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/codestable/cs-agent-mcp/agents-mdgit clone --depth 1 https://github.com/codestable/cs-agent-mcpWhat 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 | $0.00662 | $0.00662 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
cs-agent-mcp 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 yesterday.
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
AGENTS.md
本仓库发布 npm 包 cs-agent-mcp，提供本地多 Agent stdio MCP 服务。
范围
- 面向用户的唯一命令是
cs-agent-mcp。 - 无参数时必须直接启动 stdio MCP，不增加交互式输出。
- Codex、Claude 等受管 Agent 通过 ACP adapter 启动。
- 不依赖 npm 包
acpx；当前仓库自带所需 ACP runtime 和 MCP Facade 实现。 - 用户文档统一使用中文，只描述安装、配置、启动和 MCP 能力。
环境
- Node.js
>=22.13.0 - pnpm
10.34.5
pnpm install
开发
从源码启动：
pnpm run dev -- --cwd /absolute/path/to/workspace
构建并检查命令：
pnpm run build
node dist/mcp-cli.js --help
关键实现：
src/mcp-cli.ts：npm binary 与 stdio MCP 入口。src/mcp/transport/：stdio/loopback HTTP transport、workspace roots 和进程锁。src/mcp/facade/：Agent、Turn、Message、Permission、Event 和递归委派状态机。src/mcp/runtime-adapter.ts：Facade 到 ACP runtime 的适配。src/runtime/、src/acp/：ACP 会话、Agent 进程、恢复和权限处理。test/mcp-cli.test.ts、test/mcp-e2e.test.ts：公开入口和 15 个工具的 E2E。
验证
修改代码、配置、CLI、状态格式或文档后运行：
pnpm run check
发布前还要用 npm pack 生成的 tarball 做临时安装，并通过 MCP SDK 验证 15 个工具。
涉及 Codex/Claude 启动时，应在本机登录状态下各跑一次真实调用；涉及递归委派时，至少验证
Claude 创建 Codex 子 Agent 或反向等价链路。
持久化与兼容性
- 用户配置：
~/.cs-agent-mcp/config.json - 项目配置：
<cwd>/.cs-agent-mcprc.json - MCP 与会话状态：
~/.cs-agent-mcp/ - Facade snapshot schema：
cs-agent-mcp.facade.v1
工具名、输入字段、结构化输出、错误码、状态枚举和持久化 schema 都属于公开契约。修改时必须 同步 README、回归测试和 CHANGELOG，不能静默替换无法恢复的持久会话。
发布
版本来自 package.json。tag 必须为完全匹配的 vX.Y.Z，且 tagged commit 已位于 main。
GitHub Actions 使用 npm trusted publishing 发布 cs-agent-mcp；不得把 npm token 写入仓库。
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.
- yesterday First seen · 72 lines · 662 tokens per session scan A fb1c25c17a15
cs-agent-mcp AGENTS.md is an instructions file published in the GitHub repository codestable/cs-agent-mcp (1 stars, last pushed 11d ago), licensed MIT. It adds 662 tokens to every session, about $0.0033 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.