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 addyosmani · Codex Skill · ★ 97.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-skills safe to install? View the security audit →
Agent Skills Production-grade engineering skills for AI coding agents. Skills encode the workflows, quality gates, and best practices that senior engineers use when building software. These ones are packaged so AI agents follow them consistently across every phase of development. Commands 7 slash commands that map to the development lifecycle. Each one activates the right skills automatically — you don't need to memorize 18 skill names. Five-a
| Stars | 97,753 |
| Forks | 10,297 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 73.1040525750785/100 |
| Open Issues | 110 |
| Last Updated | 2026-09-20 |
| Created | 2026-02-15 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~16k |
Looking for a agent-skills alternative? If you're comparing agent-skills 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.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Anti
Agent skill that removes signs of AI-generated writing from text
Installable GitHub library of 1,800+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravit
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, sessio
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memo
Explore other popular codex skill tools:
agent-skills is Production-grade engineering skills for AI coding agents.. It is categorized as a Codex Skill with 97.8k GitHub stars.
agent-skills is primarily written in JavaScript. It covers topics such as agent-skills, antigravity, claude-code.
You can find installation instructions and usage details in the agent-skills GitHub repository at github.com/addyosmani/agent-skills. The project has 97.8k stars and 10297 forks, indicating an active community.
agent-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agent-skills on Agent Skills Hub include awesome-claude-skills, agents, humanizer. 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: