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-statusgit 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-status)<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-status"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-status.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 | $0.00019 | $0.00369 |
| Opus 5 | $0.00010 | $0.00185 |
| Sonnet 5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
matcha:status 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 3d 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
/matcha:status
Master session health dashboard.
When to use: mid-session health check or before declaring done — intensity, git diff, tests, markers, and plan status in one view.
Instructions for agent
Report:
- Intensity level — current (observe/enforce/audit), defaults to enforce
- Git Diff Stats — files changed, lines +/- (
git diff --stat) - Test Status — fresh test runner execution summary
- Markers & Debt — count of
// matcha:markers found in session - Plan Status — read
.agents/plan/current.md— steps done K/N (via[x]),**▶ Current**step, and is the live plan in sync with current work? - Metrics (if
.agents/matcha-metrics.jsonexists) — planning-gate blocks, shield blocks, reviews run, issues caught, FP rate. Read the JSON directly and report the numbers — this is how matcha proves its own overhead. Zero blocks this session is fine; report what exists. - Health Verdict — overall session health (Healthy / Needs Attention / Critical)
🍵 matcha: status
Intensity: [observe|enforce|audit]
Changes: N files (+X / -Y lines)
Tests: N passed / N failed
Markers: N total (HIGH: N, MEDIUM: N)
Plan: [satisfied/missing] · Steps: K/N done (▶ Step N/M)
Health: ✅ Healthy | ⚠️ Needs Attention | 🔴 Critical
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.
- 3d ago First seen · 33 lines · 19 tokens per session scan A 158d647e8af5
matcha:status is a command published in the GitHub repository plumpslabs/matcha (1 stars, last pushed 24d ago), licensed MIT. It adds 19 tokens to every session and 369 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
release
Prepare the next release per RELEASING.md — gate, price table, surface audit, changelog — and stop at the tag command.
init
Compila contexto completo do projeto-alvo gerando .first-plan/. Roda Discovery (stacks, conventions, reuse, domain, risks), Spec-Code Reconciliation e Git Intelligence. Idempotente - pode rodar múltiplas vezes.
plan
Gera plano detalhado para uma feature usando a camada compilada. Verifica duplicidade, identifica reuse, mapeia arquivos a criar/modificar, lista riscos. Pausa pedindo aprovação ao final - não executa nada.
commit
Auto-stage, review, and commit all changes with a conventional commit message.
ship
Commit all changes and push to remote in one operation (combines /commit and /push).
check
Verifica se uma feature específica já existe (em parte ou inteira) no projeto. Antes de planejar, use isto para evitar reimplementação.