Borrowing it
Nothing to install: this file belongs to dslsdzc/rev-skills. 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/dslsdzc/rev-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/dslsdzc/rev-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/instructions/dslsdzc/rev-skills/claude-md)<a href="https://agentmods.dev/instructions/dslsdzc/rev-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/dslsdzc/rev-skills/claude-md/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/instructions/dslsdzc/rev-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/dslsdzc/rev-skills/claude-md.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 | $0.05250 | $0.05250 |
| Opus 5.5 | $0.02100 | $0.02100 |
| Sonnet 5.5 | $0.01050 | $0.01050 |
| Haiku 4.5 | $0.00525 | $0.00525 |
Grade A, and why
rev-skills CLAUDE.md 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 16d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
仓库性质
通用逆向工程 AI 技能库（122 个技能），发布形态有三个：npm 包（bin/install.mjs 安装器）、Claude Code 插件市场（.claude-plugin/marketplace.json）、以及可被任意 Agent Skills 兼容运行时读取的 .claude/skills/ 目录。
内容主体是 Markdown 技能文档，工具代码是零依赖 Node.js（>=22，当前受支持 LTS，ESM）。没有构建步骤——技能即目录，改完跑校验即可。
仓库按 LF 存储（.gitattributes：* text=auto eol=lf）。校验与转换按 LF 解析 frontmatter 与能力注册表，Windows 上 core.autocrlf=true 的旧检出会把技能读成 CRLF 并让 node validate.mjs 整库报错（missing frontmatter + 能力标签全判未注册）；重新检出即可，或把工作树按 LF 归一（lib/frontmatter.mjs 自身已容错 CRLF，但注册表读取还没有）。
双许可：技能文档内容 CC BY 4.0，工具代码（bin/、validate.mjs、tests/）Apache-2.0。新增文件注意落在正确一侧。
常用命令
npm test # 全量：结构校验 + 单元测试
node validate.mjs # 只跑结构校验，输出 OK: 122 skills validated
node --test tests/validate.test.mjs # 单跑一个测试文件
node --test --test-name-pattern="good-skill" tests/*.test.mjs # 按用例名过滤
node bin/capindex.mjs # 重新生成能力索引（改 capabilities 声明后必跑）
node bin/capindex.mjs --check # 只校验索引是否过期（npm test 已含）
node bin/toollife.mjs check # 命令/API 登记表一致性 + 时效（npm run toollife；npm test 已含一致性）
node bin/toollife.mjs candidates # 技能里出现但未登记的命令候选
node bin/toollife.mjs stale # 按超期排序的待核验项
node bin/toollife.mjs smoke # 本机探测（仅报告，CI 机器不必装）
node bin/examplecheck.mjs # 技能示例代码块语法检查（npm run examples；需 python3/bash，缺失时跳过）
node bin/auditstate.mjs status # 增量审查：哪些技能内容在复核之后又变了（= 下一轮审查波的工作集）
node bin/auditstate.mjs update <技能...> # 复核后回填（写当前 hash + 日期）
node bin/probelist.mjs # 由登记表生成 probe.sh 的工具清单（--check 校验新鲜度，npm test 已含）
npx rev-skills install --target <claude|gemini|cline|codex|cursor|copilot|windsurf|dsh|all> \
[--global|--project] [--dry-run] [--link] [--force]
node bin/convert.mjs --target <cursor|copilot|windsurf> --out <dir> # 技能 → 规则文件转换（调试用）
node bin/dsh.mjs check [--dir <skillsRoot>] [--json] # 按 DSH 发现规则校验技能根：通过则输出 OK: N skills DSH-compatible
node bin/dsh.mjs preset spec # 打印预设配置（含技能根解析结果与 REV_SKILLS_DIR 覆盖）
node bin/dsh.mjs preset status [--profile-dir <dir>] [--json] # 只读检查 profile 是否已启用该 bundle
node bin/dsh.mjs preset install [--profile-dir <dir>] [--force] [--apply] # 默认 dry-run，--apply 才写（写前备份）
node bin/dsh.mjs preset uninstall [--profile-dir <dir>] [--apply] # 默认 dry-run，有备份时从备份还原
npx rev-skills install --target dsh --global # 技能装进 DSH 技能根（~/.dsh/skills）
npx rev-skills install --target dsh --project # → .dsh/skills
node bin/wxsource.mjs kanxue list [--board re] [--pages 2] [--md] # 看雪论坛列表（经验采集源）
node bin/wxsource.mjs kanxue thread <帖子ID> [--md]
node bin/wxsource.mjs wechat <文章URL> [--md]
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.
- 16d ago Changed · +21 lines · +1,041 tokens per session 7fe6d269f544
- 22d ago Changed · +31 tokens per session 4abda44f35a2
- 1mo ago Changed · +22 lines · +608 tokens per session 54c7077d7ae2
- 1mo ago First seen · 126 lines · 3,570 tokens per session scan A c6717680247b
rev-skills CLAUDE.md is an instructions file published in the GitHub repository dslsdzc/rev-skills (203 stars, last pushed 16d ago), licensed Apache-2.0. It adds 5,250 tokens to every session, about $0.0210 per session on Opus 5.5. 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 2026-09-13.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.