Awarexone

Axguard Agent — AI skill for Claude Code

AI community

AI agent / LLM app risks — exec of model output, unrestricted shell tools.

How to install Axguard Agent

Installs to ~/.claude/skills/awarexone-axguard-axguard-agent/SKILL.md

Terminal

mkdir -p ~/.claude/skills/awarexone-axguard-axguard-agent && curl -fsSL https://raw.githubusercontent.com/Awarexone/AXguard/HEAD/commands/axguard-agent.md -o ~/.claude/skills/awarexone-axguard-axguard-agent/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Axguard Agent does

description: AI agent / LLM app risks — exec of model output, unrestricted shell tools. Usage: /axguard-agent [path]

/axguard-agent

**Specialist:** Agent Security

For apps built with AI agents, tool routers, or LLM-driven automation.

Usage

/axguard-agent

Focus

Executing or evaling model/assistant text
Shell tools without allowlists
Indirect prompt injection via retrieved docs (manual)

Steps

Scan → keep agent.*.
Inventory tools the agent can cal

Alternatives in AI

Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
Claude Usage Tracker — Native macOS menu bar app for tracking Claude AI usage limits in real-time 2.2k ★
Ante — Ghost in your shell 1.9k ★