Awesome Codex Subagents

A curated collection of more than 175 specialized Codex subagents across 13 categories, installed as TOML files into Codex's global or project agent directories.

Visit website github.com

Awesome Codex Subagents is a collection of over 175 Codex subagents across 13 categories, described as specialized AI assistants for specific development tasks, written specifically for Codex and aligned with its official documentation.

Subagents are installed by cloning the repository and copying the wanted TOML agent files into Codex's global agent directory for use in every project, or into a project's own agent directory, which takes precedence in that repository. Because Codex does not auto-spawn custom subagents, they must be delegated to explicitly in a prompt, and agent configuration more generally is kept in a project configuration file under an agents section.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies