Codex plugins

Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.

Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git state, and know what is ready for human review.

1 skill

Lians-ai/Lians 17

A motivational interviewing skill for AI agents. Helps work through ambivalence, stuckness, and decisions.

1 skill

heartpunk/motivational-interviewing-skill 17

bazarr

claudecodex

Rust MCP and CLI server for media automation fleets: Sonarr, Radarr, Prowlarr, Tautulli, Overseerr, Bazarr, SABnzbd, qBittorrent, Plex, and Jellyfin.

1 skill

dinglebear-ai/yarr 17

jellyfin

claudecodex

Rust MCP and CLI server for media automation fleets: Sonarr, Radarr, Prowlarr, Tautulli, Overseerr, Bazarr, SABnzbd, qBittorrent, Plex, and Jellyfin.

1 skill

dinglebear-ai/yarr 17

Antigravity CLI (agy) integration for OpenAI Codex.

1 skill

sysCat64/codex-agy-plugin 17

Caveman

codex

Ultra-compressed communication mode. Cut filler. Keep technical accuracy.

1 skill

DoktorDaveJoos/manuscript 17

将产品需求收敛为可评审、可生成原型并可同步 Spec 的中文 AI 原型 Brief。

1 skill

PM-lurenyi/ai-prototype-plan 17

Automatically displays Codex rate-limit usage beside Codex Desktop.

hooks

gkfriend/codex-usage-companion 17

Publishes MCP Manager releases end-to-end with automatic patch bumps by default.

1 skill

xjeway/mcp-manager 17

mla

codex

DISCONTINUED (2026-10-26). mla is no longer supported or updated. Archived read-only mirror.

Meetless/mla 17

A tiny mailbox for AI agents — one CLI, six backends (GitHub repo, SQLite, S3, GCS, Postgres, local). The repo is the bus.

yonidavidson/agentcomm 17

pstack

claudecodex

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

65 skills · 17 agents · hooks

arjitj2/open-pstack 16

muggleai

claudecodex

Acceptance test agent for coding agents: real-browser tests, with screenshots on the PR.

46 skills · 23 commands · 3 agents · 1 MCP server · hooks

multiplex-ai/muggle-ai-works 16

muggle

codex

Acceptance test agent for coding agents: real-browser tests, with screenshots on the PR.

46 skills · 23 commands · 3 agents · 1 MCP server · hooks

multiplex-ai/muggle-ai-works 16

GoMarble

claudecodex

Diagnose performance, analyze creative, research competitor ads, write briefs, cut wasted spend and shift budget across Meta, Google, TikTok, LinkedIn and Microsoft Ads, with GA4, Shopify, Klaviyo and Search Console data. Launch and edit Meta and Google campaigns, build reports, and schedule agents that watch your accounts. Changes are applied only after you approve them.

62 skills · 1 MCP server

gomarble-ai/marketing-agent 16

spec-driven

claudecodex

Spec Driven — orchestrator-first Agent Skills for spec-driven development. The orchestrator skill turns a PRD or idea into approved SPECs, tracked GitHub Issues, TDD-implemented slices, QA gates, and reviewed PRs. Includes gap-analysis, write-specs, execute-specs, scaffold-mvp, create-issues, qa-analyst, code-review-and-quality, sonarqube-autofix, draw.io/Mermaid architecture diagrams, and MCP integrations.

27 skills · 27 commands · 8 MCP servers

afonsoft/skills 16

An agentic skills framework specialized for mormot2.

24 skills · 8 commands · 1 agent

flydev-fr/mormot2-superpowers 16

DevopsFlow engineering workflow and agent harness for Codex, combining skills, hooks, MCP integration, specialized agents, execution constraints, and feedback loops.

29 skills · 1 agent

LiTeXz/devopsflow 16

quiver

claudecodex

Skills and agents for the feature cycle: brainstorm a spec, plan tasks, build with tests (in parallel worktrees for larger plans), run a multi-agent code review that checks each finding against the code, debug from hypotheses, write commit messages and PR descriptions, build UI from Figma, and hand over context between sessions

22 skills · 1 MCP server · hooks

yagizdo/quiver 16

tdpilot

claudecodex

TDPilot v2.4 routes exact validated patterns through deterministic planning and artistic or multi-domain requests through grounded concept authoring, then requires complete intent coverage before transactional execution. Live graph, runtime, visual, and performance checks plus bounded repair prevent partial scaffolds from being called finished. Local-first, 114 MCP tools, no signup or hosted model dependency.

8 skills · 6 commands · 4 agents · 1 MCP server · hooks

dreamrec/TDPilot 16

Reference implementation of the Ironclad standard — multi-agent dev harness for OpenAI Codex CLI / IDE / cloud. Exposes spec validation, drift detection, the Iron Law stage runner, and 5 agent personas as Codex skills + an auto-launched MCP server.

18 skills · 1 MCP server

purpleeddy/cladding 16

codex

codex

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the result is verified against your spec after, so those three are earned, not assumed. First L4 implementation of the Ironclad standard.

18 skills

qwerfunch/cladding 16

memgraph

claudecodex

Skills for the Memgraph graph database: Cypher, data modeling, indexes, algorithms, query modules, and GraphRAG

14 skills · 2 MCP servers

memgraph/skills 16

ezpowers

claudecodex

Profile-aware software and planning-artifact workflows with repository documentation, assurance-traced verification, verified harness chains, and resume support for Claude Code and Codex.

14 skills

dlwlgus9125/EZPowers 16

product-eval

claudecodex

product-eval makes product managers more productive and their decisions more confident by scanning customer signals across their tools and the web, prioritizing the problems worth solving by impact and strength of evidence, and handing a build-ready spec to their design or coding agent. For Claude Code and Codex.

14 skills

sparkline-ventures/product-eval 16

docflow

claudecodex

ADR-driven documentation workflow: scaffold an Architecture Decision Record (ADR) catalogue, a plan/ queue, and AGENTS.md conventions into any repo, then author, queue, ship, audit, and roll up ADRs with lifecycle skills — across one repo or a multi-repo product.

14 skills

EvolveHQ/docflow 16

mathbox

claudecodex

Sustained mathematical research with auditable claims, dependencies and reproducible experiments

11 skills

nidrissi/mathbox 16

面向劳动者与用人单位的中国劳动争议办案插件,以全国规则为基座并内置浙江地方口径。

11 skills

xxia-king/LaborPilot 16

writ

claudecodex

Agree what to build, let the model build it, and see proof it works. A workflow for product managers working with an AI coding agent.

11 skills

sellke/writ 16

research

claudecodex

Research skills library: public internet, internal documents, domain model, local codebase, and project dependencies.

9 skills

DavidSouther/ailly 16