VoltAgent/

awesome-codex-subagents

GitHub Website

A large collection of Codex subagents organized into categories, with installation guidance and TOML-based configurations for Codex agents. The repo claims 171+ subagents across 13 categories, tracked with MIT license and active maintenance as of 2026-07-10.

5.9kstars

646forks

6issues

MITlicense

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

Egonex-AI/

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

77k6.5kTypeScriptgiant

sickn33/

agentic-awesome-skills

▲ 328/wk

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,000+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

44k6.5kPython

VoltAgent/

awesome-agent-skills

▲ 426/wk

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

30k3.2k

NousResearch/

hermes-agent

▲ 3.5k/wk

The agent that grows with you

225k44kPython

Graphify-Labs/

graphify

▲ 4.6k/wk

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

102k9.9kPython

ComposioHQ/

awesome-claude-skills

▲ 585/wk

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

72k8.1kPython

Compareawesome-codex-subagents vs Understand-Anything awesome-codex-subagents vs agentic-awesome-skills awesome-codex-subagents vs awesome-agent-skills

Reviewgenerated from repository data · Aug 5, 2026

What it is

The repository is a collection of Codex Subagents, specialized AI assistants intended for development tasks. It documents a structure where each subagent uses a Codex-native .toml format and includes a model routing scheme and sandbox modes. It also provides how-to instructions for using Codex custom agent directories.

How it works

Subagents are defined as individual .toml files containing name, description, model, model_reasoning_effort, sandbox_mode, and an [instructions] text block. A model field routes to either gpt-5.4 or gpt-5.3-codex-spark depending on the task (deep reasoning vs fast scanning). Sandbox_mode controls filesystem access with read-only or workspace-write options.

Getting started

Installation steps are provided:

1. Clone this repository.
2. Copy the `.toml` agent files you want into one of the directories above.
3. Restart or refresh your Codex session if needed.
4. Delegate explicitly in prompts (Codex does not auto-spawn custom subagents).

Examples show copying specific agent TOML files into ~/.codex/agents or .codex/agents and the corresponding directory setup commands:

mkdir -p ~/.codex/agents
cp categories/01-core-development/backend-developer.toml ~/.codex/agents/

mkdir -p .codex/agents
cp categories/04-quality-security/reviewer.toml .codex/agents/

If using agent configuration in Codex, place it in .codex/config.toml under [agents] as described in the official docs.

Recent releases

RELEASES (latest 0):

none

Traction

Stars: 5912 Forks: 646 Open issues: 6

Behind the repo

Linked to VoltAgent organization; sponsors section mentions Ego Lite sponsorship details, but no external startup/company link beyond organization and sponsor references.

Caveats

License: MIT Created: 2026-03-17 Last push: 2026-07-10 Languages: -

SharePost on X LinkedIn