What is ClawdAgent CLAUDE.md?

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.

Use it to document architecture, development commands, testing and linting rules, type-safety requirements, and task or commit procedures.

It gives coding agents consistent project context and expectations at the start of each session, reducing setup questions and avoidable mistakes.

How liortesta/ClawdAgent configures Claude Code

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/liortesta/clawdagent/claude-md/github.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/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/liortesta/clawdagent/claude-md"><img src="https://agentmods.dev/badge/instructions/liortesta/clawdagent/claude-md.svg" alt="Reviewed on agentmods" width="80" 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.

Model	Per session	Once invoked
Fable 5.1	$0.03271	$0.03271
Opus 5.5	$0.01308	$0.01308
Sonnet 5.5	$0.00654	$0.00654
Haiku 4.5	$0.00327	$0.00327

Measured 2mo ago against content hash e12e1389fb1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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.

2mo 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 (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,271 tokens to every session, about $0.0131 per session on Opus 5.5. 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.

Building agents Project management

ClawdAgent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ClawdAgent CLAUDE.mdliortesta/ClawdAgent	Instructions file	12	2mo ago	Apache-2.0	C	3,271	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

ClawdAgent: Instructions file for Claude Code