What is pi-crew CLAUDE.md?

Repository instructions for pi-crew, a Pi extension that coordinates teams of AI agents. They describe its three layers: the extension interface, the workflow runtime, and durable saved state.

Use them when working on pi-crew features such as team tools, task scheduling, child-agent execution, worktree isolation, state files, and run management.

They give an agent the project structure and important source locations before it changes the repository.

How baphuongna/pi-crew configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to baphuongna/pi-crew. 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/baphuongna/pi-crew/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/baphuongna/pi-crew

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/baphuongna/pi-crew/claude-md.svg)](https://agentmods.dev/instructions/baphuongna/pi-crew/claude-md)

Your own site

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

Per session 1,655 This file is loaded in full into every session.

When invoked 1,655 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	$0.01655	$0.01655
Opus 5	$0.00827	$0.00827
Sonnet 5	$0.00331	$0.00331
Haiku 4.5	$0.00166	$0.00166

Measured 8d ago against content hash 80513c6a0bb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pi-crew 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 8d 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 · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 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.

Repository Overview

This is the pi-crew repository — a Pi extension for multi-agent team orchestration. It coordinates autonomous AI agent teams with durable state, parallel execution, worktree isolation, and safe defaults.

Architecture

Three-Layer Design

Pi extension layer
  register tools, slash commands, widget/dashboard, notifier, lifecycle cleanup

Runtime layer
  team runner, task graph scheduler, child Pi process runner, async runner,
  model fallback, policy engine, worktree manager

State layer
  <crewRoot>/state/runs/{runId}/manifest.json
  <crewRoot>/state/runs/{runId}/tasks.json
  <crewRoot>/state/runs/{runId}/events.jsonl
  <crewRoot>/artifacts/{runId}/...

crewRoot resolves to .crew/ (default) or .pi/teams/ (legacy repos).

Key Source Paths

Path	Purpose
`src/extension/team-tool.ts`	Main tool — 54 schema actions across 5 domain dispatchers (run/status/control/manage/automate); see `src/schema/team-tool-schema.ts:381-432`
`src/runtime/team-runner.ts`	Workflow scheduler, task graph, concurrency control
`src/runtime/task-runner.ts`	Task execution, workspace/worktree context, model selection
`src/runtime/child-pi.ts`	Child Pi process runner — spawns real `pi` workers
`src/runtime/async-runner.ts`	Detached background run spawner
`src/state/`	Durable state/event/artifact store
`src/worktree/`	Worktree creation and cleanup
`src/config/`	Runtime config, resource discovery
`agents/`, `teams/`, `workflows/`	Builtin resources

Tool Actions (28 total)

Action	Purpose
`recommend`	Suggest team/workflow for a goal
`run`	Execute workflow (foreground or async)
`plan`	Preview workflow without executing
`status`	Read run/task status
`summary`	Read/write run summary artifact
`cancel`	Cancel queued/running work
`resume`	Re-queue failed/cancelled/skipped tasks
`list`	List teams, agents, workflows, runs
`get`	Inspect resource details
`events`	Read event log (append-only)
`artifacts`	List run output artifacts
`worktrees`	List run worktree metadata
`cleanup`	Delete run worktrees
`forget`	Delete run state + artifacts
`prune`	Delete multiple old finished runs
`export`	Export portable run bundle
`import` / `imports`	Import/store run bundles
`create` / `update` / `delete`	Manage agents/teams/workflows
`validate`	Validate resources
`doctor`	Environment diagnostics
`config`	Show/update configuration
`init`	Initialize project layout
`autonomy`	Delegation policy management
`api`	State interop for advanced integration
`help`	Display help text

Read the full file on GitHub · 183 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.

8d ago First seen · 183 lines · 1,655 tokens per session scan A 80513c6a0bb9

Subscribe to this mod's changes

pi-crew CLAUDE.md is an instructions file published in the GitHub repository baphuongna/pi-crew (51 stars, last pushed 3d ago), licensed MIT. It adds 1,655 tokens to every session, about $0.0083 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.

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 · 5,153 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

pi-crew: Instructions file for Claude Code