Tag

OpenAI Codex tooling

76 entries tagged with #codex.

The Codex-aware slice of the directory. Most of the tools here also support Claude Code; the curated Codex guide highlights where Codex support is first-class.

GitHub LibraryFeatured

Garden Skills - production skill pack for Claude Code, Cursor, and Codex

Three carefully-scoped skills: web-design-engineer (with an anti-cliche blocklist that breaks the generic-AI-landing-page loop), gpt-image-2 (80+ templates, three runtime modes including advisor-only fallback), and kb-retriever (layered data_structure.md navigation for bounded local-KB retrieval). Tested across Claude Code, Claude.ai, Cursor, Codex, Gemini, OpenCode.

Why I saved this - The web-design skill's anti-cliche blocklist is the most opinionated take on 'stop producing the same hero + 3 cards' I've seen.

#claude-code #skills #cursor #codex #gemini-cli

GitHub ToolFeatured

wanman - worktree-isolated multi-agent runtime for Claude Code and Codex

Multi-agent runtime that spawns each Claude Code or Codex agent in its own git worktree and home directory. JSON-RPC subprocess control, task pooling, artifact storage. Solves the share-a-directory failure mode that breaks most multi-agent harnesses.

Why I saved this - The 'one-man train' framing is load-bearing: humans observe rather than approve every step. Worktree-per-agent isolation is the upgrade most multi-agent harnesses skip.

#claude-code #codex #multi-agent #orchestration #typescript

GitHub ToolFeatured

PostTrainBench - can a CLI agent post-train a base LLM in 10 hours?

Benchmark measuring whether Claude Code, Codex CLI, Gemini CLI, and OpenCode can autonomously improve 4 small base models (Qwen3-1.7B/4B, SmolLM3-3B, Gemma-3-4B) on 7 evals (AIME, BFCL, GPQA, GSM8K, HealthBench, HumanEval, Arena Hard) within a single H100 GPU and 10 hours. Includes agent-as-judge anti-reward-hacking and baseline-replacement penalties for tampering.

Why I saved this - Current leader: Opus 4.6 via Claude Code at 23.2 average. The reward-hacking safeguards (eval tampering and model-substitution detection, baseline-replacement penalty) are the part most agent benchmarks skip.

#evals #claude-code #codex #gemini-cli #opencode

GitHub Library

gpt_image_2_skill - 162-prompt gallery and skill for GPT Image 2

Curated gallery, CLI, and agentic skill for OpenAI's GPT Image 2. 162 reusable prompts across anime, gaming, photography, UI/UX, and research-figure categories. Supports text-to-image, mask-edit, multi-reference edits, and batch ops. Installable as a Claude Code plugin, Codex skill, or standalone CLI via uv.

Why I saved this - Bigger prompt gallery than garden-skills' gpt-image-2 (162 vs 80+) but narrower in scope - this is just the image skill, not a multi-skill pack.

Garden Skills - production skill pack for Claude Code, Cursor, and Codex

wanman - worktree-isolated multi-agent runtime for Claude Code and Codex

PostTrainBench - can a CLI agent post-train a base LLM in 10 hours?

gpt_image_2_skill - 162-prompt gallery and skill for GPT Image 2

SmolVM - one-command sandbox for Claude Code and Codex

Orca - IDE for coding agents

llm-openai-via-codex - reuse a Codex subscription as an LLM backend

agent-hub - one chat surface for every local and remote agent

AI Inner OS - inner-monologue plugin for AI CLIs

agent-session-resume - cross-agent session resume skill

codex-mcp-server - call Codex from Claude Code

tnl - typed natural language plan mode

Recall - TUI search across agent session history

OpenClawdex - orchestrator UI for Claude Code and Codex

AgentBox - SDK to run coding agents in any sandbox

VTCode - Rust TUI coding agent with multi-provider support

jeeves - TUI for browsing AI agent sessions

revdiff - TUI diff reviewer for AI agents

witchcraft - multi-vector semantic search in Rust

maestro-orchestrate - multi-agent orchestration platform

coding_agent_session_search - 11-provider session search

agent-sessions - native macOS session cockpit

opensessions - tmux sidebar for coding agents

horizon - GPU terminal canvas for agent sessions

token-ninja - local shell command router for AI tools

anywhere-agents - portable multi-agent config

ctx - cross-agent /resume for Claude Code and Codex

haft - engineering decisions engine with evidence decay

ai-setup - sync AI configs across coding agents

codexia - agent workstation for Codex and Claude Code

claude_agent_teams_ui - kanban for AI engineering teams

simulink-agentic-toolkit - Simulink MCP and skills

zeroshot - autonomous engineering team CLI

hcom - cross-terminal agent messaging

agent-style - 21 writing rules for coding agents

herdr - terminal agent multiplexer

onWatch - real-time agent API quota tracker

skillfile - declarative skill manager for AI agents

codexfast - unlock Fast mode in OpenAI Codex.app

ccmanager - session manager for AI coding CLIs

Palmier - phone bridge for AI coding agents

Spool - local search across agent histories

snip - LLM token-saving proxy in Go

vibe-remote - chat-app remote for coding agents

compose-skill - Jetpack Compose agent skill

skillshare - sync agent skills across CLIs

codemap - architectural context for LLMs

hydra - unified wrapper across AI CLIs with fallback

agent-order - cross-model PRD planning workflow

cli-continues - resume an AI session in a different tool

agent-skills - reusable skills for Codex

TokenTracker - cross-tool token usage dashboard

Skills-Manager - manage skills across AI coding tools

claude-code-history-viewer - browse session history

rightStage - sync AI context across terminals

claude-codex-settings - daily-driver agent config

OpenContext - personal context store for agents

claude-delegator - delegate to Codex and Gemini from Claude Code

TAKT - agent coordination topology in YAML

cccc - chat-style multi-agent orchestrator

claude-code-tools - utilities for CLI coding agents

relay - hand off Claude Code session to other agents

IDEA.md - portable idea-intent file for agents

modular-context-obsidian-plugin - Claude Code in Obsidian

unity-cli-plugin - Claude Code/Codex plugin for Unity

oh-my-agent - portable multi-agent harness

Codeburn - token cost TUI for Claude Code & Codex

agents-md - drop-in AGENTS.md template

abtop - htop for AI coding agents

lazyagent - terminal observability for coding agents

cc-telegram-bridge - Codex & Claude Code on Telegram

agent-deck - terminal session manager for coding agents

parallel-code - Claude, Codex, Gemini side-by-side

Codesight - universal AI context generator

Paseo - orchestrate coding agents from your phone

agentfiles - manage agent configs from Obsidian

Browse other tags