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 axeldelafosse · Codex Skill · ★ 276
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is loop safe to install? View the security audit →
loop Dead-simple Bun CLI that runs and in a loop. Uses to run the interactive TUIs side-by-side. Codex and Claude talk to each other through the Codex App Server and Claude Code Channels. Install: Run: or By default uses Codex as the main worker and Claude as a reviewer. To run Claude as the main worker instead: Agent-to-agent pair programming One agent is the main worker, the other acts as a reviewer. They work together on a PLAN.md and iterate until they both agree the task is done. Then the main worker creates a draft PR. What this is This is a "meta agent loop" to help coding agents become long-running agents. Stop baby sitting your agents: let them iterate on tasks with clear proof requirements until they are done. Run multiple reviews to continue the feedback loop. This is not an "agent harness" and the goal isn't to re-invent the wheel: leverages existing agent harnesses like and , with their own implementation of the "agent teams" orchestration. The models are getting better
| Stars | 276 |
| Forks | 21 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 74.8867300091198/100 |
| Open Issues | 3 |
| Last Updated | 2026-04-01 |
| Created | 2026-02-20 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~28k |
Looking for a loop alternative? If you're comparing loop 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.
Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reu
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p
a project brain for your AI. Give LLMs instant architectural context without burning tokens
Claude Skill to do your tasks with subagents in Git worktrees
Best Practices for Claude Code Configuration
CodexFlow is a unified desktop workbench for AI coding agents (Codex/Claude/Gemini/Antigravity) across Windows
Explore other popular codex skill tools:
loop is Dead-simple Bun CLI that runs Codex and Claude Code in a loop.. It is categorized as a Codex Skill with 276 GitHub stars.
loop is primarily written in TypeScript. It covers topics such as bun, claude, claude-code.
You can find installation instructions and usage details in the loop GitHub repository at github.com/axeldelafosse/loop. The project has 276 stars and 21 forks, indicating an active community.
loop is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to loop on Agent Skills Hub include getspecstory, quint-code, codemap. 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: