by trailofbits · Codex Skill · ★ 241
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Isolated VM environment for running Claude Code and Codex
| Stars | 241 |
| Forks | 13 |
| Language | Rust |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 55.8823729697713/100 |
| Open Issues | 43 |
| Last Updated | 2026-09-17 |
| Created | 2026-04-02 |
| Platforms | claude-code, cli, codex, rust |
| Est. Tokens | ~22k |
These tools work well together with coop for enhanced workflows:
Looking for a coop alternative? If you're comparing coop 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.
Give coding agents a disposable Linux VM, not your laptop
Fast, red-teaming browser built for AI agents, with direct HTTP traffic control, sandboxed execution, and audi
CLI tool for running coding agents inside hardware-isolated microVMs
the universal sandbox runtime for agents and humans.
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t
Explore other popular codex skill tools:
coop is Isolated VM environment for running Claude Code and Codex. It is categorized as a Codex Skill with 241 GitHub stars.
coop is primarily written in Rust. It covers topics such as claude-code, cli, codex.
You can find installation instructions and usage details in the coop GitHub repository at github.com/trailofbits/coop. The project has 241 stars and 13 forks, indicating an active community.
coop is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to coop on Agent Skills Hub include clawk, h5i, brood-box. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: