release

release is a skill for Claude Code, Codex from ebibibi/ebi-agent-chat-relay. It costs 40 tokens per session (1,073 once invoked), scanned A, original, MIT.

A release checklist for the ccdb project, including version changes, changelog updates, a release branch, and a pull request. A changelog records what changed between software versions.

In plain words
What is it for?
Use it to prepare a named release, update its version and changelog, create the release branch, and open the required pull request.
Why use it?
It makes manual minor or major releases follow the project’s versioning and review process.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ebibibi/ebi-agent-chat-relay/release
Any agent
npx skills add ebibibi/ebi-agent-chat-relay --skill release
Clone the repo
git clone --depth 1 https://github.com/ebibibi/ebi-agent-chat-relay

Made for: Claude Code, Codex.

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/ebibibi/ebi-agent-chat-relay/release.svg)](https://agentmods.dev/skills/ebibibi/ebi-agent-chat-relay/release)
Your own site
<a href="https://agentmods.dev/skills/ebibibi/ebi-agent-chat-relay/release"><img src="https://agentmods.dev/badge/skills/ebibibi/ebi-agent-chat-relay/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,073 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.01073
Opus 5 $0.00020 $0.00536
Sonnet 5 $0.00008 $0.00215
Haiku 4.5 $0.00004 $0.00107

Measured 5d ago against content hash 8556a5febb13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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/release/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ccdb リリース手順

バージョン体系

v1.3.0  ← 手動マイナーリリース(このスキルの対象)
v1.3.1  ← PR マージごとに自動インクリメント(普段は何もしない)
v1.3.2  ← 同上
...
v1.4.0  ← 手動マイナーリリース(このスキルの対象)
  • 自動パッチバンプ: 普通の PR をマージするたびに .1 ずつ自動インクリメント。操作不要
  • 手動リリース: マイナー/メジャーの区切りを付けたいときに使う(このスキル)

手動リリース手順(「v1.4.0としてリリースして」)

Step 1: リポジトリに入る

cd /home/ebi/claude-code-discord-bridge
git checkout main && git pull

Step 2: ブランチを作る

git checkout -b release/v1.4.0   # バージョンは指定されたものに変える

Step 3: pyproject.toml のバージョンを更新

pyproject.tomlversion = "1.3.x" を指定バージョンに書き換える:

version = "1.4.0"

Step 4: CHANGELOG.md を更新

  1. ## [Unreleased] セクションを ## [1.4.0] - YYYY-MM-DD に変更(今日の日付)
  2. その上に新しい空の ## [Unreleased] セクションを追加
## [Unreleased]

## [1.4.0] - 2026-02-22   ← 今日の日付

### Added
...(既存の Unreleased 内容がここに来る)

Step 5: PR を作成(タイトルに 必ず [release] を含める)

PATH="/home/ebi/.local/bin:$PATH" git add pyproject.toml CHANGELOG.md
PATH="/home/ebi/.local/bin:$PATH" git commit -m "release: v1.4.0 [release]"
git push -u origin release/v1.4.0

gh pr create \
  --repo ebibibi/ebi-agent-chat-relay \
  --base main \
  --title "release: v1.4.0 [release]" \
  --body "Release v1.4.0

## Changes
See CHANGELOG.md for details."

⚠️ 重要: PR タイトルに [release] を含めること。これがないと自動パッチバンプが走って v1.4.1 になってしまう。

Step 6: 確認(数分後)

auto-approve により PR が自動マージされ、タグ v1.4.0 と GitHub Release が作成される:

gh release view v1.4.0 --repo ebibibi/ebi-agent-chat-relay

仕組み(裏側)

PR マージ(auto-approve.yml)
  └── repository_dispatch: pr-merged
        └── auto-version-bump.yml
              ├── [release] あり → 現在バージョンでタグ & Release(バンプなし)
              └── [release] なし → patch++ を main に直接コミット → タグ & Release
  • docs-sync PR(翻訳・ドキュメント更新)はバンプも Release も発生しない
  • patch-bump は main への直接コミット(enforce_admins=false で許可)
  • リリース時にはえびログ(Discord)に自動通知

よくある失敗

状況 原因 対処
v1.4.1 になってしまった PR タイトルに [release] がなかった タグを削除して再度 release PR を作る
タグが既に存在するエラー 同じバージョンでタグを作ろうとした タグを削除: gh api repos/ebibibi/ebi-agent-chat-relay/git/refs/tags/v1.4.0 --method DELETE

Read the full file on GitHub · 112 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 · 112 lines · 40 tokens per session scan A 8556a5febb13

Subscribe to this mod's changes

release is a skill published in the GitHub repository ebibibi/ebi-agent-chat-relay (56 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,073 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 2026-08-30.

Related

Other skills, from other repositories

switch

How to take part in a Switch room. Load this skill before your first Switch action and whenever Switch comes up — the user mentions Switch, a Switch room or another Switch agent; you are asked to list, join, read or post in a room, create a room or room group, work with references, links or roles, or inspect an agent…

sandbox-quantum/switch · 125 tokens

release-manager

Prepare and operate repository releases through a finite, approval-gated hosted workflow. Use when the user asks to inspect release status, check setup, record component impact, create a generated release PR, plan or approve publication, dispatch post-release evidence, or prepare the OpenAI handoff.

stark-ai-de/agent-skills · 59 tokens

senmu-build-delivery

Govern development batches, non-routine Git, repository and release units, artifacts, deployment, rollback, and production state. Not for ordinary implementation.

SenMuShare/senmu-buildos · 35 tokens

configure

Set up the Switch connector for Claude Code — register this Claude Code instance as a Switch agent and write the credentials the bundled MCP server and hooks read. Use when the user asks to configure Switch, set up the plugin, register with a Switch server, or when the Switch tools report no identity.

sandbox-quantum/switch · 61 tokens

ci-validation-gates

Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22.

webmaxru/is-ai-native · 32 tokens

release-process

Step-by-step release checklist for Squad — prevents v0.8.22-style disasters.

webmaxru/is-ai-native · 20 tokens