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/fattail4477/claw-decode/claude-mdgit clone --depth 1 https://github.com/fattail4477/claw-decodeWrote 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/fattail4477/claw-decode/claude-md)<a href="https://agentmods.dev/instructions/fattail4477/claw-decode/claude-md"><img src="https://agentmods.dev/badge/instructions/fattail4477/claw-decode/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 | $0.00763 | $0.00763 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
claw-decode 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.
What it actually says
CLAUDE.md — Project Context
项目定位
Claw Decode = Claude Code 的 X 光片。
一个网页体验，让任何人（不只是开发者）在 30 秒内看完 Claude Code 内部最惊人的发现。
一句话："Anthropic 不想让你看到的，都在这一页里。"
目标：可传播的体验，不是文档。 视觉冲击力 > 文字深度。
项目信息
- Repo: https://github.com/fattail4477/claw-decode
- Author: Avery Chai (@chatoliciuh)
- GitHub Pages: 需要做，是最高优先级
泄露源码位置
~/Desktop/claw-decode-sources/hangsman/src/
关键文件：
src/constants/prompts.ts— 主系统提示词 (914行)src/tools/*/prompt.ts— 各工具提示词src/buddy/sprites.ts— ASCII 宠物动画帧（18种生物）src/buddy/types.ts— 宠物稀有度系统src/buddy/prompt.ts— 宠物 promptsrc/tasks/DreamTask/DreamTask.ts— 做梦模式src/services/autoDream/consolidationPrompt.ts— 记忆整合提示词src/utils/undercover.ts— 卧底模式src/constants/cyberRiskInstruction.ts— 安全指令
已完成
- ✅ README.md — "10 Biggest Secrets" 格式
- ✅ 完整系统提示词重建 (prompts/FULL_SYSTEM_PROMPT.md)
- ✅ 速查表 (CHEATSHEET.md)
- ✅ 7篇隐藏功能分析 (hidden-features/)
- ✅ 40个工具定义 (tool-definitions/)
- ✅ 架构图 (architecture/)
- ✅ 实操指南 (guides/steal-these-patterns.md)
- ✅ Logo + GitHub Sponsors
最高优先级：GitHub Pages 网站
在 /docs 文件夹做一个单页网站：
设计要求：
- 暗黑主题，视觉冲击力强
- 打开 3 秒内要 "哇"
- ASCII 宠物 sprite 要能动画播放（从 sprites.ts 提取）
- 10 大秘密做成卡片，带动画
- 内部版 vs 外部版对比区域
- 43 个工具做成可搜索列表
- 好的 Open Graph meta tags（分享时好看）
- 用原生 HTML/CSS/JS，不要框架
- 适配手机
内容来源：
- README.md 的 10 Biggest Secrets
- CHEATSHEET.md 的工具列表
- hidden-features/ 的详细分析
- prompts/FULL_SYSTEM_PROMPT.md 的 prompt 内容
- 源码 sprites.ts 的 ASCII art
其他待做
- usable/ — 可直接用在 Claude Code 里的资产（CLAUDE.md 模板、agent 配置等）
- comparisons/ — vs Cursor/Copilot/Cline 架构对比
- 更多工具的完整 prompt 原文
规则
- 不要直接复制源码文件到 repo
- 小片段引用（<10行）用于分析是 OK 的（fair use）
- 每次改完都要 commit + push：
git add -A && git commit -m "描述" && git push
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 · 81 lines · 763 tokens per session scan A e2b25ac32acf
claw-decode CLAUDE.md is an instructions file published in the GitHub repository fattail4477/claw-decode (56 stars, last pushed 5mo ago), licensed MIT. It adds 763 tokens to every session, about $0.0038 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.