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 kodustech · Codex Skill · ★ 96
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is awesome-agent-skills safe to install? View the security audit →
Awesome Agent Skills A curated list of agent skills for software engineering Maintainer Note: This list is curated and maintained by the engineering team at Kodus. We love open source and building better devtools. Content What are Agent Skills? Agent Skills Frontend Development Backend Development DevOps Testing & QA Security Observability Performance Mobile Development Blockchain Infrastructure Data Science AI/ML Tooling Code Review FAQ: Agent Skills Agent Skill Template What are Agent Skills? Agent skills are modular, standardized capability packages that give agents on-demand abilities. In practice, a skill is usually a small SKILL.md file that defines: When it should be used How the task should be executed What constraints and best practices apply Skills follow a model of progressive disclosure: lightweight metadata loads first, and full instructions are loaded only when the skill becomes relevant. This allows agents to stay fast and focused, while still executing
| Stars | 96 |
| Forks | 80 |
| Category | Codex Skill |
| Quality Score | 56.5824786915713/100 |
| Open Issues | 45 |
| Last Updated | 2026-08-14 |
| Created | 2026-01-07 |
| Platforms | claude-code, codex |
| Est. Tokens | ~22k |
These tools work well together with awesome-agent-skills for enhanced workflows:
Looking for a awesome-agent-skills alternative? If you're comparing awesome-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.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
AI tools curated by autonomous agents for makers and SMBs
A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.
Build, test, and deploy intelligent AI agents the Laravel way
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Explore other popular codex skill tools:
awesome-agent-skills is Curated list of Agent Skills for AI coding agents like Claude Code, Codex and Cursor.. It is categorized as a Codex Skill with 96 GitHub stars.
You can find installation instructions and usage details in the awesome-agent-skills GitHub repository at github.com/kodustech/awesome-agent-skills. The project has 96 stars and 80 forks, indicating an active community.
The top alternatives to awesome-agent-skills on Agent Skills Hub include claudepro-directory, riseofmachine, awesome-azure-openai-llm. 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: