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.
git 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-off)<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-off"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-off/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-off"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-off.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.00345 |
| Opus 5.5 | $0.00005 | $0.00138 |
| Sonnet 5.5 | $0.00002 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
matcha:off 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 1mo 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:off
Completely disable all matcha governance. Zero token overhead, zero friction. Agent behaves as if matcha is not installed.
When to use:
- Rapid prototyping / throwaway experiments
- Debugging a tricky issue where gate friction slows you down
- Pair coding sessions where you want raw agent speed
- Exploring an unfamiliar codebase before planning
What silences (truly zero overhead):
- Planning Gate → disabled, no plan required before edits
- Safety Shield → disabled, no command filtering
- Post-Write Scan → disabled, no DRY/debt checks after writes
- Stop Tips → disabled, no session summary
- Rule Injection → disabled, no matcha context in system prompt
💡 This is real OFF — not "observe mode". The hooks return immediately with no processing, no token cost, no LLM context injection.
Instructions for agent
- Write to
.agents/matcha-state.json:{ "enabled": false, "intensity": "off" } - Confirm to user:
🍵 matcha: governance OFF ───────────────────────────── State: ⏸ Disabled Overhead: zero — no hooks, no scans, no injections All guardrails silent. Agent runs unrestricted. To re-enable: /matcha:on or /matcha:toggle
Terminal shortcut
matcha off
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.
- 1mo ago First seen · 47 lines · 12 tokens per session scan A 2fe8f85e5038
matcha:off is a command published in the GitHub repository plumpslabs/matcha (2 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 345 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-11.
Other commands, from other repositories
refresh
Atualiza incrementalmente .first-plan/ baseado nos arquivos marcados como stale pelo hook PostToolUse. Mais barato que /fp:init - só recompila o que mudou.
resume
Resume an interrupted HOTL workflow run.
ponytail-help
Quick reference for ponytail levels, skills, and commands.
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.