M3E: Skill for Claude Code

.claude/skills/m3e-scratch/SKILL.md

m3e-scratch is a skill for Claude Code from akaghef/M3E. It costs 247 tokens per session (1,668 once invoked), scanned A, original, MIT.

A scratchpad workflow for adding ideas, bug reports, notes, and future tasks to a project's map. It can also group and organize items already in that scratch area.

In plain words
What is it for?
It is for recording ideas, bugs, memos, and TODO-style tasks, including several items supplied as a list, and sorting them into categories.
Why use it?
It keeps raw thoughts and reported problems from being lost or mixed into finished work. The items remain temporary until they are organized, promoted, or removed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is akaghef/M3E's own configuration. It tells Claude Code how to work on M3E itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything M3E configures →

View source ↗ akaghef/M3E
Reuse

Borrowing it

Nothing to install: this file belongs to akaghef/M3E. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/akaghef/M3E/main/.claude/skills/m3e-scratch/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/akaghef/M3E

Made for: Claude Code.

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.

agentmods badge for m3e-scratch

README.md
[![agentmods](https://agentmods.dev/badge/skills/akaghef/m3e/m3e-scratch/github.svg)](https://agentmods.dev/skills/akaghef/m3e/m3e-scratch)
Your own site
<a href="https://agentmods.dev/skills/akaghef/m3e/m3e-scratch"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/m3e-scratch/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.

agentmods 80×15 button for m3e-scratch

Your own site · 80×15
<a href="https://agentmods.dev/skills/akaghef/m3e/m3e-scratch"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/m3e-scratch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 247 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00247 $0.01668
Opus 5.5 $0.00099 $0.00667
Sonnet 5.5 $0.00049 $0.00334
Haiku 4.5 $0.00025 $0.00167

Measured 5d ago against content hash ee03ba3f3c5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

m3e-scratch 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.

.claude/skills/m3e-scratch/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

m3e-scratch

ユーザーの思いつき、アイデア、バグ報告をM3Eマップの scratch ノード配下にプールするスキル。 scratch はタスクの種(seed)置き場 — 後で整理・昇格・削除する前提の気軽な場所。

場所

M:(開発)> SYSTEM > DEV >> scratch

scratch ノードID: n_new_scratch_1775637602039


機能1: ノード追加

1. ユーザー入力を解析

ユーザーの発言から以下を抽出する:

  • テキスト: ノードの本文(簡潔に。ユーザーの言葉をなるべくそのまま使う)
  • 種別: idea / bug / memo / task のいずれか(文脈から判断)
  • 詳細: 補足があれば details フィールドに入れる
  • 複数項目: 箇条書きや列挙なら、それぞれ別ノードとして追加

2. マップに書き込む

マップAPIを使う:

  1. GET http://localhost:4173/api/maps で label="開発" の mapId を discovery し、対象 map を取得
  2. 新しいノードを作成:
    {
      "id": "n_{timestamp}_{random6}",
      "parentId": "n_new_scratch_1775637602039",
      "children": [],
      "nodeType": "text",
      "text": "ユーザーの入力テキスト",
      "collapsed": false,
      "details": "補足情報があれば",
      "note": "",
      "attributes": {
        "kind": "idea|bug|memo|task"
      },
      "link": ""
    }
    
    • カテゴリフォルダが既にあり、そこに入るべき内容なら parentId をそのフォルダにする
  3. 親ノードの children 配列の末尾に新ノードIDを追加
  4. POST で全体を書き戻す
  5. レスポンスの "ok": true を確認

3. ID生成

n_{Date.now()}_{Math.random().toString(36).slice(2, 8)}

Bashで生成する場合:

echo "n_$(date +%s%3N)_$(cat /dev/urandom | tr -dc 'a-z0-9' | head -c 6)"

4. ユーザーへの応答

追加したら簡潔に報告:

scratch に追加:
- [idea] レイアウトエンジンにgrid表示モード
- [bug] ノード削除後にalias参照が残る

機能2: scratch 整理

scratch 配下のノードが増えてきたら、カテゴリごとにグルーピングして見通しを良くする。

整理ルール

  1. 葉ノードは絶対に削除しない — 葉はユーザーのアイデアそのもの。消すのはユーザーだけ
  2. 整理はフォルダノード(中間ノード)の追加・移動のみで行う
  3. カテゴリフォルダの例:
    • UI/UX — 見た目・操作感に関するもの
    • データモデル — ノード構造・属性・型に関するもの
    • バグ — 不具合報告
    • インフラ — ビルド・デプロイ・CI/CD
    • アイデア — 大きな構想・将来のビジョン
    • カテゴリは固定ではない。内容に応じて柔軟に作る
  4. 1〜2個しかないカテゴリは無理にフォルダを作らない(scratch直下のままでOK)
  5. 既存のフォルダ構造があればそれを尊重し、追加・調整する

整理の手順

  1. GET でマップ取得
  2. scratch 配下の全ノードを走査し、内容を把握
  3. カテゴリ分けの計画を立てる
  4. 必要なフォルダノードを作成(nodeType: "text", attributes: { "role": "category" })
  5. 葉ノードの parentId を適切なフォルダに変更
  6. 旧親の children から削除、新親の children に追加
  7. POST で書き戻す
  8. ユーザーに整理結果を報告:
    scratch を整理しました:
    - UI/UX (3件): grid表示, ダークモード, ツールチップ改善
    - バグ (2件): alias参照残り, 折りたたみ状態リセット
    - 未分類 (1件): ライセンス検討
    

Read the full file on GitHub · 136 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.

  1. 5d ago First seen · 136 lines · 247 tokens per session scan A ee03ba3f3c5d

Subscribe to this mod's changes

m3e-scratch is a skill published in the GitHub repository akaghef/M3E (11 stars, last pushed 5d ago), licensed MIT. It adds 247 tokens to every session and 1,668 once invoked, about $0.0010 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 2026-10-02.