claude-guardrails: Instructions file for Claude Code

CLAUDE.md

claude-guardrails CLAUDE.md is an instructions file for Claude Code from dwarvesf/claude-guardrails. It costs 870 tokens per session, scanned B, original, MIT.

Um pacote de configurações de segurança para o Claude Code, uma ferramenta que ajuda a escrever e alterar código. Inclui variantes mais completas ou mais simples para limitar ações perigosas e proteger informações sensíveis.

In plain words
What is it for?
Configurar permissões bloqueadas, verificações antes e depois das ações do agente, regras de segurança no projeto e orientações de isolamento do sistema.
Why use it?
Ajuda a impedir eliminações destrutivas, envios diretos de código e tentativas de expor dados. Também define cuidados para trabalhar com código não confiável ou credenciais de produção.

Instructions file for Claude Code

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

This is dwarvesf/claude-guardrails's own configuration. It tells Claude Code how to work on claude-guardrails 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 claude-guardrails configures →

Reuse

Borrowing it

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

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 claude-guardrails CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dwarvesf/claude-guardrails/claude-md/github.svg)](https://agentmods.dev/instructions/dwarvesf/claude-guardrails/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dwarvesf/claude-guardrails/claude-md"><img src="https://agentmods.dev/badge/instructions/dwarvesf/claude-guardrails/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.

agentmods 80×15 button for claude-guardrails CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dwarvesf/claude-guardrails/claude-md"><img src="https://agentmods.dev/badge/instructions/dwarvesf/claude-guardrails/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 870 This file is loaded in full into every session.
When invoked 870 The same file — it is already loaded in full.
Security scan B 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 $0.00870 $0.00870
Opus 5 $0.00435 $0.00435
Sonnet 5 $0.00174 $0.00174
Haiku 4.5 $0.00087 $0.00087

Measured 9d ago against content hash cbaeafc15b0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

claude-guardrails CLAUDE.md scanned grade B 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Settings must be merged, not replaced** — Users with existing `~/.claude/settings.json` must manually merge deny rules and hooks to avoid overwriting their config.
CLAUDE.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 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.

What This Repo Is

A security configuration package for Claude Code, providing hardened settings, hooks, and CLAUDE.md security rules. Built for the Dwarves Foundation team, based on Trail of Bits, Lasso Security, and Anthropic security recommendations.

Two variants are provided:

  • full/ — Complete 5-layer defense: permission deny rules, PreToolUse hooks (destructive deletes, direct pushes, pipe-to-shell, data exfiltration, permission escalation), PostToolUse prompt injection scanner, CLAUDE.md security rules, and OS-level sandbox guidance. Use for open source repos, untrusted codebases, or production credential handling.

  • lite/ — Minimal 3-layer config: permission deny rules, 3 PreToolUse hooks (destructive deletes, direct pushes, pipe-to-shell), and a slim CLAUDE.md security section. No prompt injection scanner or exfiltration hooks. Use for internal/trusted projects.

Architecture

Each variant contains:

  • settings.json — Claude Code global settings with permissions.deny rules (blocking Read/Edit on sensitive paths like SSH keys, AWS creds, .env files) and hooks.PreToolUse entries (blocking dangerous bash patterns before execution)
  • scan-secrets.sh — UserPromptSubmit hook (bash + jq) that regex-scans prompts for live credentials (AWS keys, GitHub/Anthropic/OpenAI tokens, PEM blocks, BIP39 phrases, Bitcoin WIF / BIP-32 xprv wallet keys) and blocks submission before the prompt reaches the model or is persisted to the session transcript. Uses jq's Oniguruma regex engine for lookbehind support — no extra runtime required.
  • scan-commit.sh — PreToolUse hook (bash + jq) that intercepts Bash calls, detects git commit, runs git diff --cached -U0 through the same pattern set as scan-secrets.sh, and blocks on match. Closes the gap where Claude writes a secret into code and then commits it (the prompt scanner only catches pasted creds).
  • CLAUDE-security-section.md — Security rules to merge into a user's ~/.claude/CLAUDE.md
  • SETUP.md — Installation and usage guide

Read the full file on GitHub · 37 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. 9d ago First seen · 37 lines · 870 tokens per session scan B cbaeafc15b0e

Subscribe to this mod's changes

claude-guardrails CLAUDE.md is an instructions file published in the GitHub repository dwarvesf/claude-guardrails (33 stars, last pushed 29d ago), licensed MIT. It adds 870 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 5,153 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

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