Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 275,249 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
MUST be used when editing code that carries a hard-won lesson, a deliberate decision, or a correctness invariant. Enforces inline @agent: notes recorded next to the code, so the next agent reads the reason for free and does not repeat the mistake. Load whenever writing or modifying non-trivial logic. Paired with…
ky-ji/xie-saining-research-taste-skills
Skill Codex
Use when evaluating AI/ML research ideas, choosing research directions, framing problems, planning experiments, improving research taste or paper storytelling, resisting trend-following, or applying Saining Xie's interview-derived views on visual intelligence, world models, research culture, and scientific taste.
Skill Claude CodeCodex
Integrate Solana SPL token payments (USDC/USDT) into the Toppio payment provider system. Use this skill when implementing the Solana payment provider, handling SPL token transfers, building sweep logic for Solana, or debugging Solana-related payment issues.
Skill Claude CodeCodex
ClickHouse development best practices for schema design, query optimization, insert strategy, and cluster management.
Skill Claude CodeCodex
Use when applying 2d animation best practices.
Skill Claude CodeCodex
Trade, create, and manage Solana prediction markets on Baozi.bet — autonomous betting, market creation, affiliate earnings, and portfolio tracking.
BioTender-max/one-person-pharma
Skill Claude CodeCodex
Build a complete AI-powered protein design pipeline with cloud GPU compute (Modal) and automated wet-lab validation (Adaptyv Bio). Enables dry-wet closed-loop iteration for antibody/binder discovery at a fraction of traditional CRO costs ($1.7K for 3 rounds). Use this skill when: (1) Designing a protein/antibody…
CaptainDarkHeart/claude-skills-starter-kit
Skill Claude CodeCodex
Read this when the user asks to summarize something, wants the key points, or uploads a document to condense. Use it for long-form content such as articles, documents and reports. It produces a concise summary.
Skill Claude CodeCodex
Launch Chromium/Chrome via Playwright MCP (chrome-hook) with network hooks, multi-slot dual browsers (account A + B without logout), cookie/storage persistence, authenticated API requests, and Plan A real-browser CDP attach for strict bot protection. Use when the user wants browser automation without Browser MCP…
Skill Claude CodeCodex
Pre-install security audit for agent skills on Base. Scans SKILL.md + manifest for prompt-injection and secret-exfiltration, audits referenced contracts (unlimited approvals, upgradeable owner, honeypot), and validates x402 endpoints. Returns a deterministic risk verdict (ALLOW/WARN/DENY) with evidence. Read-only…
Skill Claude CodeCodex
Build a generic-installable CLI tool with its companion SKILL.md so any agent (Vellum, Claude, GPT, etc.) can pick it up and use it. Use when the task is "ship a CLI for service X" or "wrap API Y in a tool agents can call." Out of scope for one-off internal scripts that don't need agent discovery, and for skills that…
marco77x/openclaw-youtube-pipeline
Skill Claude CodeCodex
Carica video su YouTube con thumbnail. Usa questa skill per pubblicare video.
Skill Claude CodeCodex
Run one bounded ESRA review after a major architecture or skill change, repeated failure, or an explicit full-cycle request. Select only the meta-skills justified by observable evidence; skip routine successful work. Triggered by "orchestrate evolution", "run full ESRA cycle", "improve self-development cycle", "hermes…
Skill Claude CodeCodex
A paragraph-by-paragraph review process for Japanese documents that identifies claims, supporting reasons, connections, and opposing views. It is designed to clarify reasoning, not to guess what the writer intended.
sheng3233836/vibe-coding-standards
Skill Claude CodeCodex
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing…
Skill Claude CodeCodex
Use when reviewing model gateway routing, provider fallback, budget limits, rate limits, or agent cost controls.
Skill Codex
Execute a lightweight governed GitHub Issue-to-PR delivery loop with an optional independent goal-prompt preflight, focused implementation, clickable commit and PR links, staged 3+2+1+4-minute Codex review waits, comment resolution, human-readable diff evidence, controlled merge or staging, Issue reconciliation, and…
Skill Claude CodeCodex
Master context engineering principles for building production-grade AI agent systems with effective context management, multi-agent architectures, and memory systems.
MCP server Claude CodeCodexCursor +2
A local MCP server that helps an AI read complex documents. It runs from the Python package named doc-mcp-server through the uvx command.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-eshipz" as configured in KavinVetrivel/eshipz-mcp. Runs locally from the mcp-eshipz Python package.
wukaka/camoufox-jsreverser-mcp
MCP server Claude CodeCodexCursor +2
MCP server "camoufox-jsreverser-mcp" as configured in wukaka/camoufox-jsreverser-mcp. Runs locally from the camoufox-jsreverser-mcp npm package.
MCP server Claude CodeCodexCursor +2
Ableton Live integration through the Model Context Protocol. Runs locally from the ableton-mcp Python package.
MCP server Claude CodeCodexCursor +2
Minimal cross-platform MCP server for text-to-speech using Microsoft Edge TTS. Runs locally from the mcp-edge-tts Python package.
MCP server Claude CodeCodexCursor +2
MCP server for optional SSOT pull-worker control-plane coordination. Runs locally from the ssot-mcp Python package.
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: