Feagent CLAUDE.md

Feagent CLAUDE.md is an instructions file for coding agents from DSGWJQ/Feagent. It costs 6,560 tokens per session, scanned A, original, MIT.

A project guide for Feagent, an enterprise platform for coordinating and running AI agents. It describes the system's architecture, collaboration between Claude and Codex, and development rules.

In plain words
What is it for?
It guides feature work, architecture decisions, agent collaboration, and testing in the Feagent codebase.
Why use it?
It gives coding agents the project's structure and working agreements, including limits on file changes and test-first development.

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/dsgwjq/feagent/claude-md
Clone the repo
git clone --depth 1 https://github.com/DSGWJQ/Feagent

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 Feagent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dsgwjq/feagent/claude-md.svg)](https://agentmods.dev/instructions/dsgwjq/feagent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dsgwjq/feagent/claude-md"><img src="https://agentmods.dev/badge/instructions/dsgwjq/feagent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,560 This file is loaded in full into every session.
When invoked 6,560 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 $0.06560 $0.06560
Opus 5 $0.03280 $0.03280
Sonnet 5 $0.01312 $0.01312
Haiku 4.5 $0.00656 $0.00656

Measured 5d ago against content hash f20fa007a6bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Feagent 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.

CLAUDE.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 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

Feagent 是企业级AI Agent编排与执行平台,基于 FastAPI + LangChain + DDD-lite 架构。

当前阶段: 多Agent协作系统(Phase 8+ - Unified Definition System)

  • 三Agent架构:CoordinatorAgent、ConversationAgent、WorkflowAgent
  • EventBus事件驱动通信
  • 八段压缩器(PowerCompressor)
  • WebSocket实时通道
  • 可配置规则引擎与干预系统
  • 自描述节点验证与依赖图

Claude ↔ Codex 协作工作流(精简版)

  1. 需求理解 → Claude 快速识别疑问 → Codex 深度推理
  2. 上下文收集 → Codex 全面检索 → 输出分析报告
  3. 任务规划 → Claude 基于分析制定计划
  4. 代码执行 → Claude 直接编码(遇复杂逻辑调用 Codex)
  5. 质量审查 → Codex 深度审查 → Claude 最终决策

角色分工 / 产出

  • Claude:提炼问题、制定计划、落地代码与决策
  • Codex:深度推理/检索、给出代码原型(统一 diff 参考)、质量审查
  • 产出物:分析报告 → 计划 → 代码原型参考 → 落地实现 → Codex Review 意见 → Claude 采纳/决策

与现有规则/架构的对齐

  • 对应“架构顺序”:需求分析→Domain→Ports→Infrastructure→Application→Interface;在 Domain/Ports 阶段优先让 Codex 做深推与检索。
  • 代码执行阶段继续遵守“每次最多改 2 个文件 + TDD”与命名约定。
  • 前端/后端改动时保持原有项目结构;Codex 仅给出参考 patch,真实修改由 Claude 完成。
  • 关于 Codex 详细调用规范与合作要求,沿用文末《Core Instruction for CodeX MCP》与《Codex Tool Invocation Specification》。

关键规则(必读)

开发约束

  1. 开发节奏:每次最多修改2个文件,等待用户确认后继续

  2. TDD强制:Red → Green → Refactor

    • Domain层覆盖率 ≥ 80%
    • Application层覆盖率 ≥ 70%
  3. 架构顺序(严格)

    需求分析 → Domain → Ports → Infrastructure → Application → Interface
    
  4. 依赖方向(单向)

    Interface → Application → Domain ← Infrastructure
    

    Domain层禁止导入: SQLAlchemy、FastAPI、LangChain 或任何框架

命名约定

模式 含义 示例
get_xxx 必须存在,否则抛异常 get_agent(id)
find_xxx 允许返回None find_agent(id)
XxxUseCase 应用层用例 CreateAgentUseCase
XxxInput/Request/Response DTO CreateAgentInput

开发命令

后端

# 安装依赖
pip install -e ".[dev]"

# 数据库迁移
alembic upgrade head
alembic revision --autogenerate -m "description"

# 启动服务器(Windows 必须使用 python -m)
python -m uvicorn src.interfaces.api.main:app --reload --port 8000

# 测试
pytest                                              # 全部测试
pytest tests/unit                                   # 单元测试
pytest tests/integration                            # 集成测试
pytest tests/unit/domain/entities/test_agent.py -v # 单个文件
pytest -k "test_create_agent"                       # 按名称

# 代码质量
ruff check .                             # Lint
ruff format .                            # Format
pyright src/                             # 类型检查

Read the full file on GitHub · 591 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. 5d ago First seen · 591 lines · 6,560 tokens per session scan A f20fa007a6bc

Subscribe to this mod's changes

Feagent CLAUDE.md is an instructions file published in the GitHub repository DSGWJQ/Feagent (139 stars, last pushed 7mo ago), licensed MIT. It adds 6,560 tokens to every session, about $0.0328 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens