What is playbooks CLAUDE.md?

Repository guidance for Claude Code, covering the Playbooks project's purpose, architecture, and main framework parts. It documents how Playbooks uses Markdown and Python to define workflows for AI agents.

Use it when asking Claude Code to understand, modify, or extend the Playbooks Python framework and its natural-language workflow system.

It gives the coding agent the project context needed to make changes consistently. This reduces guesswork about the framework's design and workflow files.

How playbooks-ai/playbooks configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to playbooks-ai/playbooks. 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/playbooks-ai/playbooks/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/playbooks-ai/playbooks

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/playbooks-ai/playbooks/claude-md/github.svg)](https://agentmods.dev/instructions/playbooks-ai/playbooks/claude-md)

Your own site

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

Per session 2,640 This file is loaded in full into every session.

When invoked 2,640 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	$0.02640	$0.02640
Opus 5	$0.01320	$0.01320
Sonnet 5	$0.00528	$0.00528
Haiku 4.5	$0.00264	$0.00264

Measured 10d ago against content hash e4d71fb9bece, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

playbooks 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 10d 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 · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 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

Playbooks is an innovative Python framework for building and executing AI agents using "playbooks" – structured workflows defined in natural language (via Markdown-based .pb files) or Python code. This framework represents a significant step toward Software 3.0, where natural language becomes a first-class programming language.

Core Architecture

Framework Components

1. Language & Execution

Natural Language Programming: Write workflows in plain English that compile to executable code
Hybrid Execution Stack: Seamless interoperability between Markdown (natural language) and Python execution
Compiler-Driven Reliability: .pb files compile to .pbasm (assembly) format with semantic static analysis

2. Agent System

Multi-Agent Architecture: Built-in support for distributed agents with communication protocols
Agent Types: Local AI agents, remote AI agents, human agents, MCP agents, system agents
Agent Registry: Dynamic agent discovery and integration capabilities

3. Execution Engine

Program Class: Core execution orchestrator managing playbook lifecycle
Event-Driven Architecture: Reactive programming with triggers and event bus
Call Stack Management: Unified call stack for both natural language and Python execution

Key Architectural Insights

Compilation Pipeline

The compilation flow from .pb → .pbasm involves:

Loader (loader.py) reads and validates playbook files
Compiler (compiler.py) uses LLM to preprocess content, adding line type codes (QUE, CND, etc.)
AST Generation (markdown_to_ast.py) converts compiled content to executable structure
Program (program.py) orchestrates execution using the compiled AST

Agent Threading Model

Migrated from threading to pure async/await architecture (AsyncAgentRuntime in program.py)
Each agent runs as an independent asyncio task
Message passing between agents is handled through the event bus
Agent lifecycle managed through start_agent() and stop_agent() methods

Read the full file on GitHub · 372 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.

10d ago First seen · 372 lines · 2,640 tokens per session scan A e4d71fb9bece

Subscribe to this mod's changes

playbooks CLAUDE.md is an instructions file published in the GitHub repository playbooks-ai/playbooks (91 stars, last pushed 29d ago), licensed MIT. It adds 2,640 tokens to every session, about $0.0132 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.

Building agents LLM Writing and docs agent-orchestration ai-agents ai-agents-framework multi-agent-systems natural-language-programming

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 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 · 5,153 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

playbooks: Instructions file for Claude Code