ClawdAgent: Instructions file for Claude Code

CLAUDE.md

ClawdAgent CLAUDE.md is an instructions file for Claude Code from liortesta/ClawdAgent. It costs 3,271 tokens per session, scanned C, original, Apache-2.0.

A project instruction file that tells Claude Code how to work in a specific codebase. It records the project setup, common commands, coding standards, and workflow rules.

In plain words
What is it for?
Use it to document architecture, development commands, testing and linting rules, type-safety requirements, and task or commit procedures.
Why use it?
It gives coding agents consistent project context and expectations at the start of each session, reducing setup questions and avoidable mistakes.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is liortesta/ClawdAgent's own configuration. It tells Claude Code how to work on ClawdAgent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ClawdAgent configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/my-project.

Reuse

Borrowing it

Nothing to install: this file belongs to liortesta/ClawdAgent. 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/liortesta/ClawdAgent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

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.

agentmods badge for ClawdAgent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/liortesta/clawdagent/claude-md.svg)](https://agentmods.dev/instructions/liortesta/clawdagent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/liortesta/clawdagent/claude-md"><img src="https://agentmods.dev/badge/instructions/liortesta/clawdagent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,271 This file is loaded in full into every session.
When invoked 3,271 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03271 $0.03271
Opus 5 $0.01636 $0.01636
Sonnet 5 $0.00654 $0.00654
Haiku 4.5 $0.00327 $0.00327

Measured 3d ago against content hash e12e1389fb1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

ClawdAgent CLAUDE.md scanned grade C 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| PreToolUse → Bash | Before shell command | Blocks dangerous commands (rm -rf, DROP, etc.) |
CLAUDE.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Configuration — Claude Code MEGA Setup

This file is loaded automatically at the start of every Claude Code session. It serves as the "constitution" — all agents and commands follow these rules.

Architecture

  • Language: [DETECT_ON_SETUP]
  • Framework: [DETECT_ON_SETUP]
  • Package Manager: [DETECT_ON_SETUP]
  • Test Framework: [DETECT_ON_SETUP]
  • Database: [DETECT_ON_SETUP]
  • Deployment: [DETECT_ON_SETUP]

Key Commands

  • [pkg] run dev — Start dev server
  • [pkg] run build — Production build
  • [pkg] run test — Run tests
  • [pkg] run lint — Lint check
  • [pkg] run type-check — Type checking

Code Standards

  • TypeScript strict mode when applicable
  • No any types — use unknown or proper typing
  • All exports must have JSDoc/docstrings
  • Max file length: 300 lines — split if larger
  • Prefer composition over inheritance
  • Error handling: never swallow errors silently
  • All API endpoints must have input validation
  • Environment variables: never hardcode secrets
  • Use meaningful variable names — no single-letter vars except loop counters

Workflow Rules

  • For ANY task >50 lines of code: Enter Plan Mode FIRST (Shift+Tab)
  • For ANY commit: All tests must pass (enforced by Stop hook)
  • For ANY architecture decision: Use the CTO agent for evaluation
  • For ANY security-related code: Mandatory security-auditor agent review
  • After ANY correction from user: Update this file under "Self-Correction Rules"
  • Use subagents for parallel work when tasks are independent
  • Use background tasks (Ctrl+B) for long-running processes
  • Use Playwright MCP for visual/UI verification when available
  • ALWAYS "prove it works" before marking any task done

Background Task Rules

  • ALWAYS run dev servers in background
  • ALWAYS run watch processes in background
  • Run security scans in background while developing
  • Use /tasks to monitor running background agents

Memory Management

  • After each session, run /wrap-up to consolidate learnings
  • Update this file with key architectural decisions
  • Memory priority: Security rules > Architecture > Code style > Preferences
  • When Claude makes a mistake and is corrected, add rule to Self-Correction section

Read the full file on GitHub · 288 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. 3d ago First seen · 288 lines · 3,271 tokens per session scan C e12e1389fb1f

Subscribe to this mod's changes

ClawdAgent CLAUDE.md is an instructions file published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 3,271 tokens to every session, about $0.0164 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other instructions, from other repositories

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 · 5,182 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens