M3E: Skill for Claude Code

.claude/skills/map-update/SKILL.md

map-update is a skill for Claude Code from akaghef/M3E. It costs 93 tokens per session (811 once invoked), scanned A, original, MIT.

A procedure for updating development progress and agent status on an M3E strategy board. The board is a structured map of tasks and relationships, accessed through the project’s local API.

In plain words
What is it for?
Use it after completing work or when asked to update task status, agent status, strategy, or development notes on the M3E map.
Why use it?
It reduces the risk of writing progress to the wrong map or path and requires reading the current state before making a small update.

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/map-update/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 map-update

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/akaghef/m3e/map-update"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/map-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 811 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 $0.00093 $0.00811
Opus 5.5 $0.00037 $0.00324
Sonnet 5.5 $0.00019 $0.00162
Haiku 4.5 $0.00009 $0.00081

Measured 5d ago against content hash bebae9507e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

map-update 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/map-update/SKILL.md · 86 lines

What it actually says

map-update — Strategy Board & Agent Status 一括更新

M3E マップの開発進捗を反映する Manager 用スキル。 構造判断は Map Manager、実行経路は m3e-map skill / /api/maps に寄せる。

Target

M:(開発)> SYSTEM > DEV

主な更新先:

  • M:(開発)> SYSTEM > DEV >> strategy
  • M:(開発)> SYSTEM > DEV >> Agent Status
  • M:(開発)> SYSTEM > DEV >> scratch

/ は legacy/API compatibility only。user-facing path は M:(map label)> A > B >> C を使う。

API

  • Base URL: http://localhost:4173(beta 開発サーバー)
  • Map discovery: GET /api/maps で label="開発" の mapId を取得
  • Read map: GET /api/maps/{mapId}
  • Save map: POST /api/maps/{mapId}

final は 38482。通常の開発 state 更新には使わない。

Map Manager gates

次を含む場合は、更新前に docs/protocols/map-manager/ を確認する。

  • scope / scopen / unscopen
  • alias vs move vs GraphLink
  • cross-facet relation
  • layouting / display intent
  • MF / WMF / Mermaid / Markdown からの writeback
  • target path ambiguity

実行フロー

  1. GET /api/maps で 開発 map を discovery。
  2. 対象 path / scope を canonical display path で解決。
  3. 更新が trivial status update か、Map Manager gate 対象かを分類。
  4. GET /api/maps/{mapId} で read。
  5. in-memory で最小変更。
  6. tree invariant / relation endpoint / display intent を確認。
  7. POST /api/maps/{mapId} で save。
  8. re-read して更新箇所を報告。

進捗の表現ルール

状態 マップ上の表現
完了 ノード削除ではなく、まず status: done と完了メモを付ける。削除は明示指示時のみ
未着手 status: ready
途中 status: doing と進捗メモ
ブロック status: blocked と blocker メモ

Agent Status は以下の形式に統一する。

[{role}: {status} ; {current task}]-[next: {next task}]

Report

マップ更新完了:
- target: M:(開発)> SYSTEM > DEV >> ...
- changed: ...
- verified: ...
- unresolved: ...

注意

  • worker は direct API / SQLite / runtime file write をしない。必要なら Map Manager handoff を返す。
  • Manager がこの skill で更新する場合も、曖昧な構造判断は Map Manager gate を通す。
  • サーバー停止時は、マップ更新を未実行として明記する。
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 · 86 lines · 93 tokens per session scan A bebae9507e50

Subscribe to this mod's changes

map-update is a skill published in the GitHub repository akaghef/M3E (11 stars, last pushed 5d ago), licensed MIT. It adds 93 tokens to every session and 811 once invoked, about $0.0004 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.