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/xcodethink/open-claude-code-skills/20npx skills add xcodethink/open-claude-code-skills --skill 20git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/xcodethink/open-claude-code-skills/20)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/20"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/20.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 | $0.00257 | $0.08748 |
| Opus 5 | $0.00129 | $0.04374 |
| Sonnet 5 | $0.00051 | $0.01750 |
| Haiku 4.5 | $0.00026 | $0.00875 |
Grade A, and why
20-机构级项目治理 scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- ❌ **信"~95% 完整/真数据"自评不真机核** — audit 时凭代码读出的"完整"≠真完整; 必须 curl 生产端点 / SSH 只读核验 (见 §8.11) How it starts
The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
20-机构级项目治理 (Institutional Project Governance)
总目标: 让任何 负责人 主导的项目都能用同一套方法论从 0 推到机构级生产级 MVP, 决策可追溯, 跨项目可复用经验。
核心: PMI PMBOK 7 / SAFe Essential 单人/小团队适用子集 — 不是缩水版, 是去掉单人不需要的件 (formal stakeholder mgmt / ART sync / burndown chart / communication matrix) 之后的完整子集。
第一参考实施: ProjectA (2026-05-12 起).
docs/strategy/+docs/decisions/+docs/audit/三个目录是 reference impl, 任何新项目可对照学。
1. 什么时候触发本 skill
1.1 强制触发场景 (必须用本 skill)
- 任何项目要开始机构级生产级 MVP 推进
- 现有项目要做全平台审计 + 升级优化 ("不是介绍网站, 是真平台")
- 出现"总体方案 / 总目标 / workstream / 全局考虑 / PMI / SAFe"等关键词
- 需要决策可追溯(回查"我们为什么这么做")
- 跨多次会话的长周期项目需要 state pointer
1.2 可选触发场景 (用本 skill 更好)
- 项目有 ≥ 5 个独立功能域,需要 dashboard 视角
- 项目有重大决策需要正式记录 (ADR)
- 项目跑过审计但没结构化跟踪 (升级现有审计)
1.3 跳过本 skill 的情况
- 一次性 ≤ 3h 的纯技术任务 (用 STANDARD-PROMPT 太重)
- 探索性 prototype (没有 MVP 目标)
- 第三方代码 review (本 skill 是自家项目治理)
2. 方法论总览 — 3 层 + 4 件 PMI best practice
2.1 4 层架构 (v1.2: 加 Layer 1.5 Feature-Level Audit)
┌─────────────────────────────────────────────────────────────┐
│ Layer 0: 战略 (Strategy) — 季度 review │
│ MASTER-PLAN.md (1-2 页 总体方案) │
│ RAID-LOG.md (Risks / Assumptions / Issues / Deps) │
│ docs/decisions/ (ADR — Architecture Decision Records) │
├─────────────────────────────────────────────────────────────┤
│ Layer 1: 子版块 (Workstreams) — 每周 review │
│ WORKSTREAMS.md (N 个固定 workstream, 数量锁定) │
│ 含跨 WS 影响表 (供 GLOBAL IMPACT CHECK 查) │
├─────────────────────────────────────────────────────────────┤
│ Layer 1.5: Feature-Level Audit — 升级前 1 次 │ ⭐ v1.2 新增
│ docs/audit/YYYY-MM-DD-{ws}-audit-plan.md (方法论 + 队列) │
│ docs/audit/YYYY-MM-DD-{ws}/{NN-feature}.md (每 feature 1 份)│
│ 6 段模板: 定位 / 对标 / 现状 / 缺口 / 方案 / Wave 拆分 │
│ 4 标杆基准 (机构顶级 / 机构研究 / 零售旗舰 / 选用) │
│ P0/P1/P2 优先级矩阵 + 跨 feature 依赖图 │
│ ADR-stub 锁定方向 (实战后升级正式 ADR) │
├─────────────────────────────────────────────────────────────┤
│ Layer 2: Wave 循环 (实施) — 每个 wave (≤8h) │
│ STANDARD-PROMPT.md (wave 循环 + 行为铁律 + 沟通规则) │
│ HANDOFF.md (会话间状态接力) │
│ │
│ 循环步骤: │
│ AUDIT → ANALYZE → 🆕 GLOBAL IMPACT CHECK → REVIEW │
│ → EXECUTE → VERIFY → DOCUMENT → ⤴ │
│ ⚠️ Wave spec 必须从 Layer 1.5 audit doc 来, 不允许凭感觉 │
└─────────────────────────────────────────────────────────────┘
What ships with it
13 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.
- agents/openai.yaml 797 B
- INSTALL.md 11 KB
- README.md 2.3 KB
- SKILL.en.md 32 KB
- templates/ADR-template.md 1.7 KB
- templates/AUDIT-PLAN.template.md 4.8 KB
- templates/FEATURE-AUDIT.template.md 6.5 KB
- templates/HANDOFF.template.md 1.1 KB
- templates/MASTER-PLAN.template.md 6.3 KB
- templates/QUALITY-AUDIT-BACKLOG.template.md 9.0 KB
- templates/RAID-LOG.template.md 1.9 KB
- templates/STANDARD-PROMPT.template.md 7.1 KB
- templates/WORKSTREAMS.template.md 2.2 KB
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.
- 4d ago First seen · 475 lines · 257 tokens per session scan A 957b1a2acb1e
20-机构级项目治理 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 257 tokens to every session and 8,748 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
moai-workflow-project
Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.
project-plan
Turn a product goal or feature request into a clear Agiflow project plan with small, testable tasks in Planning status. Use when starting a project, decomposing a feature, clarifying requirements, or converting an idea into an actionable backlog.
refine-task
Refine an existing Agiflow task into an unambiguous, testable specification without expanding its intended outcome. Use when a task is vague, lacks acceptance criteria, has unclear scope or dependencies, or is not ready for backlog grooming.
getting-started
Assess an authenticated Agiflow workspace and recommend the right next project-management workflow. Use when a user is new to Agiflow, asks what to do next, needs orientation, or is unsure whether to plan, refine, groom, triage, or review daily status.