Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/instructions/iroha924/mumei/agents-md)<a href="https://agentmods.dev/instructions/iroha924/mumei/agents-md"><img src="https://agentmods.dev/badge/instructions/iroha924/mumei/agents-md.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 | $0.04858 | $0.04858 |
| Opus 5 | $0.02429 | $0.02429 |
| Sonnet 5 | $0.00972 | $0.00972 |
| Haiku 4.5 | $0.00486 | $0.00486 |
Grade A, and why
mumei AGENTS.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 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent reviewer guidance
This file follows the AGENTS.md open standard and is read automatically by AI coding / review agents that respect it (OpenAI Codex, Anthropic Claude, Gemini CLI, Cursor, Aider, and others). It supplies project-specific context so the reviewer flags the right things and stays away from the wrong things.
The canonical convention sources are .claude/rules/*.md (auto-loaded
by Claude Code) and CLAUDE.md; CONTRIBUTING.md carries the same
conventions for human contributors. This file is the thin mirror for
agents that read the AGENTS.md standard instead — it keeps the
load-bearing summary inline and links to the canonical files for depth.
What mumei is
mumei is a Claude Code plugin: a quality enforcement layer that
enforces SDD phases, Wave-by-Wave commits, and review pipelines via
hook-level gates rather than prompt-level instructions. It ships as
a git archive tarball; runtime is bash + jq so the install
footprint is zero (no Python venv, no Node runtime).
Repository layout:
- Plugin payload (shipped to users):
.claude-plugin/,agents/,skills/,hooks/(handlers and_lib/),scripts/(lint + aggregate),tests/(bats), top-levelREADME*.md/LICENSE/CONTRIBUTING.md/SECURITY.md/PRIVACY.md/CODE_OF_CONDUCT.md/AGENTS.md. - Shared dev-time only (NOT shipped):
schemas/*.jsonare hand-authored canonical contracts for the on-disk JSON the bash hooks write. Excluded from the plugin tarball (schemas/ export-ignorein.gitattributes); the hooks reference them by comment, never at runtime. - Dev-side, tracked (NOT shipped):
CLAUDE.md(project instructions, English),.claude/rules|skills|agents/(English),docs/dev records (harness-engineering.md,loop-engineering.md— pre-existing Japanese content, new entries in English). Design rationale goes in the PR description that lands the change; there is no separate decision log. - Gitignored (per-developer runtime state):
.claude/settings.local.json,.claude/agent-memory*/,.claude/worktrees/,.claude/tdd-guard/,CLAUDE.local.md.
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 · 392 lines · 4,858 tokens per session scan A ff6db8331bd7
mumei AGENTS.md is an instructions file published in the GitHub repository iroha924/mumei (2 stars, last pushed 6d ago), licensed MIT. It adds 4,858 tokens to every session, about $0.0243 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
aif-handoff CLAUDE.md
Instructions for lee-to/aif-handoff, covering claude.md, project overview, tech stack, project structure and key entry points.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
harness-evolver CLAUDE.md
Instructions for raphaelchristi/harness-evolver, covering claude.md, what this is, dependencies, running tools locally and use --no-canary to skip preflight check.
octowiz AGENTS.md
Instructions for raelli/octowiz, covering agent skills, issue tracker, triage labels, domain docs and path validation (dual-validator pattern).
Slime AGENTS.md
AGENTS.md instructions for bitqs/Slime, covering agents.md — read this first, then you can ship, what slime is, the prime directive (never violate), the other hard rules and where things live.
breakwatch AGENTS.md
AGENTS.md instructions for Kepei-Lei102/breakwatch, covering agent manual — installing and calibrating breakwatch, procedure, hard rules and if they want to build something else like this.