cook

cook is a command for Claude Code from mrgoonie/human-mcp. It costs 3 tokens per session (376 once invoked), scanned A, original, MIT.

A command for planning and carrying out software-development tasks through research, implementation, testing, debugging, and code review.

In plain words
What is it for?
Use it to create implementation plans, change code, run type checks and tests, investigate failures, and complete a review cycle.
Why use it?
It provides a repeatable process for complex changes and keeps failed tests or review issues in the work until they are addressed.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mrgoonie/human-mcp/cook
Clone the repo
git clone --depth 1 https://github.com/mrgoonie/human-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cook

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrgoonie/human-mcp/cook.svg)](https://agentmods.dev/commands/mrgoonie/human-mcp/cook)
Your own site
<a href="https://agentmods.dev/commands/mrgoonie/human-mcp/cook"><img src="https://agentmods.dev/badge/commands/mrgoonie/human-mcp/cook.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00003 $0.00376
Opus 5 $0.00002 $0.00188
Sonnet 5 $0.00001 $0.00075
Haiku 4.5 $0.00000 $0.00038

Measured 5d ago against content hash 8c5aaa7907cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • polar — 89% identical, 49 lines differ
.claude/commands/cook.md · 20 lines

What it actually says

Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules: $ARGUMENTS

Workflow:

  1. Use planner subagent and researcher subagent to create a implementation plan with TODO tasks in ./plans directory.
  2. Then use general agent (main agent) to implement the plan step by step.
  3. Run type checking and compile the code to make sure there are no syntax errors.
  4. Write the tests for the plan, make sure you don't use fake data just to pass the tests, tests should be real and cover all possible cases.
  5. Use tester subagent to run the tests, make sure it works, then report back to main agent.
  6. If there are issues or failed tests, use debugger subagent to find the root cause of the issues, then ask main agent to fix all of them and
  7. Repeat the process until all tests pass or no more issues are reported. Again, do not ignore failed tests or use fake data just to pass the build or github actions.
  8. After finishing, delegate to code-reviewer subagent to review code. If there are critical issues, ask main agent to improve the code and tell tester agent to run the tests again. Repeat the process until all tests pass.
  9. When all tests pass, code is reviewed, the tasks are completed, report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
  10. If user approves the changes, use docs-manager subagent to update the docs if needed.
  11. Finally use git-manager subagent to commit and push to git repository.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 20 lines · 3 tokens per session scan A 8c5aaa7907cb

Subscribe to this mod's changes

cook is a command published in the GitHub repository mrgoonie/human-mcp (294 stars, last pushed 5mo ago), licensed MIT. It adds 3 tokens to every session and 376 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.