24,990 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
alphaparkinc/genpark-amazon-author-ranker
Skill Claude CodeCodex
Author Performance Ranker. Tracks and analyzes creator/author performance across multi-year datasets based on feedback and frequency.
Cursor rule Cursor
Japanese-language rules for managing data quality using DMBOK principles, a data-management framework. They cover quality dimensions, measurement, root-cause analysis, improvement, and monitoring.
Skill Claude CodeCodex
Generate, refine and export data visualizations using plotnine. Use this skill when the user asks to create plots or charts with plotnine. Also use when customizing themes, applying colorblind-safe palettes, reshaping data for plotting with plotnine, or saving figures to PNG/PDF/SVG/JPEG.
SoujiOkita98/industry-map-maker-skill
Skill Claude CodeCodex
Maintain a single-file interactive industry map (index.html) with evidence-tiered relationships, clean visual hierarchy, strong logo quality, USD-normalized market text, and publish-ready repository hygiene.
claude-office-skills/claude-office-plugin
Plugin Claude Code
Bundles 26 skills, 14 commands, 8 agents, 2 MCP servers · 1,644 tokens together
An AI assistant for WPS Office spreadsheets, the spreadsheet program in WPS Office. It can analyse and clean data, work with formulas, format cells, create charts, and build templates.
Plugin Claude Code
Bundles 2 skills · 23 tokens together
A context-efficient interface for LangSmith observability and evaluations.
Plugin Claude Code
Bundles 3 skills, 2 hooks · 79 tokens together
Track the environmental cost of your AI coding sessions.
Plugin Claude Code
Bundles 1 skill · 93 tokens together
Analyze Claude Code token usage and costs from local session data. Breaks down spend by project, model, and day. Includes model recommendations showing which sessions didn't need Opus. Analyzes MCP server overhead, tool result sizes, and context bloat. Provides personalized cost savings recommendations with estimated…
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for Amplitude. Runs locally from the amplitude-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "cubejs-mcp-server" as configured in zsembek/Cube.js-MCP-server. Runs locally from the cubejs-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP server "plotly-mcp-claude" as configured in arshlibruh/plotly-mcp-cursor. Runs locally from the plotly-mcp-claude Python package.
IBM/ibm-storageinsights-mcpserver
MCP server Claude CodeCodexCursor +2 ✓ vendor
MCP server "si-mcp-server-oss" as configured in IBM/ibm-storageinsights-mcpserver. Runs locally from the si-mcp-server-oss Python package.
MCP server Claude CodeCodexCursor +2
MCP server "stockreport-mcp" as configured in jamesdingAI/stockreport-mcp. Runs locally from the stockreport-mcp Python package.
blue-sky-exist/observability-mcp
MCP server Claude CodeCodexCursor +2
MCP server "observability-mcp" as configured in blue-sky-exist/observability-mcp. Runs locally from the observability-mcp Python package.
Skill Claude CodeCodex
A skill for generating pyecharts chart examples in Python. It covers basic, combined, three-dimensional, and newer ECharts chart types, with examples that can render to HTML or notebooks.
MCP server Claude CodeCodexCursor +2
StackHawk MCP Server for Security Analytics and Developer Integration. Runs locally from the stackhawk-mcp Python package. Needs 1 environment variable to run.
petar-nauka/ai-visibility-skill
Skill Claude CodeCodex
Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not. Use this skill whenever someone asks about AI visibility, AEO, GEO, answer engine optimization, generative engine optimization, "AI SEO", brand mentions or share of voice in AI…
Plugin Claude Code
Bundles 13 skills · 1,726 tokens together
Agent skills that teach Claude, Cursor, and other AI agents to read web analytics like a senior analyst. Diagnose traffic changes, judge channel quality, and read funnels without the usual rookie mistakes. Works with any analytics source; first-class support for Clamp MCP.
Skill Claude CodeCodex
Diagnose sales activity capture quality across a team and grade it A through F. Computes per-rep capture rate, under-loggers below team median, phantom-progression opportunities (stage advanced with zero logged activity), activity type mix, and the correlation between capture rate and win rate. Use when the user asks…
SeongwoongCho/adaptive-harness
Plugin Claude Code
Bundles 4 skills, 4 commands, 29 agents, 5 hooks · 1,020 tokens together
A self-improving harness router and evaluator for Claude Code — automatically selects, evaluates, and evolves the right harness for your repo.
Plugin Claude Code
Bundles 40 commands, 15 agents, 1 MCP server · 1,015 tokens together
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
Skill Claude CodeCodex
Weekly self-improvement curation pass for Wick's site-rules. Reads the public stats (with per-cause failure breakdown), the residential probe traces, and the currently-published rules, then reasons about anomalies the deterministic harness can't resolve on its own — sites that fail EVERY tested strategy, high…
Skill Codex
Work with local VibeTime agent-coding activity data. Use when Codex needs to inspect VibeTime time tracking, agent activity, project/session/turn history, token usage, cost attribution, hook health, local SQLite data, data quality, dirty data, or safe database cleanup. Default to VibeTime CLI summaries for ordinary…
Thewhey-Brian/claude-statusline-hud
Plugin Claude Code
Bundles 1 skill, 1 hook · 37 tokens together
A comprehensive, btop-inspired statusline HUD for Claude Code with context, rate limits, session stats, system vitals, and configurable presets.
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: