llmlb: Command for Claude Code

.claude/commands/release.md

release is a command for Claude Code from akiojin/llmlb. It costs 42 tokens per session (2,006 once invoked), scanned A, original, MIT.

A release workflow command for a Rust project. It updates the version and change log, creates a release commit, merges the release branch, and triggers GitHub release and binary publishing workflows.

In plain words
What is it for?
Use it to prepare and publish a versioned software release, including tags, GitHub release notes, and built binaries.
Why use it?
It organizes the many Git steps involved in publishing a new version and checks for uncommitted work first. It also includes local formatting, linting, and test checks before pushing.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is akiojin/llmlb's own configuration. It tells Claude Code how to work on llmlb 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 llmlb configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akiojin/llmlb. 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/akiojin/llmlb/develop/.claude/commands/release.md
Clone the repo
git clone --depth 1 https://github.com/akiojin/llmlb

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 release

README.md
[![agentmods](https://agentmods.dev/badge/commands/akiojin/llmlb/release/github.svg)](https://agentmods.dev/commands/akiojin/llmlb/release)
Your own site
<a href="https://agentmods.dev/commands/akiojin/llmlb/release"><img src="https://agentmods.dev/badge/commands/akiojin/llmlb/release/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 release

Your own site · 80×15
<a href="https://agentmods.dev/commands/akiojin/llmlb/release"><img src="https://agentmods.dev/badge/commands/akiojin/llmlb/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,006 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 $0.00042 $0.02006
Opus 5.5 $0.00017 $0.00802
Sonnet 5.5 $0.00008 $0.00401
Haiku 4.5 $0.00004 $0.00201

Measured 8d ago against content hash b91a9ff8e729, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release 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 8d 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/commands/release.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

リリースコマンド(LLM主導・gwt スタイル)

LLM(Claude)がバージョン更新とリリースコミットを作成し、ワークフローがタグとリリースを作成します。

フロー

/release 実行
    ↓
① origin/develop を pull してローカルを最新化
    ↓
② LLMがバージョン更新(Cargo.toml, CHANGELOG.md)
    ↓
③ chore(release): vX.Y.Z コミット作成
    ↓
④ Closing Issue を収集(PR本文から Closes/Fixes/Resolves #N を抽出)
    ↓
⑤ develop → main マージ (PR本文に Closing Issues セクションを記載)
    ↓
⑥ release.yml がタグ作成 → GitHub Release作成
    ↓
⑦ publish.yml がバイナリビルド → Release にアタッチ

手順

0. ローカルを最新化(必須)

origin/develop の最新を取得し、ローカル develop を更新する:

git fetch origin
git pull origin develop

未コミットの変更がある場合はリリースを中断し、先に解決すること。

1. バージョン更新

Cargo.toml のバージョンを更新:

[workspace.package]
version = "X.Y.Z"  # 新しいバージョン

2. CHANGELOG.md 更新

## [X.Y.Z] - YYYY-MM-DD

### Added
- 新機能の説明

### Fixed
- バグ修正の説明

3. リリースコミット作成

git add Cargo.toml Cargo.lock CHANGELOG.md
git commit -m "chore(release): vX.Y.Z"

⚠️ git push 実行前に確認:

  • pre-commit hook が cargo fmt, cargo clippy, cargo test (2799テスト, ~8-10分) を実行
  • タイムアウトのリスク: デフォルト 60秒では不十分
  • 推奨: timeout 600秒(10分)で実行
# 推奨: タイムアウト付きで実行
timeout 600 git push origin develop

# または標準実行(デフォルトタイムアウトなし)
git push origin develop

⚠️ Push 失敗時の対応:

If push fails or times out:

  1. Timeout 確認:

    git log origin/develop -1 --oneline
    git log HEAD -1 --oneline
    
    • origin/develop と HEAD が異なる → push 未完了
  2. 再試行:

    timeout 600 git push origin develop
    
  3. 検証:

    # Push 成功確認
    git rev-parse origin/develop HEAD
    

    両者が一致すれば push 成功。ここで step 4 へ進む。

  4. 失敗時は LLM に報告:

    • Pre-commit hook の詳細ログを確認
    • 具体的なエラーメッセージを提示して修正

4. Closing Issue の収集

リリースPRに Closes #N を記載することで、main マージ時にIssueが自動クローズされる。

  1. 前回リリースタグ〜HEADのコミットからPR番号を抽出:

    LAST_TAG=$(git describe --tags --abbrev=0)
    # スカッシュマージ: (#{number}) を抽出
    # マージコミット: Merge pull request #{number} を抽出
    PR_NUMBERS=$(git log ${LAST_TAG}..HEAD --oneline \
      | grep -oE '(#[0-9]+)|\bMerge pull request #[0-9]+' \
      | grep -oE '[0-9]+' | sort -u)
    

Read the full file on GitHub · 235 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. 8d ago First seen · 235 lines · 42 tokens per session scan A b91a9ff8e729

Subscribe to this mod's changes

release is a command published in the GitHub repository akiojin/llmlb (10 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 2,006 once invoked, about $0.0002 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 2026-10-21.