release

release is a skill for Claude Code from nakashima-takeo/wezterm-ai-agents. It costs 35 tokens per session (1,236 once invoked), scanned A, original, MIT.

A release procedure for merging a development branch into the main branch, creating a version tag, and publishing a release.

In plain words
What is it for?
Use it to release a specified version, inspect changes, update the version constant, wait for CI, merge the pull request, push the tag, and prepare release notes.
Why use it?
It groups the checks needed before release, including version updates, pull-request checks, merging, tagging, and release notes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it to release a specified version, inspect changes, update the version constant, wait for CI, merge the pull request, push the tag, and prepare release notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nakashima-takeo/wezterm-ai-agents/release
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 nakashima-takeo/wezterm-ai-agents --skill release
Clone the repo
git clone --depth 1 https://github.com/nakashima-takeo/wezterm-ai-agents

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/skills/nakashima-takeo/wezterm-ai-agents/release/github.svg)](https://agentmods.dev/skills/nakashima-takeo/wezterm-ai-agents/release)
Your own site
<a href="https://agentmods.dev/skills/nakashima-takeo/wezterm-ai-agents/release"><img src="https://agentmods.dev/badge/skills/nakashima-takeo/wezterm-ai-agents/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/skills/nakashima-takeo/wezterm-ai-agents/release"><img src="https://agentmods.dev/badge/skills/nakashima-takeo/wezterm-ai-agents/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,236 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 $0.00035 $0.01236
Opus 5 $0.00017 $0.00618
Sonnet 5 $0.00007 $0.00247
Haiku 4.5 $0.00003 $0.00124

Measured 12d ago against content hash d0dd915eddf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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/release/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dev ブランチから main へのマージ・タグ・リリースを実行する。引数にバージョン番号(v0.2.0 形式)を取る。v プレフィックスがなければ付与する。

手順

1. 差分確認

git fetch origin
git log origin/main..origin/dev --oneline
git tag --sort=-v:refname | head -1

差分が 0 件なら「リリースする変更がありません」と報告して終了。

差分がある場合、コミット一覧と現在の最新タグをユーザーに提示する。引数でバージョンが指定されていなければ AskUserQuestion でバージョン番号を聞く。

2. バージョン定数の更新

plugin/init.luaM.version をリリースバージョン(v プレフィックスなし)に更新する。現在の値と一致していればスキップ。

# 現在の値を確認
grep 'version = ' plugin/init.lua
# 更新が必要なら Edit ツールで書き換え、コミット
git add plugin/init.lua
git commit -m "chore: bump version to $VERSION"

3. dev を push

ローカル dev に未 push のコミットがあれば git push origin dev する。

4. PR 作成

dev → main の PR が既にあれば、そのまま使う(新規作成しない)。

gh pr create --base main --head dev --title "Release $VERSION" --body ""

5. CI 待ち

gh pr checks <PR番号> --watch

1つでも fail があれば「CI が失敗しました」と PR URL を報告して終了。

6. マージ

gh pr merge <PR番号> --merge --delete-branch=false

7. タグ・push

git fetch origin main
git tag $VERSION origin/main
git push origin $VERSION

8. リリースノート作成(公開前の最終ゲート)

過去のリリースノートとコミットログを取得する。

gh release list --limit 3
gh release view <直近リリース>
git log <前回タグ>..origin/main --oneline --no-merges

8-1. 載せる変化の選別

コミットは素材であって項目ではない。前バージョンを使っていた利用者が受け取る正味の変化だけを書く。各論理変更を次のどちらかに分類して列挙する。

  • (a) 利用者が前バージョンから受け取る変化 — 載せる
  • (b) 本リリース内で完結した中間修正・内部都合の変更 — 載せない(利用者が一度も触れていない不具合の修正、リファクタ、CI/テスト、依存更新など)

判定の問い:「この変化は、前リリースを使っていた利用者にとって新しい体験か?」。(a) だけをノートにする。

8-2. 草案作成

過去のリリースノートのフォーマット・粒度・文体を踏襲し、(a) の変化を利用者が理解できる表現で Markdown にする。

8-3. 承認

草案を AskUserQuestion で提示し、承認を問う。ここを越えると step 9 で取り消せない公開が走る。

flowchart TD
    D[草案を提示し承認を問う] -->|修正・指摘・疑問が返る| R[草案を直す]
    R --> D
    D -->|「この版でOK」の明示的な肯定| N[step 9 へ]

承認の判定: ユーザーから修正・指摘・疑問が一つでも返ったら、それは承認ではない。前の草案の承認は無効になる。直した版を改めて提示して再び承認を問う。対応完了・沈黙・問い返しを承認とみなして step 9 に進んではならない。「この版でOK」に相当する明示的な肯定だけが公開を許す。

9. GitHub Release 作成

gh release create $VERSION --title "$VERSION" --notes "$RELEASE_NOTES"

Read the full file on GitHub · 124 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. 12d ago First seen · 124 lines · 35 tokens per session scan A d0dd915eddf5

Subscribe to this mod's changes

release is a skill published in the GitHub repository nakashima-takeo/wezterm-ai-agents (5 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,236 once invoked, about $0.0002 per session on Opus 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 2026-08-31.