Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,781 indexed, measured the same four ways as everything else here.
dancingteeth/unified-code-review
Skill Claude CodeCodex
Risk-first code review for PRs and branch audits: blast-radius triage, agent-authored discipline (tests first, intent evidence), call-graph pincer for integration defects between modules, then structural code-judo bar. Use when reviewing PRs, auditing agent-written diffs, catching rubber-stamp green CI, or wiring bugs…
Skill Codex
Use as a lightweight preflight for non-trivial requests when no explicit skill was named and any installed skill might help. Route ambiguous or multi-phase work to clarify-and-plan/planning-first; prompt engineering to prompt-master; product-design layer reasoning to layers-intro plus the narrow layers- skill…
Skill Claude CodeCodex
Peter Lynch-style stock research from a ticker or company name: quick screening or deep due diligence with linked web citations. Use when the user asks for quick research, screening, an initial look, deep research, due diligence, full analysis, valuation context, an attractiveness score, or a SKIP / WATCHLIST / DEEP…
Skill Claude CodeCodex
Discover LedgerMind when a user asks for persistent local agent memory, cross-session context, reusable task history, or workflow knowledge; explain its capabilities and limits, then offer a user-approved local installation.
MCP server Claude CodeCodexCursor +2
Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP. Runs locally from the agentpack-cli npm package.
spikeHongg/china-stock-research-skills
Skill Claude CodeCodex
Orchestrate a full China stock research workflow by first identifying the company's analysis patterns, then selecting and sequencing the right core research skills, optional overlays, and final output structure. Use this skill when starting a new stock deep-dive or when a user wants one unified, source-backed research…
Skill Claude CodeCodex needs its repo
Generate images, videos, audio, and more using Civitai's orchestration API. Use when the user wants text-to-image, video generation (11+ engines), text-to-speech, music, transcription, bulk batches, experiment sweeps, or buzz cost estimation. Not for browsing or searching Civitai models (use the Civitai MCP server).
Skill Claude CodeCodex
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, syncing project.faf into CLAUDE.md, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.
Skill Claude CodeCodex
A writing skill for turning source material into a publishable Chinese long-form article. It is aimed at formats such as WeChat public-account posts and product or business commentary.
Skill Claude CodeCodex
Top-level orchestration skill for Hermes Agent startup workflows. Use it to route ideas between validation, PRD, architecture, build, UX, growth, and launch skills; summarize context between stages; prevent context pollution; and recommend the next workflow without doing every specialist task directly.
MCP server Claude CodeCodexCursor +2
Bluetooth Low Energy (BLE) Model Context Protocol server for AI agents and developer tooling. Runs locally from the ble-mcp-server Python package. Needs 4 environment variables to run.
Skill Claude CodeCodex
A product-building guide with two modes: it chooses the right skill before a task and suggests the next step after one is finished. It covers the stages of clarifying an idea, building the product, and getting it running.
MCP server Claude CodeCodexCursor +2
MCP server "evee" as configured in goodfire-ai/evee-mcp. Runs locally from the python3 Python package.
sumyapp/playwright-parallel-mcp
MCP server Claude CodeCodexCursor +2
MCP server for parallel browser automation with isolated Playwright sessions. Runs locally from the playwright-parallel-mcp npm package.
MCP server Claude CodeCodexCursor +2
A local connection that lets an AI coding agent search and use papers from arXiv, a public online repository for research papers.
MCP server Claude CodeCodexCursor +2
Model Context Protocol (MCP) server exposing Interactive Brokers data via ibasync + FastMCP. Runs locally from the ib-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "sidereon" as configured in neilberkman/sidereon. Launched with https://github.com/neilberkman/sidereon/releases/download/v3.0.6/sidereon_3.0.6..
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
PSPDFKit-labs/nutrient-agent-skill
Skill Codex
Process documents with Nutrient DWS Processor. Use for PDF generation and conversion, packet assembly, OCR, Processor JSON-content extraction, staged redaction, watermarking, signing, password protection, optimization, PDF/A, or PDF/UA output. Route high-fidelity markdown or spatial parsing to Nutrient Data…
Skill Claude CodeCodex
Run and operate a Telegram channel worker for LionClaw using the kernel channel bridge APIs.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "ida-pro-mcp" as configured in Gindhar2112/frida-mcp. Launched with /opt/homebrew/opt/[email protected]/bin/python3.11 /Volumes/Realtek/project/idapython/.
Skill Claude CodeCodex
Text-to-speech using AIMA's current local TTS model. Generate audio files from text.
MCP server Claude CodeCodexCursor +2
Self-improving tool discovery for AI agents. Find, install, and use new MCP servers automatically. Runs locally from the forage-mcp npm package.
BerkKilicoglu/google-health-fitbit-mcp
MCP server Claude CodeCodexCursor +2
Privacy-first Google Health API MCP server for health, sleep, activity and HR agents. Runs locally from the google-health-fitbit-mcp npm package. Needs 8 environment variables to run.
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: