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/superman1006/meetmind/claude-mdgit clone --depth 1 https://github.com/superman1006/MeetMindWrote 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/superman1006/meetmind/claude-md)<a href="https://agentmods.dev/instructions/superman1006/meetmind/claude-md"><img src="https://agentmods.dev/badge/instructions/superman1006/meetmind/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 | $0.07403 | $0.07403 |
| Opus 5 | $0.03701 | $0.03701 |
| Sonnet 5 | $0.01481 | $0.01481 |
| Haiku 4.5 | $0.00740 | $0.00740 |
Grade A, and why
MeetMind 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
MeetMind 是一个多 Agent RAG 协作系统的 demo(TypeScript 项目,monorepo:apps/runtime 后端 + apps/desktop 前端):5 个角色 Agent(架构师、后端、前端、测试、产品经理)围绕一个项目需求展开讨论。架构师作为入口和终止者,其他角色在 LangGraph 条件边的驱动下自由路由。每个 Agent 拥有独立的 PostgreSQL 表 + 私有 RAG 工具(PostgreSQL 混合检索:pgvector 向量 kNN + pg_trgm 关键字召回,再过 本地 cross-encoder rerank)。存储已从 Elasticsearch 迁移到 PostgreSQL(pgvector)。
LLM 通过 OpenAI 兼容协议调用(默认配置小米 MiMo),所以 new ChatOpenAI({...}) 里有一个 modelKwargs: { thinking: { type: "disabled" } }(给后端关掉 thinking 模式)不能改。
常用命令
包管理用 pnpm,不要用 npm / yarn。运行用 tsx 直接跑 .ts,开发期不需要预编译。
# 第一次(或换机)启动:
docker compose up -d # 起本地单节点 PostgreSQL+pgvector (pgvector/pgvector:pg17, 宿主机端口 5433)
pnpm install # 安装依赖(无 torch;主要是 onnxruntime + langchain + pg,首次较慢)
pnpm dev # tsx src/index.ts 启动 CLI
pnpm start # 同上
# 生产 / 编译:
pnpm build # tsc 编译到 dist/
pnpm start:prod # node dist/index.js
pnpm typecheck # tsc --noEmit,只做类型检查
# 重置某个 agent 的 PostgreSQL 表并重灌(开发时常用)
pnpm exec tsx -e "import('./src/database/ingestion/initializer.ts').then(m => m.resetAgentDb('backend'))"
# 完全抹库后重灌(删 docker volume,下次启动重新建表 + 灌种子)
docker compose down -v && docker compose up -d
环境变量在 .env(参考 .env.example):LLM 三件套 API_KEY / BASE_URL / MODEL_NAME 是调用 LLM 的必需项;PG_URL 默认 postgresql://meetmind:meetmind@localhost:5433/meetmind(宿主机 5432 常被本地原生 postgres 占用,docker-compose 把容器映射到 5433 避让)。rerank 已改为本地 cross-encoder,不再需要 COHERE_API_KEY。 启动时唯一的硬退出是 pingDb() 失败(process.exit(1));LLM 的 key/baseUrl 缺失不会在启动时被拦截,会在第一次调用模型时抛错(zod 对这些字段给空字符串默认值,不报错)。
高层架构
调用链一句话
src/index.ts (load dotenv) → bootstrap() → buildGraph() → startServer(3002) ← 默认入口(HTTP/SSE 服务)
↓
POST /api → handleRpc → chat.send → runExecution(graph, …) → graph.stream(["custom","values"], thread_id)
↓
START → rewrite_node → intent_node → route_node ──┬─► assistant_node → END (右侧回答助手)
└─► architect_node → … 团队 (左侧 5 角色协作)
↓
createNode(agent) 闭包 → agent.invoke()(Phase1 工具循环 + Phase2 结构化收尾)
↓
routeToWhichAgent(state) → 下一个 _node 或 END
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 · 146 lines · 7,403 tokens per session scan A b2df309f0bd5
MeetMind CLAUDE.md is an instructions file published in the GitHub repository superman1006/MeetMind (57 stars, last pushed 2mo ago), licensed MIT. It adds 7,403 tokens to every session, about $0.0370 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.