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/plumpslabs/matcha/matcha-reviewgit clone --depth 1 https://github.com/plumpslabs/matchaWrote 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/plumpslabs/matcha/matcha-review)<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-review"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-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 5.1 | $0.00020 | $0.01453 |
| Opus 5 | $0.00010 | $0.00727 |
| Sonnet 5 | $0.00004 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
matcha: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 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/matcha:review
The gate between code and "done". Nothing ships until this passes.
Risk-Based Routing
Not all code needs the same review. Matcha auto-detects risk tier and routes accordingly:
| Tier | Risk | What | Review |
|---|---|---|---|
| L0 | Disposable | Spikes, scripts, temp | Output check only |
| L1 | Low | Copy, fixtures, UI text | Lint + typecheck |
| L2 | Product Logic | Features, API, business logic | Full review (9 categories) |
| L3 | High Risk | Auth, payments, DB, crypto | Expert review + threat model |
Auto-Detection
Risk tier is detected via trigger packs — domain-specific signal rules.
Default signals (no pack loaded):
| Signal | Tier |
|---|---|
| Files in security-sensitive paths | L3 (use trigger pack for specifics) |
| Keywords: credentials, tokens, secrets | L3 |
| Database schema changes | L3 |
| New public API endpoints | L2 |
| Test files, fixtures, mocks | L1 |
| Documentation, comments | L1 |
| Files in disposable paths | L0 |
// matcha:explain with justification |
L0 |
Diff-size heuristic: tiny diffs (≤10 lines) stay low; large diffs (>100 lines or many files) escalate a tier.
Review Checklists by Tier
L0 — Output Check
- Does it run without errors?
- In the right temp directory?
- Verdict: PASS if runs.
L1 — Lint + Typecheck
- Lint passes
- Typecheck passes
- No obvious issues
- Verdict: PASS if clean.
L2 — Full Review (9 categories)
Every category must be addressed explicitly — PASS or FINDINGS with file:line evidence. No category may be silently skipped. Run matcha_review_validate on the final verdict (rejects missing tier/scope/evidence/counts).
🔴 Must Fix
- Correctness — Logic changed intentionally? Edge cases? Off-by-one? Race conditions? Dead code?
- Performance — O(n²+)? N+1 queries? Unbatched I/O? Unbounded operations? Memory leaks?
- Security — Trust boundaries? AuthN/AuthZ + IDOR? Output encoding? Secrets in code/logs/responses? Fail-closed?
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.
- 5d ago First seen · 151 lines · 20 tokens per session scan A ad7830582826
matcha:review is a command published in the GitHub repository plumpslabs/matcha (1 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,453 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
selfreview
Self code review before a release — four narrow reviewers over the change (or the whole repo), findings ranked, nothing edited.
release
Prepare the next release per RELEASING.md — gate, price table, surface audit, changelog — and stop at the tag command.
refresh
Atualiza incrementalmente .first-plan/ baseado nos arquivos marcados como stale pelo hook PostToolUse. Mais barato que /fp:init - só recompila o que mudou.
check
Verifica se uma feature específica já existe (em parte ou inteira) no projeto. Antes de planejar, use isto para evitar reimplementação.
cochange
Mostra arquivos que tendem a mudar junto com o path especificado, baseado em git history. Use antes de planejar mudanças para evitar PRs incompletos.
provenance
Mostra a cadeia completa de proveniência de um finding - source, commit SHA, age, confidence atual com decay, lifecycle status. Útil para auditar de onde veio uma afirmação na camada compilada.