Borrowing it
Nothing to install: this file belongs to Ethonik/agentguard. 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/Ethonik/agentguard/main/CLAUDE.mdgit clone --depth 1 https://github.com/Ethonik/agentguardWrote 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/ethonik/agentguard/claude-md)<a href="https://agentmods.dev/instructions/ethonik/agentguard/claude-md"><img src="https://agentmods.dev/badge/instructions/ethonik/agentguard/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.
<a href="https://agentmods.dev/instructions/ethonik/agentguard/claude-md"><img src="https://agentmods.dev/badge/instructions/ethonik/agentguard/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00982 | $0.00982 |
| Opus 5.5 | $0.00393 | $0.00393 |
| Sonnet 5.5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
agentguard 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Guía de mantenimiento de agentguard
Contexto para cualquier agente (o persona) que edite este repositorio.
Qué es
Skill de Claude Code para seguridad de aplicaciones agénticas (código que usa LLMs, tool-calling,
memoria, MCP o multi-agente). Dos modos: auditoría (review) y asesoría de diseño (design).
El conocimiento de seguridad vive en skills/agentguard/references/ y se ancla a tres marcos:
OWASP Top 10 for Agentic Applications 2026 (ASI01–ASI10), OWASP Top 10 for LLM Applications
2025 (LLM01–LLM10) y CWE (MITRE) — clase de debilidad y mitigaciones por hallazgo, incl. los
CWE de IA generativa CWE-1427 y CWE-1426.
Principios de diseño (no romper)
- Read-only sobre el proyecto objetivo. El skill nunca modifica el código que audita; solo escribe su archivo de informe.
- Scripts = Python 3 stdlib únicamente, cero dependencias. Deben correr con
python3a secas. Nada depip install. Nunca ejecutan (exec/import) código del target: solo lo leen como texto. - Bilingüe. Explicaciones en español; IDs, términos técnicos y nombres OWASP en inglés
(
ASI01,prompt injection,human-in-the-loop, ...). - Cada hallazgo se mapea a un ID OWASP (
ASI0xy/oLLM0x) y a un CWE cuando exista, y trae remediación accionable, no solo la descripción del riesgo. Si un fallo es puramente agéntico y CWE no tiene categoría nativa (goal hijack, memory poisoning, behavioral drift), se reporta solo con el IDASI— no forzar un CWE que no aplica. - Uso defensivo/autorizado. El skill sirve para asegurar sistemas propios o con autorización. No produce exploits ni técnicas ofensivas.
Estructura
Motor (agnóstico, fuente de verdad del conocimiento):
skills/agentguard/SKILL.md— orquestador enriquecido para Claude Code (modos + pipeline).skills/agentguard/scripts/—detect_stack.pyyscan_agentic_patterns.py.skills/agentguard/references/— base de conocimiento por dominio + plantillas.
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.
- 1mo ago First seen · 61 lines · 982 tokens per session scan A 9ba9d331673b
agentguard CLAUDE.md is an instructions file published in the GitHub repository Ethonik/agentguard (2 stars, last pushed 2mo ago), licensed MIT. It adds 982 tokens to every session, about $0.0039 per session on Opus 5.5. 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
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.