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. 281,305 indexed, measured the same four ways as everything else here.

devops-mcp

13153

wangkanai/devops-mcp

MCP server Claude CodeCodexCursor +2

Dynamic Azure DevOps MCP Server for directory-based environment switching. Runs locally from the @wangkanai/devops-mcp npm package.

not rated 12 7mo ago A tokens not measured original MIT

banana-image-mcp

13154

zengwenliang416/banana-image-mcp

MCP server Claude CodeCodexCursor +2

A production-ready MCP server for AI-powered image generation using Gemini 3 Pro Image and Gemini 2.5 Flash Image with intelligent model selection. Runs locally from the banana-image-mcp Python package.

not rated 12 8mo ago A tokens not measured original MIT

claude-find

13155

Cavinooo/claude-find

MCP server Claude CodeCodexCursor +2

Pull Deep Memory from across your Claude Code Sessions — when you need it. Runs locally from the claude-find npm package.

not rated 12 5mo ago A tokens not measured original MIT

freshcontext

13156

PrinceGabriel-lgtm/freshcontext-mcp

MCP server Claude CodeCodexCursor +2

Context integrity for AI agents: evaluate freshness, confidence, provenance, and decision readiness. Runs locally from the freshcontext-mcp npm package.

not rated 12 1mo ago A tokens not measured original MIT

adamsjack711-ux/pkgxray

Skill Claude CodeCodex

Audit supplied evidence for AI coding-agent extensions, Codex plugins, Claude Code extensions, and MCP servers using concrete supply-chain security indicators.

not rated 12 4d ago A 36 tokens original MIT

shipcheck

13158

lohani-mohit/shipcheck

Skill Claude CodeCodex

Senior-QA review of a code change before you ship it. Sizes the diff, then launches QA reviewers — a regression hunter ("does this break anything that already worked?") and a change reviewer ("does this actually do what it claims, including edge cases?") — and consolidates ONE evidence-based SIGN OFF / SIGN OFF WITH…

not rated 12 changed 1mo ago A 162 tokens original MIT

duanyongping-perspective

13159

anneheartrecord/duanyongping-perspective

Skill Claude CodeCodex

A role-based thinking guide based on the public views and decisions of Chinese investor Duan Yongping. It tells the assistant how to assess investments, businesses, life choices, and uncertainty in his concise style.

not rated 12 7mo ago A 172 tokens original MIT

teamwork-collaborate

13160

JinPLu/Teamwork

Skill Codex

Use when the user explicitly wants to discuss, brainstorm, compare options, or make a material preference decision, or when unclear intent needs guided clarification; do not use for clear execution or a single discoverable detail.

not rated 12 2mo ago A 49 tokens original MIT archived

balise-handoff

13161

mrstev3n/balise-skills

Skill Claude CodeCodex

Audits and prepares selected Figma screens, components, prototypes, and flows for developer handoff using explicit scope, source-of-truth mapping, evidence levels, risk-based gates, open-decision ownership, and acceptance criteria. Use when a design needs a Ready for dev review, implementation-readiness verdict…

not rated 12 2mo ago A SkillSpector: pass 87 tokens original Apache-2.0

mainframe

13162

gtwatts/mainframe

Skill Claude CodeCodex

Pi shell policy, explicit task checkpoints, and runtime status. Use for Mainframe status, shell-policy questions, or resuming checkpointed project work.

not rated 12 changed 1mo ago A SkillSpector: pass 33 tokens original MIT

squish

13163

michielhdoteth/squish-memory

Skill Claude CodeCodex

ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember'…

not rated 12 changed 7d ago A SkillSpector: pass 157 tokens original MIT

turborepo

13164

wpank/ai

Skill Claude CodeCodex

WHAT: Turborepo monorepo build system - caching, task pipelines, and parallel execution for JS/TS projects. WHEN: User configures turbo.json, creates packages, sets up monorepo, shares code between apps, runs --affected builds, debugs cache misses, or has apps/packages directories. KEYWORDS: turborepo, turbo.json…

not rated 12 9mo ago A 111 tokens

context-align

13165

fending/context-engineering

Skill Claude CodeCodex

Checks AGENTS.md and SKILL.md files against the actual codebase for drift. Surfaces references to packages, directories, commands, or patterns that no longer match reality.

