Every plugin that ships hooks :)

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

Hypothesis-driven problem solving for AI agents Probe · Falsify · Escalate — never overcomplicate, never blind-retry

Runs a test-first, critic-loop workflow with an invariant-reviewer agent. Activates at session start for unattended git and GitHub automation.

Take a software change from a written spec to a tested, hardened, shipped release, firing the right engineering skill at each step.

Free AI-powered SEO, AEO, and GEO toolkit by Akii for Claude Code. Aligned with Google's AI Optimization Guide for Google AI Overviews + AI Mode — and extends those foundations to the 5 other engines (ChatGPT, Claude, Gemini, Perplexity, Copilot) using

Production-tested Claude Code skills for Peec AI — the brand-visibility tracking platform for LLM-powered search (ChatGPT, Perplexity, Google AI Overviews, Gemini).

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Standardizes python, typescript, java, kotlin and shell code, scaffolds projects, and tracks tasks across sessions. Fires via init-project, do-review, catchup, and todo commands.

Controls Spotify and Apple Music playback, volume, seek, and statusline on macOS from Claude Code. Media skills run on demand. Sessionstart hook initializes playback state.

Stay fluent in the code your AI agent writes. FluencyLoop turns each feature into a documented design, teaches the decisions at your level, tracks the rationale, and produces a reviewer-ready summary.

A hook-based framework for Claude Code that enforces task delegation to specialized agents, enabling structured workflows and expert-level task handling through intelligent orchestration. See the delegation system in action:

Write the requirements before you write the code. Spec First gives you a workflow with three steps. First, define what to build. Then implement it from the spec. Last, generate the documentation. All steps run in your terminal.

I love music but never learned an instrument. AI became the creative outlet that was always out of reach. This project started as a way to go deep on Claude Code plugin architecture, agentic workflows, multi-model orchestration, and MCP tooling.

AgentOps is the operating loop a coding agent follows: one intent, one bounded build, one fresh judge, then report and stop. It also ships skills to orchestrate multi-agent systems.

An AI content idea generator that does your morning research for you — it reads what's working across X, Instagram, TikTok, and YouTube, then hands you a daily "For You" feed of content ideas framed against your own brand.

Guides semantic versioning for skills, auto-backing up files and generating changelog entries. Fires from a posttooluse hook after every tool call.

Covers CesiumJS 3D tiles, terrain, imagery, camera controls and custom shaders, with a chrome-devtools MCP server for live checks. Fires each session when the project uses CesiumJS.

Journals coding sessions to SQLite, letting you search, recover context, and export past work via journal-search and journal-export. Auto-captures each session through a userpromptsubmit hook.

Build with Claude Code without your brain going numb. No-Numb quizzes you on the code Claude just wrote — and, by default, blocks the session from continuing until you pass. The middle ground: built fast like an agent, understood like you wrote it yourself.