Clawguard Guardian

ClawGuard Guardian v3 - Runtime guardian with behavior monitoring, interception, session freeze/replay, and emergency response

49 stars 4 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add SafeAgent-Beihang/clawguard --skill clawguard-guardian
Manual install
git clone --depth 1 https://github.com/SafeAgent-Beihang/clawguard.git /tmp/clawguard
mkdir -p ~/.claude/skills
cp -r /tmp/clawguard/guardian-skill ~/.claude/skills/clawguard-guardian

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# ๐Ÿ›ก๏ธ ClawGuard Guardian (CG-GD) v3

Runtime guardian for monitoring, intercepting, and controlling AI agent operations. Provides real-time behavior monitoring, risk-based interception, session replay, and emergency freeze capabilities.

## When to Use

Activate ClawGuard Guardian when:
- A user asks to start guardian or monitoring
- User asks to view status or logs
- User asks to replay or freeze sessions
- Emergency response is needed
- User asks "start monitoring" or "show status"

## How to Execute

### Command 1: Start Monitoring

```
User: Start guardian
Agent:
๐Ÿ›ก๏ธ Guardian starting...
   Session ID: session-xxx
   Status: ACTIVE
   Monitoring: Commands, Files, Network, Prompt Injections
```

### Command 2: View Status

```
User: Show status
Agent:
โ•”โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•—
โ•‘                 ๐Ÿ›ก๏ธ Guardian Status                      โ•‘
โ• โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•ฃ
โ•‘  Current Status: ๐ŸŸข ACTIVE                              โ•‘
โ•‘  Session ID: session-xxx                               โ•‘
โ•‘  Operations: XXX                                       โ•‘
โ•‘  Blocked: X                                            โ•‘
โ•‘  Frozen Sessions: X                                    โ•‘
โ•šโ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•
```

### Command 3: Freeze Session
Read the full skill on GitHub

Details

Skill name
clawguard-guardian
Path
guardian-skill/SKILL.md
Repo updated
29 March 2026

FAQ

What does the Clawguard Guardian skill do?

ClawGuard Guardian v3 - Runtime guardian with behavior monitoring, interception, session freeze/replay, and emergency response

How do I install the Clawguard Guardian skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add SafeAgent-Beihang/clawguard --skill clawguard-guardian. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Clawguard Guardian popular?

It lives in SafeAgent-Beihang/clawguard, which has 49 GitHub stars and 4 forks.

Related skills

Clawguard Auditor

49

SafeAgent-Beihang/clawguard

ClawGuard v3 Auditor - ไผไธš็บง Skill ๅฎ‰ๅ…จๅฎก่ฎกๅ™จ๏ผŒๆ”ฏๆŒๆ„ๅ›พๅ็ฆปๆฃ€ๆต‹ใ€SASTใ€ไพ›ๅบ”้“พๅฎ‰ๅ…จใ€ML ๅผ‚ๅธธๆฃ€ๆต‹ใ€‚ๅฝ“็”จๆˆท่ฆๆฑ‚ๅฎก่ฎกใ€ๆฃ€ๆต‹ใ€ๅฎ‰่ฃ…ๅ‰ๆฃ€ๆŸฅไธ€ไธช Skill ็š„ๅฎ‰ๅ…จๆ€งๆ—ถ่งฆๅ‘ใ€‚

AI, LLMs & Agents

Clawguard Security Checker

49

SafeAgent-Beihang/clawguard

ClawGuard Security Checker v3 - Advanced configuration analysis, runtime integrity verification, permission modeling, and one-click hardening recommendations

Security

Clawguard Self Improving Safety

49

SafeAgent-Beihang/clawguard

Self-improving safety module that proactively learns and enforces safety constraints. Works as a standalone firewall or integrates with ClawGuard Detect for automated learning.

Learning & Education

Clawguard Threat Detect

49

SafeAgent-Beihang/clawguard

ClawGuard Threat Detector - Real-time behavioral monitoring, attack pattern detection, MITRE ATT&CK mapping, and AI-powered anomaly detection for OpenClaw runtime environments

DevOps & Cloud

Symbol

113

Hmbown/Wizards-of-the-Ghosts

In D&D, Symbol inscribes a powerful glyph with a predefined effect โ€” death, fear, sleep, stunning โ€” that triggers when conditions are met. Unlike Glyph of Warding (which protects a specific place or object), Symbol marks a conceptual boundary with a named policy. The real-world version is semantic policy tagging: marking a database column as PII so access triggers audit logging, tagging a deployment as HIPAA-scoped so changes require compliance review, or labeling an API endpoint as rate-limited-aggressive so traffic spikes trigger automatic throttling. The symbol is the policy, and the policy

DevOps & Cloud11

Game CI Pipeline

57

AlterLab-IEU/AlterLab_GameForge

Designs and writes CI/CD pipelines for games: tests, headless builds, caching, Git LFS, secrets and deploys to Steam, itch.io (butler), Cloudflare or Netlify, for Godot, Unity (GameCI), Unreal (RunUAT) and Vite web builds. Use for "CI", "GitHub Actions", "automated build", "deploy to Steam/itch". Not for portal SDKs or store pages (use game-web-publish).

DevOps & CloudIn 1 list

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.