building-autonomous-team-init

building-autonomous-team-init is a skill for Claude Code, Codex from fengjunhui31/building-autonomous-team. It costs 33 tokens per session (3,039 once invoked), scanned B, original, MIT.

A skill for creating a self-directed project team with two permanent agents and additional members that can be added as needed. GitHub is used as the team's shared record of work.

In plain words
What is it for?
Use it to set up a project team with a team lead and project manager, dynamically assign other agents, and manage work through GitHub.
Why use it?
It provides a team structure that can continue generating and handling work when the task queue is empty. It also avoids relying on local state files to remember team progress.

Skill for Claude CodeCodex

Part of the building-autonomous-team plugin — 3 skills, 1 command, 12 agents, 1 hook shipped together

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 skills/fengjunhui31/building-autonomous-team/init
Any agent
npx skills add fengjunhui31/building-autonomous-team --skill init
Clone the repo
git clone --depth 1 https://github.com/fengjunhui31/building-autonomous-team

Made for: Claude Code, Codex.

Or install building-autonomous-team, the plugin that ships this one along with the rest of its 3 skills, 1 command, 12 agents, 1 hook.

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 building-autonomous-team-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/fengjunhui31/building-autonomous-team/init.svg)](https://agentmods.dev/skills/fengjunhui31/building-autonomous-team/init)
Your own site
<a href="https://agentmods.dev/skills/fengjunhui31/building-autonomous-team/init"><img src="https://agentmods.dev/badge/skills/fengjunhui31/building-autonomous-team/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,039 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00033 $0.03039
Opus 5 $0.00016 $0.01520
Sonnet 5 $0.00007 $0.00608
Haiku 4.5 $0.00003 $0.00304

Measured 4d ago against content hash 347bd2307b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

building-autonomous-team-init scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/settings.json | grep "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"
plugins/building-autonomous-team/skills/init/SKILL.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Team Creation Skill (v2.0)

Executed when user invokes /building-autonomous-team and target project has no .autonomous-team/ directory

Overview

Create a mission-driven autonomous team with 2 persistent agents (Team Lead + Project Manager) and Team Lead-managed dynamic members.

Core Changes from v1:

  • Only 2 persistent agents (was 9)
  • GitHub is the only state source (no local state files)
  • Mission-driven: team self-generates work when queue is empty
  • Event-driven: no sleep/blocking, heartbeat fallback
  • Language configurable
  • Team Lead is sole spawner: all dynamic agents spawned as team members by Team Lead, communicate via SendMessage — no sub-agent context pollution

Step 0: Pre-check

0.1 Check Environment Variable

cat ~/.claude/settings.json | grep "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"
  • ✅ Found → Continue
  • ❌ Not found → Block, prompt to add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS: "1" to settings.json

0.2 Check GitHub CLI and Repo Features

gh --version && gh auth status
gh repo view --json hasDiscussionsEnabled,nameWithOwner
  • ❌ gh not installed → Block: brew install gh
  • ❌ Not authenticated → Block: gh auth login
  • ❌ Discussions not enabled → Block: enable in repo Settings → Features → Discussions
  • ❌ No remote → Block: create repo and push

0.3 Verify Executor Worktree Hook

Plugin hook auto-loaded from hooks/hooks.json. Verify it's active.

0.4 Check Git

git rev-parse --is-inside-work-tree 2>/dev/null || echo "GIT_NOT_INIT"
  • ❌ Not initialized → git init + .gitignore + initial commit

0.5 Explore Target Project

Use Explore agent to investigate:

  • Tech stack, code size, modules
  • GitHub remote, repo name
  • Existing docs (CLAUDE.md, README)
  • Whether .autonomous-team/ exists

Step 1: Language and Constitution

1.1 Language Configuration

Check if language was provided as argument (second parameter to /building-autonomous-team).

Read the full file on GitHub · 393 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 · 393 lines · 33 tokens per session scan B 347bd2307b21

Subscribe to this mod's changes

building-autonomous-team-init is a skill published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 3,039 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

agile-product-owner

../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

subagent-delegation

Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.

toonight/get-shit-done-for-antigravity · 42 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

project-init

Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…

BlackBeltTechnology/pi-agent-dashboard · 81 tokens