a2wave: Skill for Claude Code

.agents/skills/release-workflow/SKILL.md

release-workflow is a skill for Claude Code, Codex from LilithGames/a2wave. It costs 27 tokens per session (3,037 once invoked), scanned A, original, Apache-2.0.

A release procedure for a repository that publishes a platform and command-line package from the same version line. It covers checks, changelog updates, version selection, tagging, and pushing the release.

In plain words
What is it for?
Use it when creating a release, updating the changelog, or making and pushing a version tag on the main branch.
Why use it?
It reduces release failures caused by the wrong branch, unsynced code, failing tests, uncommitted changes, leaked credentials, or mismatched versions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is LilithGames/a2wave's own configuration. It tells Claude Code and Codex how to work on a2wave 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 a2wave configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/gates/check-forbidden-tokens.mjs --all.

Reuse

Borrowing it

Nothing to install: this file belongs to LilithGames/a2wave. 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/LilithGames/a2wave/main/.agents/skills/release-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LilithGames/a2wave

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-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/lilithgames/a2wave/release-workflow/github.svg)](https://agentmods.dev/skills/lilithgames/a2wave/release-workflow)
Your own site
<a href="https://agentmods.dev/skills/lilithgames/a2wave/release-workflow"><img src="https://agentmods.dev/badge/skills/lilithgames/a2wave/release-workflow/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-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/lilithgames/a2wave/release-workflow"><img src="https://agentmods.dev/badge/skills/lilithgames/a2wave/release-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,037 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 57
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 57
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00027 $0.03037
Opus 5.5 $0.00011 $0.01215
Sonnet 5.5 $0.00005 $0.00607
Haiku 4.5 $0.00003 $0.00304

Measured 1mo ago against content hash ea9003b38347, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-workflow 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 1mo 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.

.agents/skills/release-workflow/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Workflow

Overview

发版流程:前置检查 → 确定新版本号 → 写入 CHANGELOG → 创建 tag 并推送。只能在 main 分支执行。

仓库只有一套 tag:平台与 CLI 共用同一条版本线,一个 v* tag 触发全部三个 workflow。

Tag 前缀 用途 CI 自动做的事
v*(如 v0.7.1) 整个仓库发版(平台 + CLI) ① 从 CHANGELOG 抽段落 → 创建 GitHub Release ② 构建并推送多架构 Docker 镜像到 GHCR ③ typecheck / test / 包内容校验 → 把 a2wave 包发到公共 npm(带 provenance,需 NPM_TOKEN 仓库 secret)

因此 package.json 与 apps/cli/package.json 的 version 必须始终一致,且都要与 tag 一致——两个 workflow 都会校验,不一致直接失败。

When to Use

  • 用户要求发版、打 tag、创建 release
  • 需要更新 CHANGELOG 并推送新版本
  • 关键词:发版、release、tag、changelog

Core Workflow

flowchart LR
    P[0. 前置检查] --> S[0.5 敏感 token 扫描]
    S --> W[0.7 使用手册同步]
    W --> A[1. 确定版本号]
    A --> B[2. 写入 CHANGELOG]
    B --> C[3. 创建 tag 并推送]

步骤 0:前置检查(必须全部通过)

  • main 分支:git branch --show-current 必须为 main。若非 main,中止并提示 git checkout main 后再执行。
  • 与远程同步:在 main 分支时,必须先执行 git pull origin main(或 git pull)。若 pull 产生冲突或失败,中止并提示用户解决后再发版。pull 成功后再进行后续检查。
  • 测试通过:pnpm test:all 必须零失败。失败则中止。
  • 工作区干净:git status 无未提交变更。若有其它未提交文件,提示用户先 commit 再发版。

步骤 0.5:敏感 token / 凭据扫描(HARD GATE,禁止跳过)

发版会把整份代码 tag 化并(主版本)触发 GitHub Release,一旦泄露的 secret 进入 tag,撤回成本极高。打 tag 前必须对将要发布的全量代码做一次密钥扫描:

# 全仓扫描(不只是本次 diff)——发版是整棵树的快照,必须全量
node scripts/gates/check-forbidden-tokens.mjs --all
  • 该脚本覆盖 PEM 私钥、Anthropic key(sk-ant-*)、AWS、通用高熵 token 等规则,allowlist 在 scripts/gates/forbidden-tokens-allowlist.json。
  • exit 0 → 通过,继续。exit 1 → 打印命中的「文件:行 规则」,立即中止发版:
    • 若是真实泄露:先清理(移除/改用 env/轮换该凭据),涉及历史提交的需 git filter-repo 或联系维护者,处理干净后重新走发版。
    • 若是误报(占位值 / 公钥 / fixture):把精确 literal 或路径前缀加进 forbidden-tokens-allowlist.json,commit 后再继续。禁止用 --no-verify 或跳过本步绕过。
  • 补充人工核查:git diff <上一个tag>..HEAD -- '*.env' '*.env.*' '**/config/**' 快速扫一眼配置类文件有无硬编码密钥;.env、.kubeconfig、私钥文件等绝不允许进入 tag。

步骤 0.7:使用手册(Wiki)同步

若本次发布区间(<上一个tag>..HEAD)包含用户可感知的功能/流程/触发方式变更,站内使用手册(/wiki)必须已同步,否则用户拿到新版本却查不到用法。

Read the full file on GitHub · 179 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. 1mo ago First seen · 179 lines · 27 tokens per session scan A ea9003b38347

Subscribe to this mod's changes

release-workflow is a skill published in the GitHub repository LilithGames/a2wave (27 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 3,037 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

release-cut

Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…

BlackBeltTechnology/pi-agent-dashboard · 93 tokens

release-revoke

Revoke or rollback a pi-agent-dashboard release: delete the GitHub Release, remove the git tag locally and on origin, deprecate the npm version (npm unpublish is blocked after 72h), and optionally revert the release commit. Use when the user says "revoke release", "rollback release", "delete release", "unpublish…

BlackBeltTechnology/pi-agent-dashboard · 85 tokens

github

Complete guide for the GitHub plugin — REST API access for repositories, issues, pull requests, actions, releases, and search using a GitHub Personal Access Token.

stagewise-io/stagewise · 35 tokens

changeset

USE WHEN: a change under apps/ or packages/ (or an app runtime dependency bump) needs its release note, the user asks to add, fix, or check a changeset, a PR is about to open, or pnpm release:check fails. DO NOT USE WHEN: editing the release pipeline itself (.changeset/config.json, release.yml, the check scripts) …

louisbrulenaudet/monorepo-template · 87 tokens

ship-change

Ship an OpenSpec change after openspec-apply completes. When only QA/manual tasks remain, marks them done (tested later), archives + syncs specs, commits, pushes, opens a PR against develop, watches CI, waits for CodeRabbit, auto-applies safe fixes and re-pushes, loops until CI green + no actionable review threads…

BlackBeltTechnology/pi-agent-dashboard · 129 tokens

akiship

Full release ritual end-to-end — front-loaded checks, then an unattended pass. ACTIVATION = the literal token /akiship, or an imperative turn, in any language, ordering the release ritual for this repo. A question about it, or a completion word with no release object, activates nothing — consult the checklist and…

lacvietanh/akidevrule · 120 tokens