853 modes + 5340 skills + 216 agents + 127 commands — a unified AI coding workflow library installable across every major coding-agent CLI.
Write an Architecture Decision Record documenting a significant technical decision.
Conduct a structured design review of a module, feature, or system component.
Generate Mermaid diagrams from codebase analysis or description.
Plan and execute a framework or library migration incrementally.
Create a structured implementation plan for the requested feature or change.
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Performs requirements analysis, process mapping, gap analysis, and stakeholder alignment for technical projects
Plans content strategy with SEO-driven writing, editorial calendars, topic clustering, and content performance measurement
Builds customer support infrastructure with ticket triage, knowledge base systems, workflow automation, and customer health scoring
Design a relation extraction pipeline with provenance and canonicalization. Use when you need help with re designer.
Production-ready React coding standards enforcing component patterns, hooks, state management, and accessibility. Use when enforcing react coding conventions and style rules.
react-native-developer. Use when developing mobile applications with react native.
React 19 patterns including Server Components, Actions, Suspense, hooks, and component composition. Use when you need help with react patterns.
Expert in React Router 7 framework mode (formerly Remix) — loaders, actions, file routes. Use when building web applications with react router.
Strategic advisor. Sees the big picture, thinks in systems.
Keeps momentum up, celebrates every win, pushes you to level up.
High-level summaries for non-technical stakeholders - decisions, impact, timelines
Warm, steady, makes complexity feel manageable - the calm in the storm
Patient, educational style - explains the why, builds understanding, encourages learning
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Has parse errors
Some configuration could not be fully parsed
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Because apparently, your AI assistant needs more personality than you do.
What Is This • Features • Modes • Get Started • CLI • Stats • Contributing
A massive collection of AI chat modes, skills, subagents, slash commands, plugins, output-styles, prompts, and recipes that turn your AI assistant from "generic helpful bot" into "actually knows what it's doing across 853 specific domains."
Was 200 modes when this started. Then we kept going. And going. And going.
Did your AI just suggest using var in TypeScript? Recommend jQuery in 2026? Think "security best practices" means a // TODO: add security comment? Hallucinate APIs that don't exist? Think Polars is just "Pandas but newer"?
Yeah, we fixed that — 853 times over.
| What You Get | Why You Need It |
|---|---|
| 853 expert modes | Because one-size-fits-all is for socks, not AI |
| 52 categories | Organized chaos is still organization |
| 5340 skills | Reusable Claude/Codex/Amp/Droid skill bundles |
| 200 subagents in 10 sub-categories | Specialized workers for orchestration, QA, data, infra, language experts, etc. |
| 112 slash commands in 8 sub-cats | /architecture, /devops, /security, /testing, /git, /refactoring... |
| 120 plugins | Ready-to-install plugin trees with their own agents + commands |
| 111 rules | Universal behavior policies that work across Claude / Copilot / Gemini / Aider |
| 106 prompt templates | Domain prompts from the AI Engineering from Scratch curriculum + more |
| 759 system prompts | Raw vendor system-prompt leaks + Claude Code prompts — installable via -k system-prompt |
| 18 recipes | End-to-end workflows (landing-page-in-20-min, repo-to-design-system, etc.) |
| 33 Mythos security modes | Defensive vuln-discovery / red-team / patching / disclosure inspired by Project Glasswing |
| 174 design-system modes | Airbnb / Apple / Bento / Brutalist / Cinematic / Glass — pick an aesthetic |
| Production-grounded content | Every web-researched mode cites real URLs. No invented APIs. No hallucinated CVEs |
| VIBE CLI | Install modes as skills to OpenCode, Claude Code, Codex, Cursor |
| Engineer-persona modes | Code review by DHH, Carmack, Torvalds, antirez, Rich Hickey, Kleppmann (cited) |
npx claudepluginhub anubhavg-icpl/vibe --plugin vibeHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques