Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/wangbooth/claude-code-guardrails/claude-mdgit clone --depth 1 https://github.com/wangbooth/Claude-Code-GuardrailsWrote 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/wangbooth/claude-code-guardrails/claude-md)<a href="https://agentmods.dev/instructions/wangbooth/claude-code-guardrails/claude-md"><img src="https://agentmods.dev/badge/instructions/wangbooth/claude-code-guardrails/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 | $0.01171 | $0.01171 |
| Opus 5 | $0.00585 | $0.00585 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade E, and why
Claude-Code-Guardrails CLAUDE.md scanned grade E with 4 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y jq Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/wangbooth/claude-code-guardrails/main/install.sh | bash Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Global installation (~/.claude/settings.json) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/wangbooth/claude-code-guardrails/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 133 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.
Overview
This repository implements Claude Code Guardrails - a set of protective hooks that prevent accidental code loss and provide safe development workflows when using Claude Code. The system provides branch protection, automatic checkpointing, and safe commit squashing through Claude Code hooks.
Architecture
The guardrails system consists of three main components that integrate with Claude Code's hook system:
Hook Scripts (claude/hooks/)
guard-branch.sh- Prevents writes to protected branches (main/master/dev/release*) by exiting with code 2, blocking tool execution and suggesting feature branch creationauto-commit.sh- Creates precise checkpoint commits after each Write/Edit/MultiEdit operation, staging only the modified file(s)squash-checkpoints.sh- Consolidates multiple checkpoint commits into clean task commits during Stop/PreCompact events
Hook Configuration (claude/settings.json)
Defines the hook integration points:
- PreToolUse: Branch protection before Write/Edit/MultiEdit operations
- PostToolUse: Automatic checkpoint creation after Write/Edit/MultiEdit operations
- Stop/PreCompact: Commit squashing when conversations end or are compacted
Installation System
install.sh- Merges guardrails hooks into existing.claude/settings.jsonwith backup, deduplication, and idempotent operationuninstall.sh- Safely removes guardrails hooks while preserving other user hooks
Key Development Commands
Installation
# Project-level installation (current directory)
curl -fsSL https://raw.githubusercontent.com/wangbooth/claude-code-guardrails/main/install.sh | bash
# Global installation (~/.claude/settings.json)
curl -fsSL https://raw.githubusercontent.com/wangbooth/claude-code-guardrails/main/install.sh | bash -s -- --global
# Manual installation (copy .claude/ directory)
cp -r .claude/ /path/to/your-project/
chmod +x /path/to/your-project/.claude/hooks/*.sh
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.
- 4d ago First seen · 133 lines · 1,171 tokens per session scan E 5d94198d8194
Claude-Code-Guardrails CLAUDE.md is an instructions file published in the GitHub repository wangbooth/Claude-Code-Guardrails (54 stars, last pushed 11mo ago), licensed MIT. It adds 1,171 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it E with 4 findings (asks for root, downloads and executes remote code, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
cherry-studio AGENTS.md
AGENTS.md instructions for CherryHQ/cherry-studio, a project described as: AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.
the-pair AGENTS.md
Instructions for timwuhaotian/the-pair, covering ai agent guidelines for "the pair", project identity, tech stack, architecture rules and rust backend modules (src-tauri/src/).
tree-sitter-analyzer CLAUDE.md
Claude Code instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
Vara-s--Portfolio CLAUDE.md
Claude Code instructions for VARA4u-tech/Vara-s--Portfolio, covering claude.md — anisport portfolio, project overview, tech stack, directory structure and development commands.