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/shenjingnan/haimen/agents-mdgit clone --depth 1 https://github.com/shenjingnan/haimenWrote 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/shenjingnan/haimen/agents-md)<a href="https://agentmods.dev/instructions/shenjingnan/haimen/agents-md"><img src="https://agentmods.dev/badge/instructions/shenjingnan/haimen/agents-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 5.1 | $0.02035 | $0.02035 |
| Opus 5 | $0.01018 | $0.01018 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
haimen AGENTS.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 6d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - haimen
本文档为 Claude Code 提供项目上下文和开发规范。
项目概述
haimen 是一个 AI 网关基建 CLI 工具，通过 Connector 架构集成多种消息渠道（飞书/Lark、Telegram 等），通过 Agent 抽象支持多种 AI 后端（Claude Code、MCP 协议等）。
技术栈
| 技术 | 版本 | 用途 |
|---|---|---|
| Rust | 1.85+ | 编程语言 / 编译 / 测试 / Lint / Format |
| clap | 4.x | CLI 参数解析 |
| tokio | 1.x | 异步运行时 |
| serde | 1.x | JSON/TOML 序列化/反序列化 |
| tracing | 0.1 | 日志和诊断 |
| futures-util | 0.3 | 异步流处理 |
| React | 19 | 前端 UI 框架 |
| Vite | 8 | 前端构建工具 |
| Tailwind CSS | 4 | CSS 工具链 |
| Ant Design | 6 | UI 组件库 |
快速命令参考
# 开发
cargo run # 直接运行（无参进入帮助）
cargo run -- config # 显示配置
cargo run -- feishu auth status # 查看飞书认证状态
cargo run -- feishu chat list # 列出飞书群聊
cargo run -- feishu listen # 监听飞书消息
cargo run -- completion bash # 生成 shell 补全
# 安装 pre-commit 钩子（新 clone 后必须执行一次）
npm install -g lefthook # 安装 lefthook
lefthook install # 注册 pre-commit 钩子
# 测试
cargo test # 运行测试
cargo test -- --test-threads=1 # 单线程测试（避免 env 竞争）
# 代码质量
cargo fmt # 格式化代码
cargo fmt --check # 格式检查
cargo clippy # Lint 检查
cargo clippy -- -D warnings # 严格 Lint 检查
cargo fmt --check && cargo clippy -- -D warnings && cargo test # 完整检查
# 构建
cargo build # 调试构建
cargo build --release # 发布构建
# 文档
cargo doc --open # 生成并打开 API 文档
# 前端开发（web-ui/）
cd web-ui && pnpm dev # 启动 Vite 开发服务器（HMR）
cd web-ui && pnpm build # 构建前端产物
cd web-ui && pnpm lint # Biome lint + 自动修复
cd web-ui && pnpm check # Biome CI 严格检查
cd web-ui && pnpm format # Biome 格式化
cd web-ui && pnpm test # Vitest 测试
cd web-ui && pnpm test:watch # Vitest 监听模式
cd web-ui && pnpm storybook # Storybook 组件开发
# 覆盖率
cargo tarpaulin # 生成覆盖率报告
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.
- 6d ago First seen · 178 lines · 2,035 tokens per session scan A 7138fe9b2c22
haimen AGENTS.md is an instructions file published in the GitHub repository shenjingnan/haimen (6 stars, last pushed 5d ago), licensed MIT. It adds 2,035 tokens to every session, about $0.0102 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).
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).
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.
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.
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.