awesome-codex-subagents and awesome-agent-skills
These are ecosystem siblings—one is a specialized collection of executable Codex subagents for specific development tasks, while the other is a broader curated reference list of skills and tools across multiple AI coding platforms, serving different purposes (implementation vs. discovery) within the same agentic-workflow space.
About awesome-codex-subagents
VoltAgent/awesome-codex-subagents
A collection of 130+ specialized Codex subagents covering a wide range of development use cases.
Each subagent is defined in Codex-native `.toml` configuration files with smart model routing (gpt-5.4 for deep reasoning tasks, gpt-5.3-codex-spark for lighter work) and sandbox mode controls that match the agent's role—read-only for auditors and reviewers, workspace-write for developers. Organized across 10 categories spanning core development, language specialists, frameworks, and infrastructure, agents install into `~/.codex/agents/` (global) or `.codex/agents/` (project-scoped with override precedence) and must be explicitly delegated in prompts.
About awesome-agent-skills
heilcheng/awesome-agent-skills
A curated list of skills, tools, tutorials, and capabilities for AI coding agents (Claude, Codex, Antigravity, Copilot, VS Code)
Organizes skills as lazy-loaded instruction files (`SKILL.md`) that AI agents browse, request, and execute on-demand—reducing memory overhead while supporting multiple agent platforms (Claude, Copilot, Codex, Gemini). Aggregates official skill collections from Anthropic, OpenAI, and HuggingFace alongside community-maintained repositories covering document processing, development tools, and domain-specific capabilities. Skills work across agents and delivery mechanisms including CLI installers, MCP, and package managers.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work