by AlekseiUL · Codex Skill · ★ 25
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 | 25 |
| Forks | 2 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 72/100 |
| Last Updated | 2026-09-09 |
| Created | 2026-06-10 |
| Platforms | browser, codex, python |
| Est. Tokens | ~16k |
GPT Image 2.5 Sunburst & Flare toolkit for agents: generation, reference and masked edits, PNG/JPEG/WebP, dry-runs and validated receipts. Experimental ChatGPT/Codex backend.
These tools work well together with gpt-image-2-5-agent-kit for enhanced workflows:
Looking for a gpt-image-2-5-agent-kit alternative? If you're comparing gpt-image-2-5-agent-kit 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.
中华术数 MCP 排盘服务：八字・紫微斗数・六爻・梅花易数・大六壬・奇门遁甲｜Deterministic Chinese-metaphysics chart calculator for AI agents (MCP).
视觉优先的 AI PPT Skill｜适用于挑战杯（大挑/小挑）、中国国际大学生创新大赛、全国大学生交通运输科技大赛（交科赛）、三创赛、正大杯、大创等竞赛，也适合学术汇报、论文答辩、项目路演与课程展示｜4 套风格 → 高
FlowLens is an open-source MCP server that gives your coding agent (Claude Code, Cursor, Copilot, Codex) full
< 한 걸음 앞선 개발자가 지금 꼭 알아야 할 클로드 코드 >
Claude Code skills for Bria AI - generate, edit, and transform images with Fibo, RMBG-2.0, and VGL structured
Local citation-backed recall for Pi, OMP, Claude Code, Codex, and ChatGPT history.
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: