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 tranfu-labs/tranfu-skills --skill project-init-docsgit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/project-init-docs)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/project-init-docs"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/project-init-docs/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.
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/project-init-docs"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/project-init-docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00376 | $0.04879 |
| Opus 5 | $0.00188 | $0.02440 |
| Sonnet 5 | $0.00075 | $0.00976 |
| Haiku 4.5 | $0.00038 | $0.00488 |
Grade A, and why
project-init-docs 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目初始化文档（AI 协作基线）
使用这个技能：当用户在代码仓库里说"初始化"时，分析真实仓库，并搭建一套让 AI 能安全协作、先设计再实现的知识与规格基线。
任务不是拷贝空白模板，而是把真实仓库的事实——语言、命令、目录、模块、业务域、部署方式——写进一套固定的目录契约。基线建立后，任何 AI 拿到 AGENTS.md 就知道结构/命令/禁区，拿到 DEPLOY.md 就知道部署到哪/怎么建/怎么发/怎么退/怎么验，拿到 module-map.md 就知道依赖边界，拿到 openspec/ 和 docs/adr/ 就知道"先设计再实现"的契约与既有决策，拿到 docs/wireframes/ 就知道每个页面当前的版式事实。
两套事实源并列：openspec/specs/<domain>/spec.md 是行为事实源，docs/wireframes/ 是版式事实源。两者都靠 openspec/changes/ 流转更新——改业务逻辑的 change 写 spec-delta/，改页面版式的 change 写 wireframes.md（本项目扩展，按需新建），归档时分别回流到 specs/ 和 docs/wireframes/，归档动作由 openspec/changes/AGENTS.md（本 skill 生成）统一定义。
核心原则
- 内容来自真实仓库：命令来自真实脚本（package.json scripts / Makefile / justfile 等），模块来自真实源码目录，业务域来自真实代码。探测不到的，标注
TODO: 需人工确认，绝不编造命令或依赖。 - 幂等：已存在的文件默认不做破坏性覆盖。只补全缺失小节，或报告差异交由用户决定。覆盖任何已存在文件前，必须先读它、向用户说明、得到确认。
- 目录级说明一律用 AGENTS.md + CLAUDE.md，绝不用 README：需要解释"怎么在这个目录工作"时，写一个本地
AGENTS.md（真实内容）+ 一个CLAUDE.md（仅一行See AGENTS.md ...，路径相对该目录）。 - 命名产物保留专用名：
module-map.md、spec.md、ADR 文件是具名契约产物，不被AGENTS.md取代。 - 正文用用户语言（默认中文）；文件路径与各文件的小节标题是固定契约，不翻译、不改写。
不触发
- 代码层初始化：
git init/npm init/create-react-app/cargo new/ 任何脚手架命令。 - 只新建单个文档（如"帮我写个 README / 写个贡献指南"）。
- 编写业务代码或修 bug。
- 对某个已存在文件做局部小修改——那是普通编辑，不是初始化。
脚本与引用文件
确定性骨架由脚本铺设，AI 只填真实仓库事实。脚本在仓库根运行：
scripts/probe.sh [domain...] [--pages <页...>]：只读探针，扫描全部基线目标，输出路由表状态<TAB>路径<TAB>类别（状态 = MISSING/EMPTY/PRESENT，类别 = static/repo-fact）。不写盘。scripts/fill.sh：基线产物的唯一事实源。--list列目标清单；--auto [domain...]对所有缺失/为空目标自动填充；<target>只填单个目标。已存在且非空的目标一律 SKIP，绝不覆盖。
产物分两类：
- static（纯静态）：所有
CLAUDE.md指针、openspec/changes/AGENTS.md+_template/、docs/adr/AGENTS.md+0000-record-architecture-decisions.md；以及线框图的docs/wireframes/{AGENTS.md,CLAUDE.md,legend.md,_template/page.md}。内容与仓库无关，缺失/为空时由fill.sh写死，AI 不手敲。 - repo-fact（真实事实）：根
AGENTS.md、根DEPLOY.md、docs/architecture/module-map.md、openspec/specs/<domain>/spec.md；以及线框图的docs/wireframes/flow.md（页面流转图，默认铺）和docs/wireframes/pages/<page>.md（探测到路由时追加）。缺失/为空时fill.sh只铺骨架（repo-fact 文件铺「小节标题 +TODO」，页面文件铺「比例尺+断点框+注释表」模板，flow.md 铺「流程示例+TODO 步骤表」），真实命令/模块/业务规则/部署事实/页面版式/流转关系仍由 AI 填正文。
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 80 B
- assets/icon.png 696 B
- assets/icon.svg 756 B
- assets/wireframes/_template/page.md 2.7 KB
- assets/wireframes/AGENTS.md 5.2 KB
- assets/wireframes/CLAUDE.md 61 B
- assets/wireframes/flow.md 1.2 KB
- assets/wireframes/legend.md 2.5 KB
- README.md 4.9 KB
- README.zh.md 4.2 KB
- references/file-templates.md 13 KB
- scripts/fill.sh 13 KB runs code
- scripts/probe.sh 1.2 KB runs code
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.
- 10d ago First seen · 145 lines · 376 tokens per session scan A 86a71aaf6f58
project-init-docs is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed today), licensed MIT. It adds 376 tokens to every session and 4,879 once invoked, about $0.0019 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…