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-whygit 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-why)<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-why"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-why.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 | $0.00020 | $0.00692 |
| Opus 5 | $0.00010 | $0.00346 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
matcha:why 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/matcha:why
Intent Discovery. Before planning or touching code, discover the intent: what problem is being solved, what success looks like, and the What → Why → How with evidence. Can't answer Why or How? → STOP unless trivial (≤5 LOC, 1 file, no logic change) — for trivia, proceed on a stated assumption and flag it. Never stop the user for a typo.
Process
| Field | What to answer | Minimum evidence |
|---|---|---|
| Problem | Exact problem or request being addressed | Specific error, user request, or requirement |
| Goals | What success looks like | Desired outcome, acceptance behavior |
| Success Criteria | How we know it's done | Measurable, testable condition |
| What | Scope of the change | Specific files/areas affected |
| Why | What breaks without this | Impact, user pain, business cost |
| How | Simplest full solution | Step-by-step, file-by-file plan |
| Assumptions | What we take as given | Constraints, existing patterns |
| Unknowns | What still needs discovery | Open questions → resolve in context/reuse stages |
What/Why/How is one technique inside Intent Discovery — the container also captures problem, goals, success criteria, assumptions, and unknowns.
Decision Matrix
| Confidence | Action |
|---|---|
| HIGH on Problem/Why/How | ✅ Proceed to planning |
| MEDIUM on Why or How | ⚠️ Ask user to clarify (skip for trivial tasks — proceed on assumption) |
| LOW on any | 🛑 STOP for nontrivial. For trivial (≤5 LOC, 1 file): proceed on a recorded assumption and flag it. Don't block a typo on missing "Why evidence". |
Report Format
🍵 matcha: Intent Discovery
Task: [what was requested]
Problem: [exact problem]
Goals: [desired outcome]
Success: [measurable done condition]
What: [scope — be specific]
Why: [impact without this — with evidence]
How: [simplest solution — numbered steps]
Assumptions: [what's taken as given]
Unknowns: [what needs discovery]
Confidence: HIGH / MEDIUM / LOW
[If MEDIUM/LOW: what's unclear → ask user]
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 · 63 lines · 20 tokens per session scan A 6ce595c232f0
matcha:why is a command published in the GitHub repository plumpslabs/matcha (1 stars, last pushed 23d ago), licensed MIT. It adds 20 tokens to every session and 692 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.
execute
Executa o plano aprovado em .first-plan/07-state/plans/. Segue o plano à risca, para se algo invalidar premissa, gera relatório ao final.
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.
lsp-status
Mostra quais Language Servers (LSP) estao instalados, quais o projeto atual precisa, e comandos de instalacao para os faltantes.