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/jerrylalala/compound-engineering/claude-mdgit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWrote 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/jerrylalala/compound-engineering/claude-md)<a href="https://agentmods.dev/instructions/jerrylalala/compound-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/jerrylalala/compound-engineering/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 | $0.04229 | $0.04229 |
| Opus 5 | $0.02115 | $0.02115 |
| Sonnet 5 | $0.00846 | $0.00846 |
| Haiku 4.5 | $0.00423 | $0.00423 |
Grade A, and why
compound-engineering 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 5d 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compound Engineering Plugin
本仓库基于 compound-engineering-plugin 独立开发，包含中文化、本地扩展和私有覆盖层。 本文件是兼容入口；仓库权威规则以
AGENTS.md为准。若本文件与AGENTS.md冲突，遵循AGENTS.md。
公共仓库维护标准（最高优先级）
本仓库按公共开源项目 Jerrylalala/compound-engineering 长期维护。后续所有改动都按“陌生用户能安装、能理解、能信任、能贡献”的标准处理，而不是按个人私有工作区或 Claude Code-only 项目处理。
- 定位：对外表述为多工具 workflow assets + converter/install CLI。Claude Code 是重要兼容面，但不是唯一主线。
- 稳定性：公开宣称可用前必须有新鲜验证证据；涉及 CLI/转换器运行
bun test，涉及 release/manifest 运行bun run release:validate，涉及文档站运行mkdocs build --strict。 - 社区健康：维护
LICENSE、SECURITY.md、PRIVACY.md、CONTRIBUTING.md、CODE_OF_CONDUCT.md、SUPPORT.md、issue templates、PR template。漏洞报告入口必须指向当前项目维护方，不能默认指向上游作者。 - 文档架构：
README.md是公共第一入口；docs/zh-CN/是用户文档站；docs/specs/是平台协议；docs/brainstorms/、docs/plans/是历史和规划记录；docs/solutions/是知识库，不当作清理对象。 - 兼容策略：保留 Claude Code 兼容，但不让 Claude-only 假设污染 Codex/Gemini/OpenCode 等目标。旧
workflows:*名称若只剩历史意义，必须标为 deprecated 或从用户文档移除。 - 版本策略：公共 release 由自动化管理；常规 PR 不手动 bump release-owned version，不手写新 release notes。发现 drift 时优先修 release metadata/sync 机制。
- 规则更新：用户只要求更新规则时，直接改规则文件，不主动 commit；后续产品代码、文档和 CI 改进另开实现任务。
AI 助手快速入门
仓库定位
本仓库 = 上游灵感参考 + 中文化层 + 本地扩展（Harness Fusion 覆盖层）
| 角色 | 仓库 | 说明 |
|---|---|---|
| 参考上游 | EveryInc/compound-engineering-plugin | 参考方向，不强制同步 |
| 本仓库 | Jerrylalala/compound-engineering | 独立维护的主仓库 |
核心原则
- 可修改所有文件 - 英文文档和中文文档都可以修改
- 本地扩展隔离 -
skills-custom/存放自定义技能 - 同步上游时注意冲突 - 见
docs/zh-CN/SYNC.md
本项目的特殊性
本项目是胶水编程的元层：创建编排组件本身。
- 全局规则：见
~/.claude/CLAUDE.md的"胶水编程思维"（默认生效） - 本项目例外：创建新 Skill/Agent/Command 时，不需要搜索 GitHub 现成库
- 因为本项目的工作就是创建编排组件（Skills/Agents/Commands）
- 但组件内部仍应遵循胶水编程（调用 git/gh/Codex，而非重写）
- 完整工作流：需要架构规划时使用
/glue-coding技能
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.
- 5d ago First seen · 355 lines · 4,229 tokens per session scan A 326f4c8228fa
compound-engineering CLAUDE.md is an instructions file published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 4,229 tokens to every session, about $0.0211 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 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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.