by zjunlp · Codex Skill · ★ 57
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 57 |
| Forks | 10 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 52/100 |
| Last Updated | 2026-08-17 |
| Created | 2026-05-21 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~13k |
A modular runtime for recursive improvement in long-running LLM agents 🛠️ Products Context Cleaner Context Cleaner is available, with the same plan, approval, status, and cancellation model across hosts. In Codex, opens the host-rendered task selector; the direct terminal equivalent is . Analysis is read-only until you confirm a selection, and protected tasks cannot be selected.
These tools work well together with LightMem2 for enhanced workflows:
Looking for a LightMem2 alternative? If you're comparing LightMem2 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.
Long-term memory layer for OpenClaw & MoltBook agents that learns and recalls your project context automatical
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.
Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, Open
An opinionated Claude Code Plugin Pack. Skills, Agents, Hooks, MCPs. Examples: Email draft preview assistance
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: