M3E: Skill for Claude Code

.claude/skills/launch-beta/SKILL.md

launch-beta is a skill for Claude Code from akaghef/M3E. It costs 132 tokens per session (754 once invoked), scanned A, original, MIT.

A command for starting a beta server from one of several Git worktrees. A worktree is a separate working directory connected to a Git repository; the server is opened at local viewer and home pages.

In plain words
What is it for?
Launching the beta build for the beta, data, or visual role, with the current worktree used when no role is given.
Why use it?
It selects the intended branch directory and checks that the worktree exists before running the launch script. It avoids manually finding the script or dealing with an occupied port.

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/launch-beta/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 launch-beta

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/akaghef/m3e/launch-beta"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/launch-beta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 754 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 $0.00132 $0.00754
Opus 5.5 $0.00053 $0.00302
Sonnet 5.5 $0.00026 $0.00151
Haiku 4.5 $0.00013 $0.00075

Measured 5d ago against content hash 6bd97af7c7e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

launch-beta 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/launch-beta/SKILL.md · 57 lines

What it actually says

launch-beta — 指定ワークツリーの beta 起動

ロール指定でワークツリーを選び、scripts/beta/launch.bat をバックグラウンド実行する。

Usage

/launch-beta {role}

ロール → ブランチ → ワークツリー対応:

role branch worktree path
beta dev-beta c:\Users\Akaghef\dev\M3E-dev-beta\
data (既定) dev-data c:\Users\Akaghef\dev\M3E\
visual dev-visual c:\Users\Akaghef\dev\M3E-dev-visual\

役割名を省略した場合は、現在の CWD のワークツリーで起動する。

実行手順

  1. git worktree list でロールに対応するワークツリーの存在を確認する。 存在しなければ、その旨をユーザーに報告して中断する (git worktree add はこのスキルでは行わない — 別途用意が必要)。

  2. ロール名から launch.bat の絶対パスを決定する:

    • beta → c:/Users/Akaghef/dev/M3E-dev-beta/scripts/beta/launch.bat
    • data → c:/Users/Akaghef/dev/M3E/scripts/beta/launch.bat
    • visual → c:/Users/Akaghef/dev/M3E-dev-visual/scripts/beta/launch.bat
  3. Bash ツールで run_in_background: true で実行:

    <launch.bat 絶対パス>
    
  4. ユーザーには http://localhost:4173/viewer.html および http://localhost:4173/home.html が 開けることを案内する(どちらのページが必要かはタスクによる)。

備考

  • launch.bat は %~dp0\..\.. で自身のワークツリーを解決するので、どこから呼んでも正しいパスで起動する。
  • port 4173 は launch.bat 内で自動解放される(既存プロセスがあれば kill)。
  • ビルド物がない場合は失敗する。その場合は先に npm --prefix beta run build が必要。
  • このスキルはサーバー起動「だけ」を行う。ビルド・テスト・ブラウザ起動は別スキルに任せる。
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 · 57 lines · 132 tokens per session scan A 6bd97af7c7e7

Subscribe to this mod's changes

launch-beta is a skill published in the GitHub repository akaghef/M3E (11 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 754 once invoked, about $0.0005 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.