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 huangruiteng · Codex Skill · ★ 5.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is loopx safe to install? View the security audit →
Loop engineering for long-running AI agents and peer agent teams. A lightweight state kernel and agent-agnostic local control plane for Codex, Claude Code, Cursor, and other runtimes: objectives, gates, todos, quota, scheduler hints, evidence, and typed continuation in one reviewable loop. 把会干活的 Agent，接成可管理、可复盘、可持续改进的数字员工。 LoopX is a lightweight state kernel and local control plane for loop engineering: it keeps goals, todos, gates, quota, scheduler hints, evidence, and handoffs stable while Codex, Claude Code, Cursor, or another runtime executes each bounded turn. It does not replace your agent runtime; it makes long-running agent work reviewable, restartable, and easier to hand off. Registered agents are peers. Claims and leases, task boundaries, capabilities, and typed continuation decide who acts next; no durable leader identity is required. Start with a useful loop instead of designing a whole agent platform
| Stars | 5,843 |
| Forks | 537 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 65.0397010746698/100 |
| Open Issues | 85 |
| Last Updated | 2026-09-14 |
| Created | 2026-05-31 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~24k |
These tools work well together with loopx for enhanced workflows:
Looking for a loopx alternative? If you're comparing loopx 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.
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on Skills
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that promp
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integ
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown a
Independent executor–verifier orchestration for software changes.
Explore other popular codex skill tools:
loopx is Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.. It is categorized as a Codex Skill with 5.8k GitHub stars.
loopx is primarily written in Python. It covers topics such as agent-control-plane, agent-harness, agent-ops.
You can find installation instructions and usage details in the loopx GitHub repository at github.com/huangruiteng/loopx. The project has 5.8k stars and 537 forks, indicating an active community.
loopx is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to loopx on Agent Skills Hub include Vibe-Skills, loop-engineering, holaOS. 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: