Borrowing it
Nothing to install: this file belongs to adewale/guardrails-skill. 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/adewale/guardrails-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/adewale/guardrails-skillWrote 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/adewale/guardrails-skill/claude-md)<a href="https://agentmods.dev/instructions/adewale/guardrails-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/adewale/guardrails-skill/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 | $0.00580 | $0.00580 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
guardrails-skill 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 7d 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 — 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 Is
A Claude Code skill — not a runnable codebase. There is no build system, package manager, test suite, or CI pipeline. The repository contains only markdown documentation and one bash template that together define quality gates for coding agents.
The skill lives in skills/guardrails/. SKILL.md is the core artifact (~220 lines). Everything else supports it:
skills/guardrails/references/tool-building.md— diagnostic tool/notation catalog with worked examples (loaded on demand by the circuit breaker)skills/guardrails/references/language-defaults.md— tool selection lookup table by ecosystem (JS/TS, Python, Rust, Go, Java)skills/guardrails/assets/notation-templates/reproduction-script.sh— bash scaffold for repro scripts
The repo is also a Claude Code plugin (.claude-plugin/plugin.json and marketplace.json).
Architecture
The skill defines lifecycle hooks that block agent progress until checks pass:
| Hook | Fires when | What runs |
|---|---|---|
| SessionStart | Agent boots | Discovery: git baseline, config inspection, test conventions, LESSONS_LEARNED.md, agent-tools/ |
| Stop | Agent returns control | Fast check (format, lint, types, unit tests). Circuit breaker after 2 failures |
| Commit | Any git commit | Full suite + secrets scan + integration/deployment check (is new code reachable?) |
The circuit breaker is the key enforcement mechanism: after 2 failed fix attempts, the agent must build a diagnostic tool or switch to a structured notation (from references/tool-building.md) rather than retrying. After attempt 3, the agent stops entirely and reports to the user.
Config protection prevents the agent from weakening its own guardrails (test scripts, lint config, CI definitions, coverage thresholds).
Editing Guidelines
- SKILL.md must stay under ~250 lines. It's read by agents at session start; bloat wastes context tokens.
- The skill defines when checks run and what to do when stuck, not how to lint or test — agents already know that from training.
- References are loaded on demand, not eagerly. Keep this separation: SKILL.md for hooks/rules, references/ for catalogs.
- The reproduction-script.sh template follows a 4-phase pattern (Setup → Trigger → Check → Cleanup) with
set -euo pipefail. Preserve this structure. - The
language-defaults.mdtable covers 5 ecosystems × 4 concern areas (testing, static analysis, security, infrastructure). Add new ecosystems as new columns, new concerns as new rows.
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.
- 7d ago First seen · 37 lines · 580 tokens per session scan A 3e2fc72ad92a
guardrails-skill CLAUDE.md is an instructions file published in the GitHub repository adewale/guardrails-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 580 tokens to every session, about $0.0029 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
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).
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.
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.
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).
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.