agentguard CLAUDE.md

Instructions for AgentGuard, a security framework for AI agents that scans code, evaluates planned actions, manages trust levels, and records security events.

In plain words
What is it for?
Use it to scan a path, assess a runtime action, manage skill trust, run security patrols, review audit logs, configure protection levels, or create a health report.
Why use it?
It helps identify code risks and decide whether an agent action should be allowed, denied, or confirmed. It also supports routine checks of agent environments.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/goplussecurity/agentguard/claude-md
Clone the repo
git clone --depth 1 https://github.com/GoPlusSecurity/agentguard
Per session 319 This file is loaded in full into every session.
When invoked 319 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00319 $0.00319
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 3d ago against content hash 9686a4a91eda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

CLAUDE.md · 40 lines

What it actually says

GoPlus AgentGuard

Security framework for AI agents. Provides code scanning, runtime action evaluation, and trust management.

Skill

This project provides a unified Claude Code skill: /agentguard

/agentguard scan <path>          — Scan code for security risks (24 detection rules)
/agentguard action <description> — Evaluate runtime action safety (allow/deny/confirm)
/agentguard patrol [run|setup|status] — Daily security patrol for OpenClaw environments
/agentguard trust <subcommand>   — Manage skill trust levels (lookup/attest/revoke/list)
/agentguard report               — View security event audit log
/agentguard config <level>       — Set protection level (strict/balanced/permissive)
/agentguard checkup              — Run agent health checkup with visual HTML report

Project Structure

  • skills/agentguard/ — Claude Code skill definition and supporting files
  • src/ — TypeScript source (scanner rules, registry, action detectors, MCP server)
  • data/ — Registry storage (registry.json)
  • dist/ — Compiled JavaScript output

Setup for Trust & Action CLI

The trust and action subcommands use CLI scripts that require the agentguard package:

cd skills/agentguard/scripts && npm install

For GoPlus API (optional Web3 enhancement for action evaluation):

export GOPLUS_API_KEY=your_key
export GOPLUS_API_SECRET=your_secret
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. 3d ago First seen · 40 lines · 319 tokens per session scan A 9686a4a91eda

Subscribe to this mod's changes

agentguard CLAUDE.md is an instructions file published in the GitHub repository GoPlusSecurity/agentguard (458 stars, last pushed 7d ago), licensed MIT. It adds 319 tokens to every session, about $0.0016 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 2026-08-30.

Related

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).

microsoft/vscode · 6,785 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

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 · 5,182 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 · 4,345 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

next.js 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