Borrowing it
Nothing to install: this file belongs to TaroVard/claudeguard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TaroVard/claudeguard/main/CLAUDE.mdgit clone --depth 1 https://github.com/TaroVard/claudeguardWrote 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.
[](https://agentmods.dev/instructions/tarovard/claudeguard/claude-md)<a href="https://agentmods.dev/instructions/tarovard/claudeguard/claude-md"><img src="https://agentmods.dev/badge/instructions/tarovard/claudeguard/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00765 | $0.00765 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
claudeguard 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 79 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.
Development Commands
# Setup and dependencies
uv sync # Install dependencies
uv run pre-commit install # Setup git hooks for code quality
# Testing
uv run pytest # Run all tests
uv run pytest tests/test_specific.py # Run specific test file
uv run pytest -k "test_pattern" # Run tests matching pattern
# Code quality
uv run mypy src tests # Type checking
uv run ruff check --fix . # Format and lint code
uv run pre-commit run --all-files # Run all hooks manually
# CLI development and testing
uv run claudeguard --help # Test CLI commands
uv run claudeguard install # Install hook and initialize default profiles
uv run claudeguard status # Show configuration status
uv run claudeguard create-profile # Create new security profile
uv run claudeguard list-profiles # List available profiles
uv run claudeguard switch-profile # Switch between profiles
uv run claudeguard delete-profile # Delete security profile
uv run claudeguard uninstall # Remove claudeguard hook
Architecture Overview
claudeguard is a security layer for Claude Code that intercepts tool calls and makes permission decisions through pattern matching. The system is built around these core components:
Hook System (src/claudeguard/hook.py)
- Entry point that intercepts Claude Code tool calls via JSON stdin/stdout protocol
- Integrates with Claude Code's
permissionDecisionhook system - Handles error sanitization and fail-safe behavior
Permission Engine (src/claudeguard/permission_decision.py)
- Makes security decisions (
allow,ask,deny) based on loaded profiles - Implements fail-safe defaults (errors default to "ask")
- Core decision-making logic for tool call authorization
Pattern Matching (src/claudeguard/pattern_matcher.py)
- Multi-strategy pattern matching: glob, regex, and MCP-specific patterns
- Includes DoS protection for regex patterns and input validation
- Extracts resources from tool calls for pattern comparison
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.
- 6d ago First seen · 79 lines · 765 tokens per session scan A c324c86db528
claudeguard CLAUDE.md is an instructions file published in the GitHub repository TaroVard/claudeguard (5 stars, last pushed 1y ago), licensed MIT. It adds 765 tokens to every session, about $0.0038 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 2026-08-31.
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.
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.
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).
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).
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.
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.