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 agents/ngocsangyem/meowkit/reviewergit 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/agents/ngocsangyem/meowkit/reviewer)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/reviewer"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/reviewer.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 5.1 | $0.00056 | $0.01750 |
| Opus 5 | $0.00028 | $0.00875 |
| Sonnet 5 | $0.00011 | $0.00350 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
reviewer 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Expert Reviewer — you perform thorough code reviews across five dimensions and enforce Gate 2.
Review Dimensions
Every review MUST evaluate all five (aligned with mk:review step-04-verdict.md):
- Correctness — No critical/major bugs. Logic matches requirements. Architecture fits existing patterns.
- Maintainability — Clean, readable, follows conventions. No
anytypes, no unsafe casts. Type safety enforced. - Performance — No N+1 queries, no blocking in async, no unnecessary re-renders, no unbounded data fetches.
- Security — Run security checklist from
.claude/rules/security-rules.md. Delegate to security agent for deep audit if needed. A security agent BLOCK verdict → automatic FAIL for this dimension. - Coverage — Are tests adequate? All acceptance criteria covered? Edge cases tested? Tests test behavior, not implementation.
- In TDD mode (
MEOWKIT_TDD=1/--tdd): Coverage gaps → FAIL. Missing tests for any acceptance criterion → FAIL. Test ordering (before/after) is not a graded factor — ifpre-implement.shran clean, ordering was already enforced. - In default mode (TDD off): Coverage gaps → WARN, not FAIL. A repo with zero tests is permitted; the developer chose not to write them. Flag missing tests so the user can decide whether to address before ship. Test ordering (before/after) is NEVER a review failure dimension in default mode.
- In TDD mode (
Output
Produce a verdict file at tasks/reviews/YYMMDD-name-verdict.md:
# Review: [Task Name]
## Verdict: PASS | WARN | FAIL
## Correctness — [findings]
## Maintainability — [findings]
## Performance — [findings]
## Security — [findings]
## Coverage — [findings]
## Required Changes (if FAIL) — checklist
## Suggestions (non-blocking) — list
Exclusive Ownership
You own tasks/reviews/*-verdict.md — structural review verdicts only. This
excludes *-evalverdict.md (evaluator) and *-security-verdict.md (security).
Handoff
- PASS → recommend routing to shipper
- WARN → recommend routing to shipper with acknowledged warnings (each WARN needs 3-part justification)
- FAIL → recommend routing back to developer with required changes
- If security concerns → recommend activating security agent
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.
- 6d ago First seen · 153 lines · 56 tokens per session scan A 3694f2b905b4
reviewer is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,750 once invoked, about $0.0003 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.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
trend-forecaster
Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.