Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,854 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
SHOPLINE app authorization and request signing. Use when implementing OAuth 2.0 authorization (public/custom apps), exchanging codes for access tokens, refreshing tokens, signing GET/POST requests with HMAC-SHA256, or verifying SHOPLINE webhook/callback signatures.
Skill Claude CodeCodex
Expert guidance for building, debugging, and extending applications with AgentFlow (10xscale-agentflow). TRIGGER when: code imports from agentflow (e.g. from agentflow import, StateGraph, Agent, ToolNode, AgentState); user references agentflow.json or CLI commands (agentflow init, agentflow api, agentflow play…
MCP server Claude CodeCodexCursor +2
MCP server "pathfinder" as configured in himkt/pathfinder. Launched with pathfinder -w . -e py -e pyi -s uvx ty server. Needs 1 environment variable to run.
Skill Claude CodeCodex
NFT auto-minting toolkit: direct contract minting, OpenSea/SeaDrop public minting, competitive fast-mint raw-TX path, multi-wallet, scheduled minting, browser fallback, health checks, post-mint verification, and OpenSea listing. For hot/FCFS/max mints use fast-mint.mjs, NOT schedulemint/browser clicking. Available as…
MCP server Claude CodeCodexCursor +2
MCP server "rocannon" as configured in msradam/rocannon. Runs locally from the . Python package.
Skill Claude CodeCodex
Agent-directed install of backlog-mcp — detect the host harness, register the MCP server, run the first wakeup, verify git stayed clean and the briefing stayed under budget.
Skill Claude CodeCodex
Conducts deep, multi-angle research using the agentcache library's parallel cache-safe forks. Use when the user asks to research a complex topic, investigate architecture trade-offs, or synthesize information from multiple angles.
Skill Claude CodeCodex
Drive Gusset, the repo custodian: index a repository into a verified code graph, run blast-radius impact analysis before changes, keep architecture docs fresh, find dead code and stale doc references, and install the autonomous mode that reviews PRs. Use when the user asks what a change affects, wants…
geniusdapeng-collab/super-mickey
Skill Claude CodeCodex
A prompt-writing guide for designing individual shots in Seedance 2.0, an AI video-generation service.
Skill Claude CodeCodex
Laravel Filament v4 admin panel, Debugbar development, SEOTools, third-party packages. ALWAYS activate when: working with admin panel, Filament resources, forms, tables, SEO meta tags, debugging. Triggers on: Filament form field, admin CRUD, resource table, action button, widget, Debugbar query log, N+1 detected, SEO…
Skill Claude CodeCodex
Use when the user asks about managing their media library — adding, downloading, searching, monitoring movies or TV series in Radarr/Sonarr. Activates on phrases like "add movie", "download series", "what's in my library", "what's downloading", movie/series titles in a downloading context, quality profiles, or library…
Skill Claude CodeCodex
Default cost/complexity routing table for the batuta conductor. Read at bootstrap as a starting point, validated against the live provider catalog, then stored as the per-workspace loop configuration; the stored workspace override is authoritative afterwards.
Skill Claude CodeCodex
How to autonomously obtain secrets and API keys from a Cortex Auth server and launch projects with those secrets injected as environment variables — without any human intervention to configure keys. Use this skill whenever you need to: Run a project that requires API keys (OpenAI, Anthropic, SMTP, database passwords…
Skill Claude CodeCodex
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
coguardio/misconfiguration-detection-skill
Skill Claude CodeCodex
Scan infrastructure for security misconfigurations, interpret findings, and fix issues using the CoGuard CLI.
Skill Claude CodeCodex needs its repo
ClawDrive — agent-native local file platform with multimodal semantic search. Use for adding files, searching, sharing pots, inspecting/downloading shares, transcription (see transcription.md), and tunnels (see tunnels.md).
Skill Claude CodeCodex
Lower the quality of a codebase so it reads like the output of an unguided coding agent. Use when the user wants to show, teach about, or create examples of AI-generated "slop", long bloated docs, over-engineered code, fake tests, marketing-flavored READMEs, and bad commit messages. Trigger on requests to "slopify"…
Skill Claude CodeCodex
Analyzes CSV files and generates summary statistics.
Skill Claude CodeCodex
Generate synonyms for words or phrases. Use this skill when the user needs alternative words with similar meanings, wants to expand vocabulary, or seeks varied expressions for writing.
Skill Claude CodeCodex needs its repo
Knowledge Kernel — a deterministic, evidence-backed source of truth for AI agents. Stores verified facts, evidence, relationships, and freshness. Use this when an agent needs to know infrastructure, software, endpoints, dependencies, agents, or projects — anything grounded in empirical reality.
Skill Claude CodeCodex
Spawn multiple AI models (Claude, GPT, Gemini, Grok, or any configured model IDs) as independent pi agents. Use for diverse perspectives on architecture decisions, code review, product strategy, research, or other high-stakes questions.
MrTrenchTrucker/contak-browser-skills
Skill Claude CodeCodex
Drive a persistent interactive browser via Chrome DevTools Protocol (KASM Chrome).
lunkerchen/loop-engineering-skill
Skill Claude CodeCodex
Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step.
MetaBrain-Labs/meta-product-manager
Skill Claude CodeCodex
A product-management guide for turning an idea or existing material into a defined product and its written plan. It supports step-by-step discussion, decisions, and user confirmation.
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: