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/harryyangthu/mars-multi-agent-research-system/agents-mdgit clone --depth 1 https://github.com/HarryYangthu/MARS-Multi-Agent-Research-SystemWrote 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/harryyangthu/mars-multi-agent-research-system/agents-md)<a href="https://agentmods.dev/instructions/harryyangthu/mars-multi-agent-research-system/agents-md"><img src="https://agentmods.dev/badge/instructions/harryyangthu/mars-multi-agent-research-system/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 | $0.02261 | $0.02261 |
| Opus 5 | $0.01130 | $0.01130 |
| Sonnet 5 | $0.00452 | $0.00452 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
MARS-Multi-Agent-Research-System 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- MARS-Multi-Agent-Research-System CLAUDE.md — 91% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
这是 MARS 项目的 AGENTS.md。Codex / Codex / Cowork 在 session 启动时自动加载。 控制在 200 行内,只放硬约束 + 目录结构 + 风格规范。详细 Why / What / How 看
PRODUCT.md/DESIGN.md/ACCEPTANCE.md。
项目一句话定义
MARS = 研究型多 Agent 系统的底座(Multi-Agent Research System)。
首个项目:projects/pimc/ — PIMC for FDD Massive MIMO under beam/layer switching。
技术栈
- 后端:Python 3.11 / FastAPI / python-socketio / asyncio / Redis
- 前端:Next.js 15 / Tailwind / shadcn/ui / Socket.IO 客户端
- Agent 编排:LangGraph(V0 默认实现,但 BaseAgent 接口不绑死,可替换)
- 知识库:ChromaDB(4 个独立 collection)
- LLM Backends:Anthropic / OpenAI / Qwen / Gemini API + 本地 vLLM serve
- 部署:Docker Compose,单机 4 × NVIDIA L40S
目录结构(强约束)
mars/
├─ AGENTS.md / PRODUCT.md / DESIGN.md / ACCEPTANCE.md / README.md
├─ pyproject.toml / docker-compose.yml / .env.example
├─ configs/ # 全局配置
│ ├─ agents.yaml # 5 Agent 各自的 model / debate / tools 配置
│ ├─ models.yaml # LLM provider 注册
│ ├─ tools.yaml # 工具开关与权限
│ ├─ gates.yaml # 5 个 HITL Gate 阈值
│ ├─ knowledge.yaml # 4 区 KB embedding / chunk 配置
│ └─ execution.yaml # GPU 调度 / 并发上限
│
├─ backend/app/
│ ├─ api/ # FastAPI routes(按资源拆分)+ websocket
│ ├─ bridge/ # 产品编排层 — 知道有哪些 Agent
│ ├─ harness/ # Agent-agnostic 可信机制 — 不知道任何具体 Agent
│ │ ├─ runtime/ # RunGraph / state_machine / queue / event_bus
│ │ ├─ schema/ # frontmatter_parser / validator + 5 个 JSON Schema
│ │ ├─ tools/ # 5 类 tool 注册中心(Gate 5 hook 在此)
│ │ ├─ gates/ # 5 个系统 HITL Gate
│ │ ├─ context/ # 3 层装载 + Manifest + 压缩
│ │ ├─ llm/ # 多 backend 抽象 + post_training_loader
│ │ ├─ kb/ # 4 区 ChromaDB client
│ │ └─ sedimentation/ # 每 Agent 完成后的沉淀 hook
│ ├─ agents/ # 5 Agent + debate 子模块
│ ├─ hitl/ # 高频人工交互(review / diff / approval / audit)
│ ├─ execution/ # 仿真运行(simulation_runner / log_streamer / metrics)
│ ├─ storage/ # 数据访问层(run_store / artifact_store / file_store)
│ └─ workers/ # 异步后台(agent_worker / simulation_worker / heartbeat)
│
├─ frontend/ # Next.js 工作台
├─ workspace/repos/ # 接入真实研究代码仓(submodule / 软链接 / 镜像)
├─ workspace/uploads/ # 上传论文 / 文档 / 数据
├─ knowledge/ # 4 区 KB 物理文件(literature/methodology/code_assets/run_archive)
├─ runs/<timestamp>_<task>/ # 每次任务完整沉淀
├─ templates/ # prompts / artifacts / reports / code_rules
├─ projects/pimc/ # 项目元数据 + AGENTS.md + repo_link.yaml + data_gen.py
├─ posttrain/ # V2 占位
├─ docs/ # 补充文档
└─ scripts/ # dev.sh / run_agent.py / index_repo.py
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 · 113 lines · 2,261 tokens per session scan A 17f660dc9143
MARS-Multi-Agent-Research-System AGENTS.md is an instructions file published in the GitHub repository HarryYangthu/MARS-Multi-Agent-Research-System (450 stars, last pushed 2d ago), licensed MIT. It adds 2,261 tokens to every session, about $0.0113 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).
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.