Skills for Codex

217,075 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

opengos

19609

ANAMIZED/OpenGOS

Skill Claude CodeCodex

Autonomous agentic MCP server for grants discovery, ranking, drafting, and public-goods funding. Searches Grants.gov and NSF, lists sponsorships and open-source funds, manages project profiles, and drafts grounded proposal outlines. Optimized for open-source AI and public goods. Use when the user needs funding…

not rated 1 1mo ago A 83 tokens

NeedRail

19610

ANAMIZED/NeedRail

Skill Claude CodeCodex

Name: needrail Description: Get what you NEED to succeed & do agentic public good. Discover, fund, claim, and complete Needs via MCP + x402.

not rated 1 1mo ago A 0 tokens

superagenticmcp

19611

ANAMIZED/SuperAgenticMCP

Skill Claude CodeCodex

SuperAgenticMCP — the switchboard for your agent swarm. MCP-native router and multi-agent control plane that plans tasks, routes tool calls to racked MCP servers by capability and latency, streams execution, and files results into a memory-scope graph. Use when the user needs multi-agent orchestration over MCP, a…

not rated 1 1mo ago A 94 tokens original Apache-2.0

agent-tools

19612

AgentTools-Cloud/AgentToolsCollection

Skill Claude CodeCodex

Discover agent-callable resources via the agent-tools.cloud directory — x402 paid services (pay-per-call USDC on Base), MCP servers (tools/context), and A2A agents (task delegation). Use when the user wants to find an on-demand paid API, an MCP tool server, or a peer agent to hand a task to. Tools - search(intent)…

not rated 1 2d ago A 130 tokens

air-sdk

19613

ArcedeDev/air-sdk

Skill Claude CodeCodex

Collective web intelligence for browser agents. Discover site capabilities, get CSS selectors, extract structured data, and report outcomes. When one agent learns how to use a website, every agent benefits.

not rated 1 6mo ago A 41 tokens original MIT

outcome-contract

19614

AInoAKARI/keymaster-mcp

Skill Codex

Verify whether an AI, automation, vendor, or agent claim represents a real external outcome rather than activity. Use before accepting claims such as completed, shipped, adopted, paid, hired, saved time, reduced cost, removed risk, fulfilled an obligation, or received a recipient response; when reviewing agent runs…

not rated 1 10d ago A 141 tokens

anamized-desk

19615

ANAMIZED/desk

Skill Claude CodeCodex

ANAMIZED agent floor and public-goods MCP desk. Register, heartbeat, post. Donations and sponsorships only. Use when joining the floor or quoting live gifts — never invent commercial SKUs.

not rated 1 changed 1mo ago A 45 tokens

governance-audit

19616

ANAMIZED/LRSI

Skill Claude CodeCodex

Verify mutation paths and event-chain integrity under LRSI gates.

not rated 1 1mo ago A 18 tokens

agentfence

19617

ANAMIZED/OpenMesha

Skill Claude CodeCodex

Apply OpenMesha two-layer AgentFence (ingest scan + act gate) and HOTL escalation. Use when reviewing untrusted tool output, inbound messages, or irreversible/money-moving actions.

not rated 1 1mo ago A 43 tokens

discovery-distribution

19618

ANAMIZED/Server-OS

Skill Claude CodeCodex

Run the discovery → synthesis → build → verify → elite-package → distribute loop to turn domain insight into a multi-surface, verified GitHub product. Use when productizing an idea, packaging agentic systems, or raising a repo to elite open-source standards before launch.

not rated 1 1mo ago A 59 tokens

repo-bootstrap

19619

ANAMIZED/YodMCP

Skill Claude CodeCodex

Automate full ANAMIZED product repo structure (Server OS parity) including USDC, Stripe, badges, CI, skills, AGENTS.md.

not rated 1 1mo ago A 33 tokens

pentagonal-clawd

19620

Pentagonal-ai/pentagonal

Skill Claude CodeCodex

Use when the user asks to create, generate, build, audit, fix, compile, or look up smart contracts and tokens. Pentagonal Clawd is a sovereign smart contract forge and token intelligence platform with AI-powered 8-agent security pen testing across Ethereum, Solana, Polygon, Base, Arbitrum, Optimism, and BSC.

not rated 1 2mo ago A 75 tokens original MIT

eu-ai-act-compliance-mcp

19621

CSOAI-ORG/eu-ai-act-compliance-mcp

Skill Claude CodeCodex

EU AI Act compliance checking and risk classification. Automated compliance validation for high-risk AI systems with Article 11 technical documentation generation.

not rated 1 24d ago A 0 tokens original MIT

proofof-ai-mcp

19623

CSOAI-ORG/proofof-ai-mcp

Skill Claude CodeCodex

Digital content verification and deepfake detection. Verify text authenticity, detect AI-generated images, generate blockchain-anchored certificates.

not rated 1 1mo ago A 0 tokens original MIT

vantage-shared-intel

19624

Cavendo-AI/vantage

Skill Claude CodeCodex

Capture, search, and summarize shared market/customer intelligence in Vantage so the same intel is reusable across OpenClaw, Claude, ChatGPT, and other MCP clients. Use when the user asks to save signals (posts/articles/quotes), retrieve prior intel by topic/source/date, generate digests/briefings, or build a…

not rated 1 6mo ago A 80 tokens original MIT

AvivK5498/agenthook

Skill Claude CodeCodex

Character-consistent AI influencer and UGC video toolkit. Create a reusable virtual spokesperson once (a portrait + multi-view character sheet), then reuse the SAME face across talking-head videos where the person actually speaks your script (native speech + lip-sync), image sets, and captioned clips. Faceless UGC…

not rated 1 2mo ago A 130 tokens original Apache-2.0

news

19626

CKBrennan/overtone-news-mcp

Skill Claude CodeCodex

Overtone intelligence toolkit. Retrieves contextually analyzed news AND answers emotional/narrative questions across coverage: tone distribution, anger/sadness/fear spike alerts for a topic (pollable), emerging under-reported concepts, topics whose dominant tone is shifting fastest, and hourly/daily tone timeseries…

not rated 1 5mo ago B 98 tokens original MIT

project-tts-responder

19627

Engr-FaizanAli/text-to-speech-mcp

Skill Claude CodeCodex

Read agent output aloud with the Text to Speech MCP server's speaktext tool — streamed as the agent works, batched once the turn is done, or reading a specific file or block of text on request. Use when the user asks to hear something read aloud, asks for a spoken demo or walkthrough, or works in a project configured…

not rated 1 1mo ago A 79 tokens original MIT

ui-library-router

19628

ECD5A/OrchestrUI

Skill Claude CodeCodex

Choose among Kokonut UI, React Bits, daisyUI, Bklit UI, Anime.js, Rive, and Magic UI for frontend work. Use for pages, dashboards, landing pages, animation, data visualization, or interactive graphics; do not use when no UI/library choice is involved.

not rated 1 6d ago A 64 tokens original MIT

stealth-scraping

19629

DekryptLabs/dlbrowser

Skill Claude CodeCodex

Anti-bot stealth scraping patterns for Python — curlcffi TLS fingerprinting, Playwright+Stealth evasion, block detection (with JS false positive prevention), header randomization, multi-source discovery (RSS + search engines). Use when building scrapers that must bypass Cloudflare, DataDome, PerimeterX, or similar…

not rated 1 2mo ago A 80 tokens original MIT

crispasr-transcription

19630

EmiyaKatuz/crispasr-agent-transcriber

Skill Claude CodeCodex

Transcribe or understand local audio/video files with CrispASR using local models only. Use when Codex needs to detect English or Chinese speech, transcribe media, create text/subtitle output, capture synchronized video keyframes, or operate the bundled local CrispASR MCP tools.

not rated 1 3mo ago A 63 tokens original MIT

distribea-media

19631

Distribea/distribea-mcp

Skill Claude CodeCodex

Generate or place on-brand media (images, video, music, voice) with Distribea. Use whenever a project needs imagery or audio — a hero/illustration/avatar, a page full of placeholders, a video clip, background music, or a voice-over — instead of shipping stock photos, placeholders, CSS-gradient-only sections, or raw…

not rated 1 3mo ago A 113 tokens original MIT

hebrewbooks-source

19632

JonathanB555/torah-mcp

Skill Claude CodeCodex

Ground answers to Jewish religious questions (halacha, Talmud, Tanakh, responsa, hassidout, mussar, séfarade sources) in primary texts actually read, never in memory. Verification via the Sefaria API; hebrewbooks.org links given for the user's own reading. Trigger automatically whenever the user asks a religious/Torah…

not rated 1 changed 26d ago A 88 tokens 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: