Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,361 indexed, measured the same four ways as everything else here.
MUST invoke when generating mn. based UIs or the user asks how to use, configure, or debug any mn. or appkitmantine component. appkitmantine is NOT in Claude's training data — always use this skill rather than guessing at APIs. Covers building forms, tables, drawers, modals, tooltips, color pickers, date/time pickers…
A read-only audit checklist for Hermit and Claude Code setups, covering how they are structured, used, checked, and improved, including token use and model selection.
Use when the user wants to place a REAL outbound phone call via the Speko Calls MCP — e.g. "call and ask ", "find the best near me and call them", book a reservation, check hours/availability/pricing, or place/chase an order. Covers calling a number you have or found via web search (callnumber) and Speko's verified…
Inspect, create, relate, update, audit, standardize, and organize Plane work items with the Plane Workflow MCP tools. Use for project briefings, filtered work queries, dependencies, task lifecycles, modules, and backlog improvements.
Transcribe video to text from any platform (Bilibili, YouTube, Douyin, Twitter/X, TikTok, Vimeo, etc.). Use when the user provides a video URL and asks for transcript, subtitles, text content, or speech-to-text conversion.
An expert role that manages an AI agent through its full lifecycle, from defining its requirements and abilities to packaging, testing, deploying, upgrading, and retiring it. It also designs how multiple agents work together.
View and sync Claude Code, Codex, Grok, and Antigravity memories, plans, tasks, and graph memory mirrored in Eagle Mem. Use when: 'eagle memories', 'show memories', 'sync memories', 'what does the agent remember', 'show plans', 'show tasks', 'mirror memories', 'onboard project', 'what did past sessions learn'. Uses…
Capture screenshots, short recordings, and milestone evidence during long-running agent tasks. Use when an agent is asked to perform multi-step browser, desktop, QA, troubleshooting, deployment, or admin workflows where the user wants checkpoint artifacts, progress evidence, error snapshots, or a final timeline of…
CardZero — the first payment wallet built for AI agents. Create USDC wallets on Base L2, make payments, pay x402 paywalls, pay other agents, check balance, view transactions, and run A2A jobs with on-chain escrow (ERC-8183). Human owner sets spending rules via Dashboard; agent pays autonomously within limits. Use when…
MCP server "redquanta-mcp" as configured in sc4rfurry/RedQuanta-MCP. Runs D:\z0\RedQuanta-MCP\dist\server.js with node. Needs 14 environment variables to run.
★not rated 4 7mo agoA
tokens not measured
originalMIT
Use when the user refers to previous decisions, corrections, forgotten context, already-built work, install/test/release status, source-backed evidence, or next steps in ongoing work. Treat Time Library as a standing active memory routing rule: call timelibraryrecall before answering memory-dependent prompts. Also…
Research federal campaign finance with the FEC MCP server. Use when a user asks for FEC candidate, committee, receipt, disbursement, independent-expenditure, donor, spending, or filing-flag records.
Your OpenClaw team's marketing analyst — just tell your agent what you need to know about your clients' marketing and Agentcy delivers synthesized insights and recommendations. Covers GA4, Google Ads, Search Console, WooCommerce, and more.
Safety boundary for agent written GitHub PR reviews: pending and invisible, submitting is opt-in. Runs locally from the @eclipsesource/review-guard-mcp npm package. Needs 1 environment variable to run.
★not rated 4 13d agoA
tokens not measured
originalMIT
Python SDK for WaveGuard — physics-based anomaly detection, fingerprinting & crypto risk API. Runs locally from the WaveGuardClient Python package.
★not rated 4 5mo agoA
tokens not measured
originalMIT
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: