os-release

os-release is a skill for Claude Code from CronusL-1141/AI-company. It costs 94 tokens per session (4,531 once invoked), scanned C, original, MIT.

A release checklist for publishing a new version of AI Team OS. It covers checks, synchronized version updates, bilingual release notes, builds, commits, tags, repository pushes, and GitHub release records.

In plain words
What is it for?
Use it before or after an AI Team OS release to run preflight checks, prepare version changes and release commands, verify online release information, and preserve the required user approvals.
Why use it?
It reduces the risk that code, version numbers, build files, tags, and the public release entry disagree or are published in the wrong order.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/preflight.sh # 发版必须跑全量,不要 --fast.

Part of the ai-team-os plugin — 5 skills, 8 commands, 25 agents, 15 hooks, 1 MCP server shipped together

Good fit Use it before or after an AI Team OS release to run preflight checks, prepare version changes and release commands, verify online release information, and preserve the required user approvals.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/CronusL-1141/AI-company
agentmods
npx agentmods add skills/cronusl-1141/ai-company/os-release

Made for: Claude Code.

Or install ai-team-os, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 25 agents, 15 hooks, 1 MCP server.

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 os-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/cronusl-1141/ai-company/os-release/github.svg)](https://agentmods.dev/skills/cronusl-1141/ai-company/os-release)
Your own site
<a href="https://agentmods.dev/skills/cronusl-1141/ai-company/os-release"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/os-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 os-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/cronusl-1141/ai-company/os-release"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/os-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,531 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00094 $0.04531
Opus 5 $0.00047 $0.02266
Sonnet 5 $0.00019 $0.00906
Haiku 4.5 $0.00009 $0.00453

Measured yesterday against content hash 9180f50923fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

os-release scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf plugin/dashboard-dist
plugin/skills/os-release/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OS Release — 发版清单

为什么有这份清单

凡是进了 scripts/check_invariants.sh 的红线都没烂;没进机检的漏了两次,且完全同型:

  • v1.10.0/1/2 的 tag 是 2026-07-14 打的,GitHub Release 条目 07-21 才批量补;
  • v1.10.3/v1.11.0/v1.11.1 的 tag 分别是 07-27 / 07-27 / 07-29 推的,Release 条目 07-30 才一次补齐(实测三条 publishedAt 挤在 30 秒内),期间访客主页侧边栏两周 显示 Latest v1.10.2

机检管得住的部分不用你记,跑一条命令即可。这份清单只管机检管不住的部分,以及 谁按哪个按钮

执行分工(硬约束:发布流水线必须可中断)

步骤 谁执行
0–6 准备与校验 Leader 全权
7 commit · 8 tag Leader 执行,但先把 git diff --stat 与拟好的 message 交用户批准
9 双仓推送 · 10 建 Release 条目 用户执行。Leader 只把命令准备好打印出来
11 事后核对 Leader(只读)

不要代替用户 push / publish,也不要在未批准前 commit。


0. 确认在哪儿干活

git branch --show-current

本仓库并行会话纪律:第二个及之后的会话必须用 git worktree 隔离。发版这类跨全树的 改动尤其不能与别人共享 checkout。

1. 预检全绿

bash scripts/preflight.sh          # 发版必须跑全量,不要 --fast

四道门禁:ruff check src/ tests/dashboard npm run lintcheck_invariants.sh (I1–I20)→ pytest tests/unit/

失败长这样:每项后面跟 ✗ <门禁名> 失败,末尾 ✗ 预检未通过 — 修复后再 push。 退出码非 0。

两处既定豁免

  • 未构建 dashboard/dist 的环境里 I3 输出 ⚠️ dist 目录缺失(未构建环境可忽略) ——警告不拦。但发版必须构建(见第 4 步),所以发版时这条不该还是警告。
  • I16 在 execpolicy rules 或 Codex 二进制缺席时输出 ⚠️ [I16] Codex execpolicy(...) ——本期是占位状态,warn 不拦。它转成 ok 的那一天要留意:那意味着这台机器上真的跑了 一次宿主校验,结论才有分量。

2. 版本锁步七处

I2 机检的五处(漂移即红,❌ [I2] 版本号漂移: ...):

  • pyproject.toml
  • src/aiteam/__init__.py
  • plugin/.claude-plugin/plugin.json
  • plugin/.claude-plugin/marketplace.json
  • .claude-plugin/marketplace.json

另两处由 I6 第①类硬等式盯README.mdREADME.zh-CN.md 的 announcement 行 (> ⚡ 开头)必须含 v<新版本>,否则 ❌ [I6] README 数字漂移

机检不覆盖、必须人眼看的plugin/.claude-plugin/plugin.jsondescription 文本中的数字(MCP 工具数、生命周期事件数)。v1.11.1 那次人审抓到的唯一实锤就在这里 ——两处数字腐烂了整整一个版本。

README 里的其余数字(工具数/页面数/端点数/测试数)由 I6 对照实测校验,按实测改, 不要按记忆改

3. CHANGELOG 中英双语同步

  • 英文 CHANGELOG.md 加新版本段,标题格式 ## [x.y.z] - YYYY-MM-DD
  • 中文 CHANGELOG.zh-CN.md 同步全译。缔造者 2026-07-30 裁定:中文版维持镜像 全译契约——不是摘要,也不退役。
  • 段落内容按 git log 与设计文档逐条取证写成,不照抄计划(计划里没做成的东西 写进 CHANGELOG 就是假账)。

Read the full file on GitHub · 283 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. yesterday Changed · +10 lines 9180f50923fe
  2. 2d ago Changed · +32 lines 7cbdfae86f77
  3. 11d ago First seen · 241 lines · 94 tokens per session scan C c881629f9891

Subscribe to this mod's changes

os-release is a skill published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 4,531 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

pack-submit

Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.

aeonfun/aeon · 27 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

submit-hook

Submit a deployed Uniswap v4 hook to the public univ4-hooks registry - format the listing, open a PR (issue fallback) so it lists on the hook marketplace.

aeonfun/aeon · 39 tokens

multi-repo-release

Prepares and validates GPT-RAG umbrella and multi-repository releases. Use whenever work involves release preparation, semantic versions, release branches, manifest or component pins, changelog release entries, tags, GitHub Release notes, or AI Landing Zone release alignment.

Azure/GPT-RAG · 56 tokens

changelog

AI DevKit · Update CHANGELOG.md Unreleased items from git commits since the latest release. Use when users ask to update changelog/release notes from recent commits, with one concise line per commit and commit/PR links.

codeaholicguy/ai-devkit · 49 tokens