by xieziyu · Codex Skill · ★ 50
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. Full audit →
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 | 50 |
| Forks | 2 |
| Language | TypeScript |
| Category | Codex Skill |
| License | GPL-3.0 |
| Quality Score | 61/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-29 |
| Created | 2026-07-18 |
| Platforms | codex, node |
| Est. Tokens | ~14k |
Duetlens 和 agent 看透每一处改动 官网 · 简体中文 · English Duetlens 是一个 macOS 桌面应用:把一次 code review 变成你和 agent(codex 或 pi)的双人对话,而不是读一份机审报告。 agent 扫出的每条 finding 都是一个可以继续追问的讨论线程;你也可以在 diff 的任意一行、任意一段代码上直接开口问 —— 为什么这么写、这个取舍的代价是什么、这里会不会有并发问题。看完之后筛一遍,提交成 GitHub PR review,或导出一份 Markdown。 功能 在 diff 上对话,而不是读报告。 findings 不是终点而是锚点:每条背后挂着一个常驻会话里的讨论,可以一直追问下去。行内 ✎ 或框选一段代码就在原地开一条新讨论;问架构、问整体取舍这类不落在某一行上的问题,也可以不锚定代码直接问。 记...
Looking for a duetlens alternative? If you're comparing duetlens 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.
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
Full-text search and resume for Claude/Codex conversations
Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing statefu
The rules layer for AI-written code — rig-lite: a fail-closed cross-model review gate, a written constitution,
The AI agent that works while you don't watch. Lives in your menu bar, finds you when needed.
An LLM council that reviews your coding agent's every move
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: