Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 380,968 indexed, measured the same four ways as everything else here.
Plugin Claude Code
Bundles 8 skills, 4 commands, 1 MCP server · 1,008 tokens together
Static code map for LLM agents. /map parses the repository with tree-sitter into MAP.md and map.json (every file, function, signature, type, and call edge) without spending model tokens; an 18-tool MCP server (searchcode, outline, querysymbol, getcallers, workset, impactedtests, ...) answers structural questions fr.
Plugin Claude Code
Bundles 1 skill · 26 tokens together
Vibgrate AI Context for Claude Code: a local-first MCP server with a deterministic code map (impact, navigation, search) plus version-correct, drift-annotated library docs. No API key.
MCP server Claude CodeCodexCursor +2
Retrieval platform for AI agents — 14 search providers, 12-step content extraction, dead URL recovery, site capture, and local corpus storage. One API. Runs locally from the argus-search Python package. Needs 8 environment variables to run.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 113 tokens together
Develop, test, and operate SAP ABAP systems through local ADT connections, governed HTTP, OIDC, and transport assurance.
MCP server Claude CodeCodexCursor +2
Discover and install Aura UI Blade components for Laravel, Livewire and Tailwind CSS 4. Remote server at aura-ui.com.
Skill Claude CodeCodex
Use when about to state a number, claim two programs are equivalent, claim a speedup, or state a complexity — codecalc computes these exactly instead of estimating them, and this file says when calling is mandatory and how results must be reported.
Skill Claude CodeCodex
ACMI is a universal architectural framework for giving AI agents persistent, real-time context. It replaces fragmented, multi-table database joins with a single, lightning-fast Key-Value engine (Upstash Redis) optimized specifically for LLM context windows.
openephemeris/openephemeris-MCP
Skill Claude CodeCodex
Generate and interpret astrocartography (ACG / locational astrology) — planetary lines, parans, crossings, local space, and how moving to a different location changes a chart. Use when someone asks about astrocartography, ACG, the best place to live, what city is best for their career or love life, relocation, or…
Skill Claude CodeCodex
Works with: Claude Code, Cursor, and Cline have adapter docs in this repo. Any MCP client can call the two tools below.
MCP server Claude CodeCodexCursor +2
Manage social media DMs and scheduled posts from your AI assistant, across 12 platforms. Runs locally from the @crmsolid/mcp-server npm package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server to read, inspect and troubleshoot codebase symbols. Runs locally from the @p1va/symbols npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Local MCP server exposing iGPSport cycling data with server-side training metrics (NP/IF/TSS/CTL/ATL/TSB). Runs locally from the igpsport-mcp Python package. Needs 5 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for Yandex Webmaster — SEO, indexing, search queries (Russia). Runs locally from the @theyahia/yandex-webmaster-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping. Runs locally from the gia-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Agent gateway for Index discovery, AN Score evaluation, and Resolve governed execution. Runs locally from the rhumb-mcp npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
Query a database through the valv MCP and turn the results into charts in a single self-contained HTML file (Chart.js). Use whenever the user asks to chart, graph, plot, visualize, or "show me" data from their database — e.g. "visualize revenue by month", "chart signups per week", "graph orders by status". Remembers…
MCP server Claude CodeCodexCursor +2
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP. Runs locally from the llm-usage-mcp Python package.
Skill Claude Code
Manage AgentLair email channel access — edit sender allowlists and set policy. Use when the user asks to allow or block email senders, check who can reach them, or change access policy.
Skill Claude CodeCodex
Analyze recent charging sessions and return 1–3 concrete recommendations to lower cost, preserve battery, or improve charging habits.
MCP server Claude CodeCodexCursor +2
Quote, book, track, and manage LTL, FTL, cargo van, and box truck freight via 17 MCP tools. Runs locally from the warp-agent-mcp npm package.
Skill Claude Code
Orchestrate a software task end-to-end in Claude Code. Use this whenever the user describes building, fixing, reviewing, planning, or shipping something in a project — e.g. "build the X MVP", "add feature Y", "review this PR", "diagnose this bug", "plan this out" — and especially when resuming work after a context…
yushiran/Academic-Figure-Figma-CC-Skills
Skill Claude CodeCodex
Use when the user wants a paper figure (framework, pipeline, architecture, method overview) drawn, rebuilt, or refined as an editable vector in Figma via Claude Code — including reproducing a candidate/reference image (e.g. studio-pro C01-C04) at exact print size. Also use when the user needs to set up or fix the…
k-vaca/prompt-engineering-skill
Skill Claude CodeCodex
Write, review, and optimize professional prompts for large language models. Use this skill whenever the user asks to write, draft, design, improve, fix, debug, review, or optimize a prompt, system prompt, prompt template, meta-prompt, or agent instructions; asks why a prompt "isn't working" or gives inconsistent…
pencil20388-eng/browser-automation-skills
Skill Claude CodeCodex
Connect Google's Chrome DevTools MCP to AdsPower antidetect browser profiles. This lets AI coding agents (Claude Code, Cursor, Codex CLI) control fingerprint-isolated browser sessions through natural language.
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: