What is automatasaurus CLAUDE.md?

Project instructions for Automatasaurus, a workflow framework that lets Claude Code coordinate multiple coding agents through GitHub issues and pull requests. They describe the project layout, commands, settings, and how installed files are merged and tracked.

Use them when developing Automatasaurus, initializing or updating it in another project, checking installation status, or modifying its CLI, templates, symlinks, and merge logic.

They give an agent the project-specific context needed to change Automatasaurus safely without guessing how its files, installation state, or block-based updates work.

How shwilliamson/automatasaurus configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shwilliamson/automatasaurus. 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/shwilliamson/automatasaurus/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shwilliamson/automatasaurus

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/shwilliamson/automatasaurus/claude-md/github.svg)](https://agentmods.dev/instructions/shwilliamson/automatasaurus/claude-md)

Your own site

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

Per session 1,391 This file is loaded in full into every session.

When invoked 1,391 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	$0.01391	$0.01391
Opus 5.5	$0.00556	$0.00556
Sonnet 5.5	$0.00278	$0.00278
Haiku 4.5	$0.00139	$0.00139

Measured 2mo ago against content hash f86c7cfbd52a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

automatasaurus 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 2mo 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 · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automatasaurus Development Guide

Automatasaurus is a workflow orchestration framework for Claude Code that enables multi-agent autonomous development through GitHub issues and PRs.

Project Structure

automatasaurus/
├── bin/cli.js              # CLI entry point (init, update, status)
├── src/
│   ├── commands/           # CLI command implementations
│   │   ├── init.js         # Initialize framework in target project
│   │   ├── update.js       # Update framework to latest version
│   │   └── status.js       # Show installation status
│   └── lib/                # Shared utilities
│       ├── paths.js        # Path utilities (template dir, project dir)
│       ├── manifest.js     # Track installation state (.automatasaurus/.manifest.json)
│       ├── symlinks.js     # Create .claude -> .automatasaurus symlinks
│       ├── block-merge.js  # Merge content into marked blocks in files
│       └── json-merge.js   # Deep merge JSON settings
├── template/               # Files installed into target projects
│   ├── CLAUDE.block.md     # Core framework docs (block-merged)
│   ├── commands.block.md   # Framework commands (block-merged)
│   ├── settings.json       # Claude Code settings with hooks
│   ├── mcp.json            # MCP server config (Playwright)
│   ├── commands/           # Slash command definitions
│   ├── agents/             # Specialized personas (PM, Developer, Architect, etc.)
│   ├── skills/             # Reusable knowledge modules
│   └── hooks/              # Shell scripts (notify, on-stop, request-attention)
└── .claude/                # Symlinked to template/ for dogfooding

Commands

npm test                    # Run tests (node --test src/**/*.test.js)
npx automatasaurus init     # Test installer on a project
npx automatasaurus update   # Test update mechanism
npx automatasaurus status   # Test status display

Key Concepts

Block Merging

Files with .block.md extension use marked blocks that get merged into target files:

<!-- AUTOMATASAURUS:START -->
Framework content here (replaced on update)
<!-- AUTOMATASAURUS:END -->

Content outside blocks is preserved during updates.

Read the full file on GitHub · 162 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.

2mo ago First seen · 162 lines · 1,391 tokens per session scan A f86c7cfbd52a

Subscribe to this mod's changes

automatasaurus CLAUDE.md is an instructions file published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 8mo ago), licensed MIT. It adds 1,391 tokens to every session, about $0.0056 per session on Opus 5.5. 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 Project management

automatasaurus CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
automatasaurus CLAUDE.mdshwilliamson/automatasaurus	Instructions file	5	8mo ago	MIT	A	1,391	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

automatasaurus: Instructions file for Claude Code