A one-time project setup tool for mumei, a workflow that uses written specifications, review stages, and coordinated commits. It checks existing project instruction files and prepares mumei's folders and rules.

Use it when first setting up or installing mumei in a project. It can inspect project guidance, propose additions, and create the required .mumei directory structure after approval.

It prevents mumei's expectations from conflicting with instructions already present in the project. It also gives the project a defined place for specifications, drafts, archives, and session state.

kindle — Skill for Claude Code by iroha924

Install

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.

Any agent

npx skills add iroha924/mumei --skill kindle

Clone the repo

git clone --depth 1 https://github.com/iroha924/mumei

Made for: Claude Code.

Or install mumei, the plugin that ships this one along with the rest of its 11 skills, 10 agents, 18 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iroha924/mumei/kindle/github.svg)](https://agentmods.dev/skills/iroha924/mumei/kindle)

Your own site

<a href="https://agentmods.dev/skills/iroha924/mumei/kindle"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/kindle/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iroha924/mumei/kindle"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/kindle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,101 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00083	$0.02101
Opus 5	$0.00042	$0.01051
Sonnet 5	$0.00017	$0.00420
Haiku 4.5	$0.00008	$0.00210

Measured 10d ago against content hash 3fdd46c0e1d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

kindle scanned grade D with 2 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 10d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Role: One-time setup that installs mumei into a project Input: user instruction Output: create .mumei/ directory + propose additions to CLAUDE.md / .claude/rules/ Principle: Never modify existing files without user

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

test -f .gitignore && grep -qxF ".claude/agent-memory-local/" .gitignore

skills/kindle/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kindle

Set up mumei for the current project. This skill is run once per project. It:

Creates the .mumei/ directory structure.
Detects existing CLAUDE.md / .claude/rules/*.md.
Proposes additions about mumei's expectations and applies them with explicit user approval.

When to use

The user explicitly says "set up mumei", "install mumei in this project", or invokes /mumei:kindle.
The first time /mumei:compose is invoked in a project where .mumei/ does not exist (route to this skill first).

Method

Step 1 — Detect existing project memory

Read all of:

CLAUDE.md (project root)
.claude/CLAUDE.md
~/.claude/CLAUDE.md (user-level, read-only)
.claude/rules/*.md
AGENTS.md (if present)

Summarize what is currently in place. Do NOT modify anything yet.

Step 2 — Create `.mumei/` directory and its `.gitignore`

mkdir -p .mumei/specs .mumei/archive .mumei/scratch
[[ -f .mumei/current ]] || : > .mumei/current  # empty until first feature

Generate .mumei/.gitignore so team-shared spec content (requirements / design / tasks / spec-reviews / reviews / scratch / archive) is tracked, while per-developer state (current cursor, state.json progress) is ignored. Do not overwrite an existing .mumei/.gitignore — the user may have customized it.

if [[ ! -f .mumei/.gitignore ]]; then
  cat > .mumei/.gitignore <<'EOF'
# mumei: per-developer state only. Everything else (config.json,
# specs/*/{requirements,design,tasks}.md, spec-reviews/, reviews/, scratch/,
# archive/) is tracked for team handoff — config.json carries golden_paths, so
# it MUST be committed for G1/G2 to behave the same across teammates / CI.
current
specs/*/state.json
EOF
fi

Read the full file on GitHub · 200 lines

Changes

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.

10d ago First seen · 200 lines · 83 tokens per session scan D 3fdd46c0e1d6

Subscribe to this mod's changes

kindle is a skill published in the GitHub repository iroha924/mumei (2 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 2,101 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Planning claude-code-plugin harness harness-engineering hooks quality-enforcement

kindle

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade D, and why

Hidden instructionshighPrompt injection

Reads agent configuration directoriesmediumAgent snooping

How it starts

Kindle

When to use

Method

Step 1 — Detect existing project memory

Step 2 — Create `.mumei/` directory and its `.gitignore`

What this file has done since we first saw it

Other skills, from other repositories

harness

evaluator-write-qa-parallel

evaluator-write-qa

evaluator-review-contract-parallel

evaluator-write-final-parallel

evaluator-write-retest-parallel

kindle

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade D, and why

Hidden instructionshighPrompt injection

Reads agent configuration directoriesmediumAgent snooping

How it starts

Kindle

When to use

Method

Step 1 — Detect existing project memory

Step 2 — Create .mumei/ directory and its .gitignore

What this file has done since we first saw it

Other skills, from other repositories

harness

evaluator-write-qa-parallel

evaluator-write-qa

evaluator-review-contract-parallel

evaluator-write-final-parallel

evaluator-write-retest-parallel

Step 2 — Create `.mumei/` directory and its `.gitignore`