MultiGen CLAUDE.md

MultiGen CLAUDE.md is an instructions file for coding agents from lingyuanli/MultiGen. It costs 1,388 tokens per session, scanned A, original, MIT.

A repository guide for MultiGen, a privately deployable AI-agent system. It describes the web interface, API, databases, task queue, isolated Docker sandbox, and two-agent process that plans and carries out requests.

In plain words
What is it for?
Use it when developing MultiGen's frontend, API, agent execution flow, event streaming, or Docker-based sandbox.
Why use it?
It gives coding agents a map of how messages move through the system and where each service or agent fits.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/lingyuanli/multigen/claude-md
Clone the repo
git clone --depth 1 https://github.com/lingyuanli/MultiGen

Wrote 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.

agentmods badge for MultiGen CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lingyuanli/multigen/claude-md.svg)](https://agentmods.dev/instructions/lingyuanli/multigen/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lingyuanli/multigen/claude-md"><img src="https://agentmods.dev/badge/instructions/lingyuanli/multigen/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,388 This file is loaded in full into every session.
When invoked 1,388 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01388 $0.01388
Opus 5 $0.00694 $0.00694
Sonnet 5 $0.00278 $0.00278
Haiku 4.5 $0.00139 $0.00139

Measured 4d ago against content hash 11c14d2c1000, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MultiGen 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 4d 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.

CLAUDE.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 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.

Overview

MultiGen is a general-purpose AI Agent system for fully private deployments. It uses a Planner + ReAct multi-agent architecture with A2A (Agent-to-Agent) and MCP (Model Context Protocol) tool connectivity, and executes operations inside an isolated Docker sandbox.

Architecture

Next.js UI (3000) → FastAPI API (8000) → PostgreSQL / Redis / Tencent COS
                                        ↓
                               Docker Sandbox (8080)
                               Ubuntu + Chrome + VNC

Agent execution flow:

  1. AgentService (application layer) receives a chat message and dispatches it to an AgentTaskRunner via a Redis Stream task queue.
  2. AgentTaskRunner runs PlannerReActFlow, which coordinates two agents:
    • PlannerAgent — breaks the user request into sub-steps (JSON output, no tool calls)
    • ReActAgent — iteratively executes each step using tools, then summarizes
  3. Events are streamed back to the frontend via SSE (/api/sessions/{id}/chat).

Event types (discriminated union in app/domain/models/event.py): plan, title, step, message, tool, wait, error, done.

Tools available to agents (app/domain/services/tools/): file, shell, browser, search, message (ask_user), image_generation, volcano_image, volcano_video, video_concatenation, model_3d, virtual_anchor, qwen_tts, audio_mixing, mcp, a2a.

LLM abstraction: app/domain/external/llm.py defines a Protocol. The only implementation is OpenAILLM (app/infrastructure/external/llm/openai_llm.py), which supports any OpenAI-compatible endpoint (DeepSeek, Volcengine, SiliconFlow, etc.).

DeepSeek thinking models: Models whose names start with deepseek-v4 are treated as reasoning models. When tool calls are present in a turn, reasoning_content must be included in subsequent history; when there are no tool calls, it is passthrough-safe. The codebase handles both cases with a compatibility guard in BaseAgent.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 4d ago First seen · 127 lines · 1,388 tokens per session scan A 11c14d2c1000

Subscribe to this mod's changes

MultiGen CLAUDE.md is an instructions file published in the GitHub repository lingyuanli/MultiGen (401 stars, last pushed 1mo ago), licensed MIT. It adds 1,388 tokens to every session, about $0.0069 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.