Use it when working on the building-autonomous-team project. It covers team initialization, operation and recovery, version updates, and the roles of persistent and temporary agents.

It gives Claude Code the project context needed to follow the repository's development-team workflow and recover or update it correctly.

How fengjunhui31/building-autonomous-team configures Claude Code

Q: What is building-autonomous-team CLAUDE.md?

A set of Claude Code instructions for a project that creates and operates mission-driven autonomous development teams. It describes the project's structure, architecture, agents, and commands.

Reuse

Borrowing it

Nothing to install: this file belongs to fengjunhui31/building-autonomous-team. 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/fengjunhui31/building-autonomous-team/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fengjunhui31/building-autonomous-team

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/fengjunhui31/building-autonomous-team/claude-md.svg)](https://agentmods.dev/instructions/fengjunhui31/building-autonomous-team/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/fengjunhui31/building-autonomous-team/claude-md"><img src="https://agentmods.dev/badge/instructions/fengjunhui31/building-autonomous-team/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,588 This file is loaded in full into every session.

When invoked 1,588 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	$0.01588	$0.01588
Opus 5	$0.00794	$0.00794
Sonnet 5	$0.00318	$0.00318
Haiku 4.5	$0.00159	$0.00159

Measured 6d ago against content hash 117c17b6b6de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

building-autonomous-team 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 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.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 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

A Claude Code plugin (v2.0.0) that creates mission-driven autonomous development teams. Teams use 2 persistent agents + Team Lead-managed dynamic members, GitHub-only state management, event-driven architecture, and two-round perspective-driven discussions. All dynamic agents are spawned by Team Lead as background team members and communicate via SendMessage (context isolation). The plugin installs into Claude Code's plugin system and runs in the target project (not this repo).

Entry point: /building-autonomous-team [language] command auto-detects init vs operation mode. Optional language argument (e.g. 中文, English).

Repository Structure

plugins/building-autonomous-team/
├── .claude-plugin/plugin.json     # Plugin metadata
├── skills/
│   ├── init/SKILL.md              # Team creation (2 persistent + dynamic)
│   ├── run/SKILL.md               # Operation/recovery (pre-flight + state reconstruction)
│   └── update/SKILL.md            # Version upgrade (v1 → v2 migration)
├── commands/team.md               # Entry command (routes to init/run/update)
├── agents/                        # 11 agent definition files (.md)
├── templates/                     # Files copied to target project's .autonomous-team/
├── hooks/
│   ├── hooks.json                 # PreToolUse hook config
│   └── check-executor-worktree.sh # Blocks executor without isolation: "worktree"
└── knowledge/                     # patterns.md, lessons.md, decisions.md
.claude-plugin/marketplace.json    # Marketplace registry (root level)
docs/v2.0-architecture.md          # Architecture design document

Architecture

Team Lead = main agent (always online, runs /loop) — health monitoring, GitHub scanning, Boss interaction, sole agent spawner. Loop does ONLY monitoring + spawn handling, no project decisions.
Project Manager = persistent opus agent — Discussion queue, consensus orchestration, Spec writing, mission review. Hands off to Impl Coordinator after SPEC_READY.
Impl Coordinator = dynamic per-Discussion — coordinates Executor → Review → merge for ONE Discussion. Terminates after merge.
Boss = human user — interacts via GitHub (Discussions, Issues, comments)

Read the full file on GitHub · 117 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.

6d ago First seen · 117 lines · 1,588 tokens per session scan A 117c17b6b6de

Subscribe to this mod's changes

building-autonomous-team CLAUDE.md is an instructions file published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,588 tokens to every session, about $0.0079 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 2026-08-31.

Building agents

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 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

building-autonomous-team: Instructions file for Claude Code