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.
npx agentmods add skills/peiiii/skild/project-osnpx skills add Peiiii/skild --skill project-osgit clone --depth 1 https://github.com/Peiiii/skildWrote 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.
[](https://agentmods.dev/skills/peiiii/skild/project-os)<a href="https://agentmods.dev/skills/peiiii/skild/project-os"><img src="https://agentmods.dev/badge/skills/peiiii/skild/project-os.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00763 |
| Opus 5 | $0.00010 | $0.00381 |
| Sonnet 5 | $0.00004 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
project-os 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 6d 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.
What it actually says
Project OS
用于在新项目中快速落地“开发规范 + 迭代日志 + 发布闭环”的通用体系（Project OS），面向未来演进为可自治、可编排、自动驱动研发流程的 AI 操作系统。
三段式定位
-
自治闭环
覆盖需求—实现—验证—发布—线上冒烟—复盘的端到端闭环，系统自动推动流程完成并形成可追踪证据链。 -
自动化编排
将研发流程拆解为可编排的步骤与指令（commands/skills/workflows），以最小人工干预串联执行、回滚与验收。 -
规则驱动执行
所有行为由 Rulebook 统一约束与裁决，确保执行一致性、合规性与可审计性；如需例外必须显式声明并记录。
适用场景
- 想把一套严格交付流程迁移到其他项目。
- 需要在团队内统一验证/冒烟/发布规范。
启用方式（必须先初始化才生效）
本 Skill 安装后不会自动生效，首次使用时需要初始化；初始化完成后规则与流程才会被执行。
初始化流程（首次使用）
- 用户安装本 Skill 并开始与 agent 对话。
- agent 检测到目标项目尚未初始化（如缺少
AGENTS.md/commands/docs/logs）。 - agent 主动提示初始化必要性与影响，并请求确认。
- 用户确认后，agent 自动完成初始化并反馈结果。
初始化会做什么
- 生成/更新
AGENTS.md（若已存在，则合并而非覆盖） - 生成/更新
commands/commands.md - 生成/更新
docs/logs与docs/workflows - 保证规则、指令索引、日志制度完整落地
手动初始化（仅作为兜底）
将本 Skill 的模板复制到目标项目根目录（若已有文件，需合并而非覆盖）：
cp -R <skill>/assets/commands ./commands
cp -R <skill>/assets/docs ./docs
cp <skill>/assets/AGENTS.template.md ./AGENTS.md
关键约束
- “完成所有/完成全部”默认执行完整上线闭环（migrations -> deploy -> 线上冒烟）。
- 冒烟测试默认使用非仓库目录环境，禁止写入仓库子目录。
- 每次开发阶段结束必须完成 build/lint/tsc + 冒烟（如适用）。
扩展与维护
- 新增/修改指令：更新
commands/commands.md并同步 AGENTS 索引。 - 新增/修改规则：只在 AGENTS 的 Rulebook 维护。
- 发布流程统一写入
docs/workflows/npm-release-process.md。
模板索引
assets/AGENTS.template.mdassets/commands/commands.mdassets/docs/logs/TEMPLATE.mdassets/docs/logs/README.mdassets/docs/workflows/npm-release-process.md
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 81 lines · 19 tokens per session scan A e38cb7df8565
project-os is a skill published in the GitHub repository Peiiii/skild (113 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 763 once invoked, about $0.0001 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.
Other skills, from other repositories
cis-aws-compute-2.3
Ensure Tag Policies are Enabled.
methode-projet
Méthodologie de gestion de projet: décomposition, priorisation, jalons, estimation, bonnes pratiques. À consulter lors de la structuration de projets.
nouveau-projet
Démarrer et structurer un nouveau projet de A à Z.
demande-evolution
Recueillir et cadrer une demande d'évolution ou de nouvelle fonctionnalité.
ticket-incident
Traiter un ticket d'incident pour Martin Digital.
retro
Engineering retrospective from git metrics. Reports deployment frequency, release cycle span, churn hotspots, backlog health. Outputs narrative report with 3+ actionable items. Flags: --since, --path, explicit range argument.