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. 272,426 indexed, measured the same four ways as everything else here.

linear

16273

stoa-platform/stoa

MCP server Claude CodeCodexCursor +2

One of 4 in .mcp.json

MCP server "linear" as configured in stoa-platform/stoa. Launched with bash -c LINEAR_API_KEY=$(security find-generic-password -a linear-mcp -s linear-.

not rated 7 2mo ago A tokens not measured original Apache-2.0

comic-sol

16274

wenn-id/comicsol

Skill Claude CodeCodex

Create, storyboard, render, resume, repair, and export finished original manga/anime comics from a short prompt, prose story, pasted narrative, or local .txt/.md source. Use when the active agent should produce editable plans, consistent panel PNGs, composed page PNGs, a PDF, manifest, and transparent QA report…

not rated 7 2d ago A 75 tokens original MIT

agent-comm-hub

16275

liuboacean/agent-comm-hub

Skill Claude CodeCodex

A local communication hub that lets separate AI agents exchange messages, share context, coordinate tasks, and review suggestions.

not rated 7 changed 3d ago A 54 tokens original MIT

collattice

16276

MrBildo/collattice

Skill Claude CodeCodex

Operate a Collattice kanban board through its Model Context Protocol (MCP) endpoint — connecting, authentication, the board model, identifier rules (board-level reads need a board GUID, not a slug), the Markdown a board renders, and the full tool reference: reading and creating cards, moving and reordering lanes…

not rated 7 changed yesterday A SkillSpector: pass 111 tokens original MIT

mcp-server-builder

16277

archimedes-run/omniHarness

Skill Claude CodeCodex

Scaffold, generate, and test a FastMCP server that can be used as an MCP tool provider. Handles API wrapper, database connector, and custom tool templates.

not rated 7 10d ago A 39 tokens original MIT

代码调试

16278

jianchen08/Agent-os-open

Skill Claude CodeCodex

A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.

not rated 7 +2 changed 28d ago A SkillSpector: pass 82 tokens original Apache-2.0

bonsai-mcp

16279

Show2Instruct/bonsai-mcp

MCP server Claude CodeCodexCursor +2

MCP server "bonsai-mcp" as configured in Show2Instruct/bonsai-mcp. Runs locally from the /path/to/bonsai-mcp Python package. Needs 3 environment variables to run.

not rated 7 1mo ago A tokens not measured original MIT

angular-patterns

16280

NicoGenti/opencode-orchestrator-kit

Skill Claude CodeCodex

Angular structure, component, and state-management conventions to apply when writing or reviewing Angular code. Load before implementing or reviewing any angular.json-based feature.

not rated 7 +1 28d ago A 33 tokens original MIT

agile-v-verifier

16281

Agile-V/agentic_agile_v

Skill Claude CodeCodex

Independent review behavior for verifier sessions in the Agile-V process.

not rated 7 18d ago A 18 tokens CC-BY-SA-4.0

pr-review

16282

desikai-lab/Marrow

Skill Claude CodeCodex

Use when opening, reviewing, or merging a pull request. Covers pre-PR checks (linting, tests, branch naming), PR description requirements, and post-merge cleanup. Not for code review commentary or architecture decisions — use the relevant role guidelines for those.

not rated 7 today A 59 tokens original MIT

explainer-video

16283

PouyanJay/lunaris

Skill Claude CodeCodex

Turn any topic into a 3Blue1Brown-style animated explainer video (MP4) via a five-stage pipeline of factual grounding, scene-contract planning, Manim code generation, render plus visual-QA verification, and assembly. Works for ALL topics, whether mathematical (algorithms, physics, statistics), scientific, technical…

not rated 7 17d ago A 213 tokens AGPL-3.0

herd

16284

Kampe/Herdforge

Skill Claude CodeCodex

Operate the Herdforge self-forging software factory with Kaneo, Herdr, isolated worktrees, verification, review, and cleanup.

not rated 7 +1 10d ago A 30 tokens original MIT

prompt_control_lab

16285

VeraPyuyi/prompt_control_lab

Skill Claude CodeCodex

Guard and improve prompts before expensive Codex, IDE, or CLI agent work. Use when a prompt is vague, broad, risky, costly, or should be optimized before implementation.

not rated 7 6d ago A 40 tokens

llm-d-incubation/llm-d-skills

Skill Claude CodeCodex needs its repo

Configure and deploy Workload Variant Autoscaler (WVA) for llm-d inference deployments. Guides users through namespace selection, WVA repo location, configuration (with presets or custom values), deployment via Makefile + kubectl apply, and verification. Produces a reusable deployment script.

not rated 7 1mo ago A 68 tokens original Apache-2.0

design-md-creator

16287

iFurySt/DESIGN.md

Skill Codex

Create or refine a DESIGN.md from a public website URL, then use that design system to build and open a standalone HTML page based on either a reference URL or the user's requested page and content. Visually validate the HTML and feed reusable corrections back into DESIGN.md. Use when the user wants a DESIGN.md, an…

not rated 7 2mo ago A 99 tokens original MIT

tmux-remote-linux

16288

lenovobenben/tmux-remote-linux

Skill Claude CodeCodex

Use this whenever the task requires operating, inspecting, testing, or diagnosing a remote Linux environment through a user-prepared tmux pane, especially when you would otherwise run ssh. Replace direct ssh attempts with this skill unless the user explicitly asks for direct SSH. Covers bastion hosts, Kubernetes…

not rated 7 changed yesterday B 76 tokens original MIT

collapse-r

16289

fastverse/skills

Skill Claude CodeCodex

Expert guidance for the collapse R package (v2.x) — fast, class-agnostic data transformation and statistical computing in R, and the core of the fastverse. Covers the Fast Statistical Functions (fmean/fsum/fmedian/fmode/fnth/fndistinct … with their g/w/TRA arguments), grouping objects (GRP, qF, qG, group, fgroupby…

not rated 7 1mo ago A 426 tokens

process-interview

16290

bmbouter/redhat-agents

Skill Claude CodeCodex

Interview the user about their Jira workflow and generate a local jira-workflow.md config file that all agents reference.

not rated 7 28d ago A 25 tokens original Apache-2.0

wise-image-flow

16292

WiseWong6/wise-skills

Skill Codex

A Chinese-language workflow for creating images from articles, content blocks, or presentation outlines. It turns content into image prompts, selects suitable sizes and layouts, and can send prompts to available image-generation tools or APIs.

not rated 7 changed yesterday A SkillSpector: pass 111 tokens original MIT

teleagent-chat

16293

T786279007/teleagent-mcp

Skill Claude CodeCodex

A connector for chatting with TeleAgent, a macOS desktop AI application from China Telecom that provides cloud-hosted TeleAI models through the OpenCode/ACP runtime.

not rated 7 +1 3mo ago A 125 tokens

research-social-insights

16295

oyorf/personal-workbench-skills

Skill Codex

A research workflow for studying recent Chinese-language AI discussions across public websites and authorized social-media pages.

not rated 7 +1 1mo ago A 102 tokens original MIT

21st-registry

16296

21st-dev/codex-plugin

Skill Claude CodeCodex

Publish your own work to 21st.dev and manage it from the terminal with the 21st CLI (@21st-dev/cli): publish a React component to a team library, publish a CSS theme or a template listing, edit / unpublish / delete your published items, list and reopen existing component work, and read/replace your public profile page…

not rated 7 15d ago A 259 tokens copy · 100% Apache-2.0

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: