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.
git clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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.
[](https://agentmods.dev/commands/ngocsangyem/meowkit/cook)<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/cook"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/cook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/cook"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/cook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00415 |
| Opus 5.5 | $0.00000 | $0.00166 |
| Sonnet 5.5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
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 1mo 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.
What it actually says
/cook — Implementation Pipeline
Usage
/cook [feature description]
/cook [plan-path]
/cook [feature description] --tdd
Purpose
Run the current implementation workflow for a single task: orient, plan, optionally test first, build, simplify, verify, review, ship, and reflect. The authoritative procedure lives in mk:cook.
Dispatch
Activate mk:cook with the user's task or plan path. Keep Gate 1 (plan approval) and Gate 2 (review approval) intact.
Flags
--tdd— Opt into strict test-first mode for this run. Default: off.
TDD mode dispatch (MANDATORY when --tdd is in invocation)
If the user invocation contains --tdd, the first action before any workflow step is to write the TDD sentinel file:
mkdir -p .claude/session-state && echo on > .claude/session-state/tdd-mode
This sentinel is the compatibility mechanism used by workflow helpers. MEOWKIT_TDD=1 remains a higher-precedence environment opt-in for existing automation.
Safety notes
When a plan path is provided, scan the plan directory for tdd: true, ## Tests Before, or ## Regression Gate. If found and neither --tdd nor MEOWKIT_TDD=1 is active, print:
Plan contains TDD sections but cook is not in TDD mode. Re-run with --tdd to enforce RED-first execution, or continue in default mode with TDD guidance only.
- Gate 1 (after Phase 1): Approve/reject/revise the plan.
- Gate 2 (after Phase 4): Approve/reject the review verdict, acknowledge WARNs.
- Gate 2 is never auto-approved.
- In default mode, test-first enforcement is off unless the user requested tests or the approved plan requires them.
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.
- 1mo ago First seen · 44 lines · 0 tokens per session scan A 94cb449311f7
cook is a command published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 415 tokens. 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.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
review
Submit a story for verification (In Progress → In Review, no PR yet).
standup
Alias of /board — the async sprint snapshot.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.