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 skills add tsyzthh/skills --skill projgit clone --depth 1 https://github.com/tsyzthh/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/tsyzthh/skills/proj)<a href="https://agentmods.dev/skills/tsyzthh/skills/proj"><img src="https://agentmods.dev/badge/skills/tsyzthh/skills/proj.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 | $0.00183 | $0.05725 |
| Opus 5 | $0.00092 | $0.02863 |
| Sonnet 5 | $0.00037 | $0.01145 |
| Haiku 4.5 | $0.00018 | $0.00573 |
Grade A, and why
proj 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
总入口（proj）
proj-* 流水线的用户总入口：用户描述问题，由本 skill 作薄 Supervisor + 有界 plan-execute-verify loop + facade，编排 5 个专家 skill（proj-experts / proj-shape / proj-plan / proj-survey / proj-run）跑完「想法 → 收敛 → 规划 → 执行 → 验证」闭环，并在 GATE 处停下交人。
落实
docs/discuss/DECISIONS.mdORD-29（薄入口 facade）/ ORD-30（职责收窄 · 不重做 host 路由）/ ORD-31（有界 loop + autonomy slider）；EXP-07 passed 验证。
这个 skill 是什么 / 不是什么（ORD-30）
| 是 | 流水线之上的 Supervisor + 状态机 + 有界 loop + facade。持有「现在到哪一阶段、该停哪个 GATE、下一步跑哪个专家」的跨 skill 状态——这是 host 单次路由给不了的。 |
| 不是 | 一个「决定调用哪个 skill」的路由器。host 的 model-invocation 已按 description 做单次 skill 选择（纯 LLM 推理，无路由代码）；本 skill 不重做这件事。 |
为什么这条重要：Agent Skills 默认 model-invoked（Anthropic），重做路由 = 重复 host 已做的事，撞「先求最简、必要才加复杂度」（Anthropic Building Effective Agents）。本 skill 的唯一增量 = host 给不了的有状态序列 + GATE + loop。
设计 vision · 角色分工（Supervised-AI mode）
| 角色 | 谁 | 职责 |
|---|---|---|
| Sponsor + 关键决策 | 人 | GATE 审批 / go-no-go / 关键 trade-off / abort-retry |
| Orchestrator（编排） | AI（本 skill） | 维护 pipeline 状态、按序调专家、跑有界 loop、到 GATE 停、回写 memory |
| Specialist（执行） | 5 个 proj- skill* | 各自单一关注点；本 skill 读其 SKILL.md 并跟随 |
对齐 PMBOK 8 AI 立场：AI augment, human accountable for critical decisions（Agentic PM Supervised-AI mode）。
固定专家集（Supervisor 调用对象 · ORD-29）
| 阶段 | 专家 skill | 产出 |
|---|---|---|
| 商业论证 | proj-experts |
专家视角（无状态，按需） |
| 决议收敛 | proj-shape |
docs/discuss/ + DECISIONS.md |
| 规划 | proj-plan |
docs/pmo/phase-NN/plan.md |
| 执行 | proj-run |
acceptance.md + 产出登记 |
| 接管 | proj-survey |
docs/survey/ 现状基线（brownfield 入口） |
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.
- 8d ago First seen · 239 lines · 183 tokens per session scan A 7df0c0cdb510
proj is a skill published in the GitHub repository tsyzthh/skills (5 stars, last pushed 11d ago), licensed MIT. It adds 183 tokens to every session and 5,725 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…