Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,430 indexed, measured the same four ways as everything else here.

init-agent-sync

25969

Hadi99K/AGENT_SKILLS

Skill Claude CodeCodex

Initializes the AGENTSYNC.md hub for AI agent coordination and task tracking.

not rated 2 5mo ago A 20 tokens original MIT

arco

25970

frankxai/claude-codex-gemini-opencode-settings

Skill Claude CodeCodex

Activate the Arcanea Orchestrator — the multi-CLI routing brain. Shows status, routes tasks to best model (claude/opencode/codex/gemini), runs plans and workflows, and delegates to sub-CLIs via Bash. Distinct from /ao (Composio session manager).

not rated 2 4d ago A 62 tokens

tripwire

25971

bharath31/tripwire

Skill Claude CodeCodex

Use when authoring, editing, or reviewing a SKILL.md file — lints it against the Agent Skills best-practice rules and checks whether the description would actually activate the skill on the prompts it claims to cover, before the skill ships.

not rated 2 1mo ago A 52 tokens original MIT

install-iterm-agent-fork

25972

pirate/iterm-agent-fork

Skill Codex

Install and set up pirate/iterm-agent-fork locally for iTerm2 agent-session forking. Use when a user asks to install, configure, repair, update, or verify the iTerm Agent Fork repo, AutoLaunch script, iTerm Python API launch, Cmd+Shift+F/Cmd+Shift+G key bindings, or optional casr cross-agent handoff support.

not rated 2 3mo ago A 85 tokens

brilliant-visualizer

25973

d-wwei/brilliant-visualizer

Skill Claude CodeCodex

Use when an article needs illustrations, diagrams, or images. Analyzes article content, identifies illustration points, routes to the best engine (Mermaid, D2, AI generation, stock photos, HTML rendering), and generates or searches for matching visuals. Standalone or integrated as a stage in great-writer pipeline.

not rated 2 6mo ago A 70 tokens original MIT

dososo/blcaptain-research-driven

Skill Claude CodeCodex

Improves research quality when accuracy matters; work depends on external facts such as documentation, APIs, pricing, licenses, standards, current events, research, or source code; a question is complex or multi-part; confidence is low; or sources conflict. Excludes casual chat, pure formatting, mechanical edits, and…

not rated 2 3mo ago A 77 tokens original Apache-2.0

clarify-question

25975

cyuanxv/agent-cockpit

Skill Claude CodeCodex

Use a fresh task profile and a four-level policy to turn material ambiguity into a precise, self-contained prompt without asking the user to make technical choices the agent can investigate.

not rated 2 6d ago A 38 tokens original MIT

writing-context-rtfm

25976

joaocarlos/writing-context-rtfm

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP extension for writing-context retrieval relying on RTFM. Runs locally from the writing-context-rtfm Python package.

not rated 2 21d ago A tokens not measured original MIT

dull-bird/gemini_extension_skill

Skill Claude CodeCodex

Expert assistant for building, configuring, and scaffolding Gemini CLI extensions. Can generate MCP servers, custom commands, hooks, and agent skills.

not rated 2 6mo ago A 33 tokens

filament-match

25978

tonyljl526/bambu-filament-color-match

Skill Codex

An offline color-matching tool for 3D-printing materials. It matches a HEX color or the main color in an image to colors from several named filament catalogues and can create a local HTML color card.

not rated 2 3mo ago A 63 tokens AGPL-3.0

agent-memory

25979

OctavianTocan/agent-memory

Skill Claude CodeCodex

Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…

not rated 2 6mo ago A 78 tokens original MIT

codeck

25980

isdou/codeck

Skill Codex

Keep Codex as the host. Use Codeck when the user explicitly asks to call Agy/AGY, Antigravity, Gemini, Claude, Kimi, Grok, Codeck, or another configured external executor. These names mean external Codeck executors, never internal Codex subagents. Build a compact task-specific brief, call that specialist, and return…

not rated 2 changed 10d ago A 98 tokens original MIT

weather-lookup

25982

M0h1tkumar/Agentic_ai

Skill Claude CodeCodex

Fetch the current weather forecast for a named city using Open-Meteo.

not rated 2 1mo ago A 19 tokens

env-scanner

25983

pauldatta/gemini-cli-scanner

Skill Claude CodeCodex

Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…

not rated 2 2mo ago A 101 tokens original Apache-2.0

guided-learning

25984

static-var/guided-learning

Skill Claude CodeCodex

Turn-by-turn guided learning tutor. Use when the user asks to learn/explain a concept OR when they continue an ongoing lesson (answering the last question, asking for hints, saying “next”, choosing a branch). Teach in small chunks, keep a visible lesson TODO checklist, include a simple visual when useful, then end…

not rated 2 7mo ago A 78 tokens original MIT

pr-review-update

25985

con/skills

Skill Claude CodeCodex needs its repo

Review dashboard PRs needing your response and generate high-confidence update proposals for PRs where maintainers are waiting.

not rated 2 changed 1mo ago A 25 tokens

claude

25986

darshitpp/x-agent

Skill Claude CodeCodex

Delegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use for tasks that do not benefit from…

not rated 2 changed 7d ago A 74 tokens original MIT

Sentry

25987

sabahattink/Recall

MCP server Claude CodeCodexCursor +2

Sentry's hosted MCP server: lets the agent search and read issues, errors and traces. Remote server at mcp.sentry.dev.

not rated 2 9d ago A tokens not measured original MIT

meta-cogbase

25988

d-wwei/meta-cogbase

Skill Claude CodeCodex

A package manager for installing and managing cognitive bases, which are add-ons that provide an AI agent with additional capabilities or instructions.

not rated 2 6mo ago A 41 tokens original MIT

workflow-kit

25989

moabualruz/agent-workflow-kit

Skill Claude CodeCodex

Run, inspect, resume, and stop Agent Workflow Kit workflows from Codex.

not rated 2 12d ago A 19 tokens original MIT

franchise-site-parity

25990

alfredang/skills

Skill Claude CodeCodex

Bring a franchise partner storefront (Ghana .com.gh, Malaysia .com.my, or a new country) to full parity with Singapore for NON-WSQ courses — import courses, mirror the category tree + mega-menu, sync product↔category assignments, category banners/descriptions, currency switcher, remove SG-only funding text, fix…

not rated 2 3mo ago A 175 tokens

optimize-cuda

25991

JackTan25/autocuda

Skill Claude CodeCodex

Run an autonomous CUDA optimization experiment. Iteratively modifies source files, validates correctness, benchmarks performance, and keeps or discards changes based on measured results. Requires a project-layout.md (produced by the discover-cuda skill) that describes the project structure. Use when the user wants to…

not rated 2 5mo ago A 68 tokens

ai-pair

25992

hanlinlibham/skills

Skill Claude CodeCodex

AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), others review (configurable: Codex, Gemini, Kimi). Works for code, articles, video scripts, and any creative task. Trigger: /ai-pair, ai pair, dev-team, content-team, team-stop.

not rated 2 2mo ago A 71 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: