What is Lingxi CLAUDE.md?

Project instructions for Lingxi, a multi-agent software engineering framework that coordinates several AI agents to resolve software issues. They cover the project overview, setup, environment variables, development commands, and code-quality checks.

Use them when installing dependencies, configuring API keys, starting the development environment, linting, or formatting Lingxi.

They give an AI coding agent the repository context and commands needed to work on the project consistently.

How lingxi-agent/Lingxi configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lingxi-agent/Lingxi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lingxi-agent/Lingxi/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lingxi-agent/Lingxi

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lingxi-agent/lingxi/claude-md/github.svg)](https://agentmods.dev/instructions/lingxi-agent/lingxi/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lingxi-agent/lingxi/claude-md"><img src="https://agentmods.dev/badge/instructions/lingxi-agent/lingxi/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lingxi-agent/lingxi/claude-md"><img src="https://agentmods.dev/badge/instructions/lingxi-agent/lingxi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,328 This file is loaded in full into every session.

When invoked 1,328 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01328	$0.01328
Opus 5.5	$0.00531	$0.00531
Sonnet 5.5	$0.00266	$0.00266
Haiku 4.5	$0.00133	$0.00133

Measured 2mo ago against content hash 3caeec917b85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Lingxi 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 2mo 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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 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.

Project Overview

Lingxi is a multi-agent software engineering framework that automates issue resolution using LangGraph workflows. It achieved 74.6% success on SWE-Bench Verified. The system uses specialized agents (Problem Decoder, Solution Mapper, Problem Solver) that coordinate through a supervisor to analyze GitHub issues and generate code fixes.

Development Commands

Environment Setup

# Install dependencies
pip install -e .

# Or using uv (recommended)
uv run --env-file .env [command]

Required Environment Variables

Create a .env file in the project root with:

LLM_PROVIDER=anthropic  # or "openai", "deepseek"
LLM_MODEL=claude-3-5-haiku-latest
ANTHROPIC_API_KEY=your_key_here  # or OPENAI_API_KEY, DEEPSEEK_API_KEY
OPENAI_API_KEY=your_key_here     # Required for embeddings
GITHUB_TOKEN=your_token_here     # For GitHub API access

Running the Application

# Start LangGraph Studio
langgraph dev --no-reload

# Or with uv
uv run --env-file .env langgraph dev --no-reload

Code Quality

# Linting with ruff
ruff check src/
ruff format src/

# Type checking
mypy src/

Testing

pytest

Architecture Overview

Core Components

LangGraph Workflows: Two main graph implementations in src/agent/:

supervisor_graph_demo.py: Primary issue resolution workflow with supervisor coordination
hierarchy_graph_demo.py: Extended workflow with multi-agent manager and reviewer

Agent System: Five specialized agents with distinct roles:

Supervisor: Routes workflow between agents based on progress
Problem Decoder: Analyzes issues and performs bug localization using [view_directory, search_relevant_files, view_file_content]
Solution Mapper: Creates detailed code change plans using [view_directory, search_relevant_files, view_file_content]
Problem Solver: Implements code changes using [view_directory, search_relevant_files, str_replace_editor]
Multi-Agent Manager: Coordinates between issue resolver and reviewer (hierarchy graph only)
Reviewer: Validates fixes and runs tests using [view_directory, search_relevant_files, view_file_content, run_shell_cmd]

Read the full file on GitHub · 152 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.

2mo ago First seen · 152 lines · 1,328 tokens per session scan A 3caeec917b85

Subscribe to this mod's changes

Lingxi CLAUDE.md is an instructions file published in the GitHub repository lingxi-agent/Lingxi (258 stars, last pushed 7mo ago), licensed MIT. It adds 1,328 tokens to every session, about $0.0053 per session on Opus 5.5. 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.

Lingxi CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Lingxi CLAUDE.mdlingxi-agent/Lingxi	Instructions file	258	7mo ago	MIT	A	1,328	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

Lingxi: Instructions file for Claude Code