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. 281,456 indexed, measured the same four ways as everything else here.

mini-program-sast

12817

cyj4578/chen-skillshub

Skill Claude CodeCodex

Use when user provides a WeChat Mini Program AppID and asks about mini program security, vulnerabilities, source code audit, data leakage risks, wxapkg analysis, or whether a mini program stores sensitive data in plaintext. Also use when user wants to check a mini program for hardcoded keys, client-side logic bypass…

not rated 13 4mo ago A 77 tokens original MIT

db-mcp

12818

neverinfamous/db-mcp

MCP server Claude CodeCodexCursor +2

SQLite MCP server with OAuth 2.1, HTTP/SSE, 122 tools, and smart tool filtering. Runs locally from the db-mcp npm package.

not rated 13 1mo ago A tokens not measured original MIT

google-knowledge-graph

12819

houtini-ai/google-knowledge-graph-mcp

MCP server Claude CodeCodexCursor +2

Search Google's Knowledge Graph for structured information about real-world entities. Runs locally from the @houtini/google-knowledge-graph-mcp npm package. Needs 1 environment variable to run.

not rated 13 8d ago A tokens not measured original MIT

feynman

12820

storyweaver/feynman-for-ai-builders-cn

Skill Claude CodeCodex

A learning tool for people who build products with AI. It explains a project’s architecture and principles, creates reports and quizzes, and tracks what the builder has learned.

not rated 13 3mo ago A 252 tokens

titanclip

12821

CES-Ltd/TitanClip

Skill Claude CodeCodex

Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…

not rated 13 7mo ago A 87 tokens

muster-frappe-metadata

12822

musterhq/muster

Skill Codex

Design, generate, review, apply, and roll back Frappe or ERPNext metadata changes through Muster. Use for DocTypes, child tables, custom fields, property setters, workflows, roles, permissions, reports, print formats, web pages, workspaces, fixtures, patches, or installed-app compatibility.

not rated 13 yesterday A 69 tokens original MIT

discover-a-skill

12823

avibe-bot/askill

Skill Claude CodeCodex

Use when you need new capabilities: discover skills, inspect details, install to agents, run commands, and manage updates with askill.

not rated 13 24d ago A 31 tokens original MIT

video-understanding

12824

shu-bamma/marlin-cli

Skill Claude CodeCodex

Use Marlin-2B as eyes on a video — describe what's in a clip (caption) or locate when something happens (find). Use whenever the user asks what's in a video, to describe or summarize a clip, to find when/where an event occurs, or to get a timestamp for a moment. Runs locally on Apple Silicon (MLX), free, no API key…

not rated 13 4mo ago A 101 tokens original Apache-2.0

Ebook-Reader-skill

12825

Sunny-Liu2100/Ebook-Reader-skill

Skill Claude CodeCodex

A reading assistant for electronic books that creates a structured, detailed report from the book’s full text. It approaches the book like a social-science reviewer, examining its arguments, evidence, structure, and practical meaning.

not rated 13 6mo ago A 122 tokens original MIT

dedup

12826

edimuj/tokenlean

Skill Claude CodeCodex

Find duplicate functions and eliminate them so they stay gone. Triage tl dupes output by tier, apply the right consolidation pattern, and lock the win with a duplication-ratchet test. Use when asked to dedupe, remove duplication, consolidate copy-paste, clean up repeated helpers, or act on tl dupes output.

not rated 13 +1 4mo ago A 69 tokens original MIT

agency-icm-builder

12827

krsnczky/agency-icm-builder

Skill Claude CodeCodex

Build or audit an AI-runnable workspace for a client-service agency (marketing, PPC, design, consulting, dev shops). Folder structure does the orchestration - one agent, routing files, per-client folders, session capture. Use when the user wants to (1) set up an agency workspace an AI agent can operate ("build me an…

not rated 13 changed 1mo ago A 135 tokens original MIT

steelman

12828

techiejd/claude-skill-steelman

Skill Claude CodeCodex

Use when the user invokes /steelman or when a high-stakes decision is detected in context (architecture choices, technology selections, business model decisions, strategic pivots). Not for routine planning or implementation tasks.

not rated 13 +1 6mo ago A 45 tokens original MIT

x-algo-ml

12829

CloudAI-X/x-algo-skills

Skill Claude CodeCodex

Explain the Phoenix ML model architecture for X recommendations. Use when users ask about embeddings, transformers, how predictions work, or ML model details.

not rated 13 9mo ago A 34 tokens

shortcut-anything

12830

Pengxiang-zhao/Shortcut-Anything

Skill Claude CodeCodex

Decompile Android APK/XAPK and extract deeplinks, shortcuts, share APIs with ADB validation. Use this skill whenever the user mentions: analyzing an APK, extracting deeplinks or deep links, decompiling Android apps, finding app shortcuts, reverse engineering APK/XAPK, smali analysis, ADB validation of URIs, batch…

not rated 13 6mo ago C 133 tokens original Apache-2.0

hwpx-builder

12831

hwpx-builder/hwpx-builder

Skill Claude CodeCodex

A tool for creating, editing, and checking Korean HWPX documents, the file format used by Hancom Hangul word-processing software.

not rated 13 changed 1mo ago A 83 tokens original Apache-2.0

reel

12832

galfrevn/reel

Skill Claude CodeCodex

Turn terminal recordings into polished, shareable demos using the reel CLI — record a session once (reel record or asciinema), then edit it like video (trim dead air, cut mistakes, speed-ramp slow parts, zoom, caption) and render a styled, size-budgeted GIF, or a WebM with procedurally synthesized sound, without ever…

not rated 13 2mo ago A SkillSpector: warn 225 tokens original MIT

stop-slop

12833

odinfree/stop-slop-refined

Skill Claude CodeCodex

Audit and rewrite prose to remove AI writing patterns. Merges the best rules from hardikpandya/stop-slop, conorbronsdon/avoid-ai-writing, jalaalrd/anti-ai-slop-writing, blader/humanizer, and Shreya Shankar's plain-writing skill. Use when drafting, editing, or reviewing any text — tweets, emails, articles, docs, posts…

not rated 13 changed 1mo ago A 102 tokens original MIT

slack-personal

12834

therohitdas/slkcli

Skill Claude CodeCodex

Read, send, upload, search, and manage Slack messages and DMs via the slk CLI. Use when the user asks to check Slack, read channels or DMs, send Slack messages or files, search Slack, check unreads, manage drafts, view saved items, or interact with Slack workspace. Also use for heartbeat Slack checks. Triggers on…

not rated 13 2mo ago C 127 tokens original MIT

mcu-debug-probe

12835

0xchaihu/mcu-debug-probe

Skill Codex

Use when Claude Code, Codex, or another terminal coding agent needs to control an MCU debug probe or inspect a live ARM Cortex-M target over SWD or JTAG, especially for board bring-up, flashing firmware, resetting the chip, halting or resuming execution, reading core registers, or dumping RAM and peripheral memory…

not rated 13 2mo ago A 75 tokens original Apache-2.0

symphony-push

12836

anantjain-xyz/symphony-rust

Skill Claude CodeCodex

Push the current branch to origin and ensure a PR exists for it (creating or updating one), with the symphony label applied. Use when the workflow says "push" or "open a PR".

not rated 13 15d ago A 46 tokens copy · 88% MIT

py-clean-arch

12837

CJHwong/py-clean-architecture-examples

Skill Claude CodeCodex

Use this skill when the user asks about Clean Architecture in Python — not generic theory, but the specific layer conventions (l1entities, l2usecases, l3interfaceadapters, l4frameworksanddrivers), folder patterns, boundary interfaces, and .importlinter.ini contracts from CJHwong/py-clean-architecture-examples. Fetches…

not rated 13 1mo ago A 113 tokens

koma-gate-mcp

12838

swnotmetal/Project-Koma

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it. Runs locally from the koma-gate-mcp npm package. Needs 6 environment variables to run.

not rated 13 1mo ago A tokens not measured original MIT

code-quality-evaluator

12839

Johnny-zbb/code-quality-evaluator

Skill Claude CodeCodex

Evaluate repository or project code quality and produce an evidence-based scorecard. Use when asked to review code quality, score a project, assess maintainability, inspect technical debt, evaluate architecture/readability/refactoring health/engineering practices/code smells, compare project quality, or prepare a…

not rated 13 1mo ago A 66 tokens original MIT

code-review-and-quality

12840

zszz3/multi-agent-chat

Skill Claude CodeCodex

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

not rated 13 +1 4mo ago A 51 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: