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.
npx agentmods add commands/ngocsangyem/meowkit/reviewgit 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/review)<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/review"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/review.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00629 |
| Opus 5 | $0.00000 | $0.00315 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
review 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — Phase 4: Structural Audit and Gate 2
Usage
/review [optional: specific files or PR number]
Behavior
Triggers Phase 4 structural audit. Runs the 5-dimension review using the structural-audit skill. Enforces Gate 2.
Execution Steps
-
Determine scope. If specific files or a PR number are provided, review only those. Otherwise, review all staged/changed files since the last approved review.
-
Run 5-dimension structural audit using the
structural-auditskill. Evaluate:Dimension What it checks Correctness Does the code do what the plan says? Logic errors, edge cases, off-by-ones. Security Apply rules/security-rules.md. Check for blocked patterns. BLOCK-level findings fail this dimension.Performance N+1 queries, unnecessary re-renders, missing indexes, unbounded loops, memory leaks. Maintainability Naming conventions (per rules/agent-conduct.md(B1)), code duplication, separation of concerns, readability.Test Coverage Are new behaviors covered by tests? Do tests test the right things (behavior, not implementation)? -
Generate verdict file. Write to:
tasks/reviews/YYMMDD-feature-name-verdict.mdThe verdict file contains per-dimension results (PASS/WARN/FAIL) with specific findings.
-
Print summary. Display a table:
🐱 Review Results: ┌─────────────────┬────────┐ │ Dimension │ Result │ ├─────────────────┼────────┤ │ Correctness │ PASS │ │ Security │ PASS │ │ Performance │ WARN │ │ Maintainability │ PASS │ │ Test Coverage │ PASS │ └─────────────────┴────────┘ -
Gate 2 enforcement.
- If any dimension is FAIL: block shipping. Print what must be fixed. Do not proceed.
- If any dimension is WARN: list the warnings and ask the human to acknowledge each one.
- If all dimensions PASS: request explicit human approval to proceed to shipping.
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.
- yesterday First seen · 66 lines · 0 tokens per session scan A 48317737c3d8
review is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 629 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 2026-09-03.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).
review
Submit a story for verification (In Progress → In Review, no PR yet).