not rated 12 7mo ago A 38 tokens original MIT

llm-wiki-kb

13166

chengjialu8888/LLM-Wiki-KB

Skill Claude CodeCodex

Build and maintain personal knowledge bases as LLM-compiled markdown wikis, inspired by Andrej Karpathy's LLM Wiki pattern. The LLM incrementally ingests raw sources (articles, papers, repos, images) into a structured, interlinked wiki of .md files — with summaries, entity pages, concept pages, cross-references, and a…

not rated 12 7mo ago A 219 tokens original MIT

wiki-lint

13167

schub-tech/llm-ideation-wiki

Skill Claude CodeCodex

Run semantic wiki lint beyond structural link checks. Use when the user asks to audit, lint, health-check, find stale claims, find unsupported claims, check provenance, or identify contradictions in the wiki.

not rated 12 changed 1mo ago A 44 tokens original MIT

know-before-act

13168

yj972/know-before-act

Skill Claude CodeCodex

Reduce decision-relevant uncertainty before execution. Use at the start of tasks where missing goals, constraints, context, or preferences could materially change the plan; ask at most one high-information question at a time and otherwise proceed with reasonable assumptions.

not rated 12 3mo ago A 51 tokens original MIT

daemonicai/teambuilder

Skill Claude CodeCodex

Dispatch pending tasks from an OpenSpec change's tasks.md to the right Teambuilder persona in fresh subagents. Use from /opsx:apply (or openspec-apply-change) when Teambuilder personas are present in .claude/agents/.

not rated 12 +1 6mo ago A 64 tokens original MIT

webman

13170

zjkal/webman-skill

Skill Claude CodeCodex

Expert skill for the webman framework (a long-lived, in-memory PHP framework based on workerman). Covers routing, controllers, middleware, database/Redis, custom processes, timers, coroutines (v2), plugin development, and guarding against memory leaks and cross-request state pollution under the resident process model.…

not rated 12 3mo ago A 111 tokens original MIT

verify

13171

changzhiai/claude-code-patch

Skill Claude CodeCodex

Verify a code change does what it should by running the app.

not rated 12 7mo ago A 13 tokens original MIT

deslop

13172

skyzer/deslop-the-copy

Skill Claude CodeCodex

Deslop, humanize, edit, or audit AI-sounding, robotic, generic, corporate, or ChatGPT-like copy while preserving the writer's voice.

not rated 12 3mo ago A 35 tokens original MIT

obai-strategy

13173

sixteen-dev/obai

Skill Claude CodeCodex

Quantitative equity strategy design and backtesting via the OBaI backtest MCP server (http://localhost:8007/mcp). Use when the user wants to build, test, backtest, optimize, refine, repair, or compare a trading strategy, run walk-forward robustness validation, inspect trade logs, or follow up on a backtest job.…

not rated 13 changed 29d ago A 121 tokens

cortivex-nodes

13174

AhmedRaoofuddin/Cortivex

Skill Claude CodeCodex

Complete reference for all Cortivex pipeline node types with configurations and usage guidance.

not rated 12 7mo ago A ✓ AI review 22 tokens

hitl-protocol

13175

rotorstar/hitl-protocol

Skill Claude CodeCodex

HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website…

not rated 12 changed 1mo ago B 163 tokens original Apache-2.0

prolog-reasoner

13176

rikarazome/prolog-reasoner

MCP server Claude CodeCodexCursor +2

LLM-powered logical reasoning with Prolog - Calculator for logic. Runs locally from the prolog-reasoner Python package.

not rated 12 6mo ago A tokens not measured original MIT

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: