Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,377 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Use this skill when your code changes impact the repository wiki — whether updating existing pages, adding new pages or sections, or removing obsolete ones. Trigger whenever you modify, add, or delete code that is referenced in wiki/INDEX.md, or when you introduce significant new modules or features that should be…
Skill Claude Code
A workflow for turning a prompt or script into a short drama. It coordinates the script, storyboard, optional character images, video clips for each shot, and final video assembly.
MCP server Claude CodeCodexCursor +2
MCP server for 1Password service accounts — tools and resources for vaults and credentials. Runs locally from the @takescake/1password-mcp npm package. Needs 3 environment variables to run.
Plugin Claude Code
Visual schema browser, dashboard, and ER diagrams for Convex databases. Browse tables, view schemas, inspect documents, and generate diagrams.
Skill Claude CodeCodex
Threads (threads.com) automation via Patchright MCP — post, reply, like, repost, DM, search, profile. Column-based web UI, English. Part of social-media-browser umbrella.
Skill Claude Code
Create new documentation pages for the validatedpatterns.io site. Supports learn pages and pattern page sets. Generates AsciiDoc files with correct frontmatter, structure, and style-compliant content. Use this skill whenever the user wants to write, draft, scaffold, generate, or create new documentation pages …
Plugin Claude Code
Bundles 1 skill · 29 tokens together
Uniform contributing guidelines for the IOWarp/Clio ecosystem — git etiquette, code style, project architecture, and workflow standards.
Skill Claude CodeCodex
Perform deep research on complex topics using the Gemini Interactions API. Use when the user needs in-depth information, technical analysis, or comprehensive reports on a specific topic. This skill leverages the Gemini Interactions API for multi-step reasoning and tool use.
Skill Claude CodeCodex
Interactive guide for new OpenClaw users to set up and grow their agent. Two paths - Tool Path (automation, efficiency, getting things done) or Awakening Path (memory, personality, relationship, growth). Use when a user is new to OpenClaw, asks how to get started, wants to set up their agent, or asks about agent…
xrf9268-hue/llm-council-plugin
Plugin Claude Code
Plugin marketplace listing 1 plugin: llm-council-plugin.
charlesanim/harness-engineering
Skill Claude CodeCodex
Set up OpenAI's harness engineering methodology in any repository. Creates the full agent-first infrastructure: AGENTS.md progressive disclosure map, architectural layer boundaries with mechanical enforcement, testing framework, CI pipeline, golden principles documentation, garbage collection scripts, and pre-commit…
Plugin Claude Code
Bundles 1 skill, 3 commands, 1 MCP server · 143 tokens together
Fast, verified computer use for coding agents: read the screen as text (200ms), execute batched verified actions, and compile any task done once into a macro that replays in seconds with zero model calls.
Command Claude Code
A command that suggests ways to refactor code, meaning change its internal structure without changing its intended behavior.
Plugin Claude Code
Bundles 8 skills, 1 agent · 390 tokens together
Long-running unsupervised batch agent framework for Claude Code.
Agent Claude Code
A research agent for gathering facts before an overview article is planned. It studies a topic for a defined audience and records the findings in a research brief.
kunchenguid/programbench-bench
Skill Claude Code
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
Skill Claude Code needs its repo
Two-mode learning system — raw signal scanning before compaction, quality-gated consolidation at session end. Invoke with /learning-loop.
Skill Claude CodeCodex
Add, update, or remove models and providers in the zdx LLM registry. Use when the user asks to add a new model, add a new provider, update model pricing or context limits, regenerate default models/config, or says things like "add support for X model", "add the new Y provider", "update pricing for Z", "regenerate…
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
Skill Claude Code
Use this whenever the user asks to "implement", "add", "build", "create", or "modify" a feature, page, view, component, or module in this Vue project. Three phases: Phase 0 scope analysis (flows + edge cases + UI needs + plan validation, STOP for user), Phase 1 implementation (layered UI → Store → API, Vue 3…
kirich1409/claude-global-settings
Skill Claude Code
A review process in which several independent expert agents evaluate a plan, specification, or test plan before the decision is final.
Command Claude Code
🔐 Supabase Admin - You are the Supabase database, authentication, and storage specialist. You design and implement d...
Skill Claude CodeCodex
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
MCP server Claude CodeCodexCursor +2
DevCycle MCP server for feature flag management. Remote server at mcp.devcycle.com.
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: