clawker — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by schmitthub · Codex Skill · ★ 53

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is clawker safe to install? View the security audit →

About clawker

Clawker: Claude Code agent-in-container orchestration and automation clawker is a cli for orchestrating, monitoring, and automating portable devcontainers for Claude Code agents — a security-first AI container sandbox for Anthropic's models, including the latest mythos-class Fable 5. It works on any MacOS/Linux host with docker installed. I wrote this because I didn't want to have to pay someone to run claude code agents with --dangerously-skip-permissions when containers have been around for a decade, and claude code's sandbox mode is the temu version of a con

agentagent-sandboxagentic-aiagentic-codingai-agentai-sandboxanthropicchatgptclaudeclaude-code

Quick Facts

Stars53
Forks6
LanguageGo
CategoryCodex Skill
LicenseAGPL-3.0
Quality Score62.6293450712476/100
Open Issues44
Last Updated2026-09-08
Created2026-01-07
Platformsclaude-code, codex, docker, go
Est. Tokens~23k

Compatible Skills

These tools work well together with clawker for enhanced workflows:

  • clampdown — semantic(0.50)+complementary+same_lang+similar_pop+shared_platform (63%)

clawker alternative? Top 6 similar tools

Looking for a clawker alternative? If you're comparing clawker with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • vibepod-cli by VibePod · ⭐ 165

    Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, H

  • kasetto by pivoshenko · ⭐ 202

    📼 Declarative AI agent environment manager, written in Rust

  • claudex by Mng-dev-ai · ⭐ 224

    Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git

  • minimal by gominimal · ⭐ 124

    Run your agent in a Minimal box. Ship and run software with isolation on your own computer.

  • pydantic-ai-backend by vstorm-co · ⭐ 121

    File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is clawker?

clawker is AI coding agent sandbox: run agents locally in isolated Docker containers behind an egress firewall — self-hosted & free. It is categorized as a Codex Skill with 53 GitHub stars.

What programming language is clawker written in?

clawker is primarily written in Go. It covers topics such as agent, agent-sandbox, agentic-ai.

How do I install or use clawker?

You can find installation instructions and usage details in the clawker GitHub repository at github.com/schmitthub/clawker. The project has 53 stars and 6 forks, indicating an active community.

What license does clawker use?

clawker is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to clawker?

The top alternatives to clawker on Agent Skills Hub include palot, vibepod-cli, kasetto. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools