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 instructions/plumpslabs/matcha/copilot-instructionsgit clone --depth 1 https://github.com/plumpslabs/matchaWhat 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 | $0.00303 | $0.00303 |
| Opus 5 | $0.00151 | $0.00151 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
matcha copilot-instructions.md 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.
What it actually says
🍵 matcha — Engineering Convention
This project uses the matcha engineering convention. Read the AGENTS.md file at the project root and follow its philosophy:
Simple. Efficient. Deliberate. Never twice.
Key principles (see AGENTS.md for the full ruleset):
- ⚖️ Proportionality (effort ↔ risk) — match ceremony to task size. Trivial (≤5 LOC, 1 file, no logic): minimal plan, fast pass. Small (1-3 files): short plan + light review. Large (cross-cutting/prod risk): full gate. Planning > implementation = over-planning. Exit conditions beat STOP — proceed on a recorded assumption rather than blocking on trivia.
- Purpose (Intent Discovery) — know why before how. Can't explain why/how? Stop and rethink — unless the task is trivial, then proceed on a recorded assumption.
- Reuse — search the codebase before writing new code. Never write what exists.
- Implementation — one function, one job. Explicit errors. No hardcoded values. Validate inputs at boundaries. Never log secrets/PII.
- Cleanup — done means working and clean. No debug leftovers, no dead code.
- Verify — run tests, typecheck, and lint before declaring done.
Respect the // matcha: decision markers when you find them in code — they are intentional, logged shortcuts.
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 · 16 lines · 303 tokens per session scan A fbf62797f33f
matcha copilot-instructions.md is an instructions file published in the GitHub repository plumpslabs/matcha (1 stars, last pushed 22d ago), licensed MIT. It adds 303 tokens to every session, about $0.0015 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 instructions, from other repositories
assaio AGENTS.md
Instructions for assaio/assaio, covering agents.md — assaio, what this is, code philosophy (non-negotiable), code standards (enforced + human-reviewed) and honesty rules (product-critical).
assaio CLAUDE.md
Instructions for assaio/assaio, a project described as: Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugins in any language, and…
agent-toolkit AGENTS.md
Instructions for Arnosdeus/agent-toolkit, covering shared agent instructions, repository inspection, existing architecture, frontend and ui quality and testing.
kluris CLAUDE.md
Instructions for ngvoicu/kluris, covering claude.md, what this is, knowledge base, build & test and architecture.
skillr CLAUDE.md
Instructions for eooo-io/skillr, covering claude.md, project direction, repo layout, tech stack (cli) and dev workflow.
syncai copilot-instructions.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.