Borrowing it
Nothing to install: this file belongs to double-coding-lab/Flow2Spec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/double-coding-lab/Flow2Spec/main/.cursor/skills/repo-dev-check 19-45-15-720/SKILL.mdgit clone --depth 1 https://github.com/double-coding-lab/Flow2SpecWrote 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/double-coding-lab/flow2spec/repo-dev-check-19-45-15-720)<a href="https://agentmods.dev/skills/double-coding-lab/flow2spec/repo-dev-check-19-45-15-720"><img src="https://agentmods.dev/badge/skills/double-coding-lab/flow2spec/repo-dev-check-19-45-15-720/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/double-coding-lab/flow2spec/repo-dev-check-19-45-15-720"><img src="https://agentmods.dev/badge/skills/double-coding-lab/flow2spec/repo-dev-check-19-45-15-720.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 | $0.00104 | $0.02426 |
| Opus 5 | $0.00052 | $0.01213 |
| Sonnet 5 | $0.00021 | $0.00485 |
| Haiku 4.5 | $0.00010 | $0.00243 |
Grade A, and why
repo-dev-check 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 9d 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.
This is a copy
88% identical to repo-dev-check — 53 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-dev-check（本仓开发纪律自查）
适用：仅在 Flow2Spec 双仓自身（
Flow2Spec-public/flow2spec）里开发时启用。下游项目不会拿到本 SKILL——它只存在于本仓的.claude/skills/、.cursor/skills/、.codex/skills/，从不进templates/。单一事实源：本 SKILL 依据
f2s-dev-workflow-constraints规则执行（Claude：.claude/rules/repo-dev-workflow-constraints.md；Cursor：.cursor/rules/repo-dev-workflow-constraints.mdc；Codex：.codex/topics/repo-dev-workflow-constraints.md）。步骤 0 必须 Read 该规则全文。
触发场景
- 用户显式说「跑 dev-workflow 自查 / 检查双仓 / 检查是不是改错地方了」；
- 用户在 Flow2Spec 双仓内、Agent 即将提交前主动自查；
- Agent 发现自己刚做了配置根下的
Edit/Write，或只在单侧仓库落了盘，须补做本自查； - Agent 在改开发纪律相关的规则 / skill / topic 时（比如本文件、
f2s-dev-workflow-constraints）。
不触发：下游项目内、纯业务代码修改无 template/config-root 交集时。
前置
步骤 0：Read .claude/rules/repo-dev-workflow-constraints.md（Cursor：.cursor/rules/*.mdc；Codex：.codex/topics/*.md）全文。不 Read 直接开跑属违规。
编排
- 主 agent 通篇执行：本 skill 无重 IO 操作，无需拆子。
- 配置：不受
flow2spec.config.json.subAgent约束（无论 true / false 都主 agent 跑）。 - 写权：本 skill 不主动落盘业务文件；只做判定 + 建议；确实需要写盘时逐条回到具体 skill（如
f2s-git-commit）流程。
步骤
步骤 1：定位当前仓 + git 摸底
- 判断当前工作目录是否在 Flow2Spec 双仓内：
Bash跑git remote -v查看，若 URL 含github.com/Lands-1203/Flow2Spec或git.dev.sh.ctripcorp.com/trainH5/flow2spec则算作双仓，否则报错退出（下游项目不该跑本 skill）。 Bash：git status -s | grep -v DS_Store列出所有未提交改动。Bash：ls "/Users/<user>/Desktop/项目/ai/flow2spec 双仓/"（或用户当前放双仓的父目录）确认另一侧仓库是否存在于本机。用户不用双父目录时，跳过对侧检查、只做本侧自查（并在摘要提示）。
步骤 2：写盘边界判定（对每份 pending 文件）
对步骤 1 列出的每一份改动文件，套下表判定：
| 文件路径模式 | 是否合规 | 判定依据 |
|---|---|---|
templates/zh-CN/** 或 templates/en-US/** |
✅ 合规 | 生产侧唯一入口 |
docs/** / lib/** / cli.js / scripts/** / package.json |
✅ 合规 | 包源码 |
.Knowledge/** |
✅ 合规 | 本仓自身知识库 |
.claude/rules/repo-dev-workflow-constraints.md |
✅ 合规 | 本仓专属手写规则（templates 无对应源） |
.claude/skills/repo-dev-check/** |
✅ 合规 | 本仓专属手写 skill（templates 无对应源） |
.cursor/rules/repo-dev-workflow-constraints.mdc |
✅ 合规 | 同上（Cursor 端） |
.cursor/skills/repo-dev-check/** |
✅ 合规 | 同上 |
.codex/topics/repo-dev-workflow-constraints.md |
✅ 合规 | 同上（Codex 端） |
.codex/skills/repo-dev-check/** |
✅ 合规 | 同上 |
.claude/rules/<其它>.md / .cursor/rules/<其它>.mdc / .codex/topics/<其它>.md |
❌ 违规 | 有 templates 对应源 → 应改 templates/{zh-CN,en-US}/rules/<其它>.md |
.claude/skills/<其它>/** / .cursor/skills/<其它>/** / .codex/skills/<其它>/** |
❌ 违规 | 有 templates 对应源 → 应改 templates/{zh-CN,en-US}/skills/<其它>/SKILL.md |
根 AGENTS.md |
❌ 违规 | 由 buildCodexAgentsMd(templatesDir, ...) 从 templates 拼装 → 应改 templates/{zh-CN,en-US}/AGENTS.md |
.claude/hooks/** / .cursor/hooks/** / .codex/hooks/** / .claude/settings.json / .cursor/hooks.json / .codex/hooks.json |
❌ 违规 | init 产物 → 需求要改的话改 lib/init.js 或 templates/ |
.claude/memory/** / LOCAL_CONTEXT.md |
⚠️ 本地态 | 不入库，不受约束（但提醒别 commit） |
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.
- 9d ago First seen · 123 lines · 104 tokens per session scan A 526b02d0c2f6
repo-dev-check is a skill published in the GitHub repository double-coding-lab/Flow2Spec (48 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 2,426 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to repo-dev-check, differing in 53 lines, and is treated as a copy.
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…