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 instructions/haojing8312/workclaw/claude-mdgit clone --depth 1 https://github.com/haojing8312/WorkClawWrote 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/haojing8312/workclaw/claude-md)<a href="https://agentmods.dev/instructions/haojing8312/workclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/haojing8312/workclaw/claude-md.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 | $0.06403 | $0.06403 |
| Opus 5 | $0.03202 | $0.03202 |
| Sonnet 5 | $0.01281 | $0.01281 |
| Haiku 4.5 | $0.00640 | $0.00640 |
Grade A, and why
WorkClaw 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 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.
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 — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
本文件为 Claude Code (claude.ai/code) 在此代码库中工作时提供指导。
重要约定:除代码、命令、文件路径、技术术语等必须使用英文的内容外,所有说明、注释、文档均使用中文。
项目概述
WorkClaw 是一个开源的 AI Skill 打包与桌面应用发布平台。项目由两个 Tauri 桌面应用组成:Studio(供创作者打包 Skill)和 Runtime(供用户安装和运行 Skill)。Skill 使用 AES-256-GCM 加密打包成 .skillpack 文件。
Monorepo 结构
apps/
├── studio/ # 创作者端应用 (Tauri + React)
├── runtime/ # 用户端应用 (Tauri + React + Node.js Sidecar)
│ ├── src-tauri/ # Rust 后端,包含 agent 系统
│ └── sidecar/ # Node.js HTTP 服务器 (Playwright, MCP)
packages/
└── skillpack-rs/ # 核心加密/打包库 (Rust)
包管理器: pnpm workspaces + Turborepo
常用命令
# 开发
pnpm runtime # 以开发模式运行 Runtime 应用
pnpm studio # 以开发模式运行 Studio 应用
# 构建
pnpm build:runtime # 构建 Runtime 生产版本
pnpm build:studio # 构建 Studio 生产版本
# 测试
cd apps/runtime/src-tauri
cargo test # 运行所有 Rust 测试
cargo test --test test_registry # 运行特定测试文件
# Sidecar
cd apps/runtime/sidecar
pnpm build # 构建 Node.js sidecar
核心架构
1. 加密系统(基于用户名)
加密模型使用确定性密钥推导方式,从用户名生成密钥:
username → PBKDF2-HMAC-SHA256 (100k iterations) → AES-256-GCM key
↓ salt = SHA256(skill_id + skill_name)
关键特性:
- 相同用户名 + Skill 始终生成相同密钥
- 创作者无需存储密钥
- 通过 manifest 中加密的 "SKILLMINT_OK" token 验证用户名
代码位置: packages/skillpack-rs/src/crypto.rs
2. SkillPack 格式
.skillpack 文件是 ZIP 压缩包:
myskill.skillpack
├── manifest.json # 明文(id, name, version, username_hint, encrypted_verify)
├── icon.png # 明文(可选)
└── encrypted/ # AES-256-GCM 加密文件
├── SKILL.md.enc
├── templates/*.md.enc
└── examples/*.md.enc
打包: packages/skillpack-rs/src/pack.rs
解包: packages/skillpack-rs/src/unpack.rs
3. 多模型系统(双协议架构)
所有 LLM 交互通过两种适配器格式:
Anthropic Messages API (adapters/anthropic.rs):
- 原生支持:Claude 模型
- 兼容:MiniMax Anthropic 端点
OpenAI 兼容 API (adapters/openai.rs):
- 原生支持:OpenAI GPT 模型
- 兼容:DeepSeek, Qwen, MiniMax, Moonshot, Yi
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 · 633 lines · 6,403 tokens per session scan A 13a8aacc5257
WorkClaw CLAUDE.md is an instructions file published in the GitHub repository haojing8312/WorkClaw (140 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 6,403 tokens to every session, about $0.0320 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 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.