A hook fires on its own, before you type or as a session starts. These plugins ship one, and each page shows exactly what runs.
242 plugins ship 966 hooks.
Installs a skill library and agents for code review, quality gates, and test automation in Python, TypeScript, Node, and Swift. Fires on install, pr-review, and retro commands.
@notqueSee the hooksRuns 23 agents to scaffold full-stack React/Node apps, compress tokens, and enforce security through built-in hooks. Fires when you start generating, debugging, or reviewing code in Claude Code.
@smorky850612See the hooksClaude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
@rohitg00See the hooksOrchestrates multi-agent spec-driven development with skills, agents, and semantic memory. Fires during scaffolding, spec workflow, and lifecycle hooks.
@komlukSee the hooksEvery AI model has blind spots. Claude Octopus supports ten external provider integrations — Codex, Gemini, Antigravity CLI, Copilot, Qwen, Ollama, Perplexity, OpenRouter, OpenCode, and Grok — alongside the built-in Claude Code host, with consensus gates that
@nyldnSee the hooksRuns role-based agents for architecture, code review, security, and TDD, with 44 commands for git, PR, and build-error fixes. Hooks fire on tool calls and session events, prompt to session end.
@xiaobei930See the hooksCoordinates persistent memory for AI agents through a shared protocol and MCP. Fires whenever the agent stores, recalls, or updates context.
@vbcherepanovSee the hooksCoordinates specialized coding agents through a stateful sqlite-backed workflow. Activates during development sessions to handle planning, implementation, review, and worktree management.
@michael-harrisSee the hooksMCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
@nikolai-vysotskyiSee the hooksCoordinates multi-agent workflows with approval gates and verification rubrics. Fires on session and tool-use hooks to enforce git conventions and Jira tracking.
@metratonSee the hooksCoordinates a full game development cycle through Claude Code skills, from design docs to engine builds and CI validation. Fires when you start a game project, sprint, playtest, or launch.
@alterlab-ieuSee the hooksOrchestrates dev agents and slash skills for testing, review, git ops, and Figma-to-code. Fires via session hooks, tool events, and MCP for Atlassian and Figma.
@ggombeeSee the hooksLoop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.
@kanevrySee the hooksOne board for every Claude Code session on your machine. Run more than two or three Claude Code sessions and you lose track of them: which terminal is which, which one is blocked on a permission prompt, and which two are editing the same file.
@lacionSee the hooksAnalyst, engineer and pm agents track requirements, enforce quality gates and run retrospectives across git and CI. Hooks fire every session stage, from start through subagent stop.
@arch-teamSee the hooksSaves session notes and error logs as markdown, backing them up to GitHub for recall across projects. Commands like save, sync, and reload fire around compaction and session handoffs.
@helloruruSee the hooksRemoves AI-isms and rewrites stilted prose into a human voice. Fires from unslop skills for commits, file edits, reviews, and reasoning.
@mohamedabdallah-14See the hooksWatches token spend and savings through Claude Code hooks, offering recall skills and code exploration agents. Activates on session events, prompt submission, tool use, and compaction to trim costs.
@withwozSee the hooksHe says nothing. He writes one line. It works. An agent skill that stops your AI from over-building. Two hooks, one command. npm install -g @0xwilliamortiz/ponytail-improved ponytail
@0xwilliamortizSee the hooksGates task completion until evidence is shown via session hooks and proof-checking skills. Fires on session, prompt, tool use, subagent stop, and task completion events.
@borelchuSee the hooksSends Claude Code session traces, tool calls, and subagent activity to Opik for LLM observability. Hooks capture events from prompt submit through session end, including compaction and failures.
@comet-mlSee the hooksMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
@dietrichgebertSee the hooksGates shipping steps with SHA256-verified, locked state files and reviews code through eight critic agents before PR automation. Hooks run session-wide, from prompt submit to precompact.
@elb-prSee the hooksDecomposes features into tasks tracked in a context graph, then reviews PRs against that plan. Fires when brainstorming, decomposing tasks, or reviewing pull requests via its MCP server.
@frkakSee the hooks