless evidence.

Do not mark a task done on confidence alone. The tester proves the behavior. The reviewer checks that the implementation is correct, scoped, and aligned with the repo. For risky or non-trivial work, spawn a reviewer before marking the task complete.

Update task status as you go so the execution trail stays trustworthy.

3. Review the whole change set

After the task list is complete, review the combined diff before declaring success. Cross-task issues often appear only in the final aggregate: mismatched assumptions, naming drift, incomplete ripple updates, or verification that was too narrow. Spawn a reviewer for this final pass.

4. Report

When done, summarize:

• what changed
• how each claim was verified
• decisions that materially shaped the implementation
• any follow-up the user should know about

Request

$ARGUMENTS