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.
Track your AI usage, lines of code generated, time spent prompting AI, etc. using the WakaTime plugin for Claude Code. WakaTime is an open source plugin for metrics, insights, and time tracking automatically generated from your programming activity.
@wakatimeSee the hooksGoverns Claude Code context by compressing sessions, filtering tool output, and enforcing guardrails to save tokens. Activates on session start, prompt submission, tool use, and before compaction.
@0xhimanshuSee the hooksYour agent reads the rules. This checks whether it followed them. A ratchet turns one way. Complexity in your codebase goes down or stays flat, unless someone deliberately turns it the other way and writes down why.
@0xwilliamortizSee the hooksBundles kits for debugging, security audits, SQL and NoSQL review, and state management across Vue, Angular, and Tailwind. Fires during framework migrations, database changes, or verification passes.
@altafinoSee the hooksScopes threat hunts, correlates evidence from git and GitHub activity, and triages false positives. Fires when writing hunt queries or validating findings before an incident response.
@backbay-labsSee the hooksfrontend-craft is a universal frontend plugin that brings the same opinionated engineering standards to all 15 AI coding assistants.
@bovinphangSee the hooks**An integrity hook for Claude Code that watches the agent's own tool calls and blocks the ones that fake a check.** When Claude says it did something — ran the tests, cited a paper, committed the fix, verified the certificate — makoto holds that word against
@clear-sightsSee the hooksAdds a Claude Code statusline with caveman-mode minimalism, configured through an interactive installer. Activates on terminal startup, using Node and bash across Linux and PowerShell.
@fahimfbaSee the hooksTracks token usage and context size, alerting via desktop notifications and status line. Fires at session start, each prompt, stop, and around compaction.
@fomyioSee the hooksArchives sessions into local SQLite with full-text search, secret masking, and checkpointing for memory recall. Hooks run at session start and end, prompt submit, precompact, and stop.
@ij5aSee the hooksRuns repository scans for secrets, duplicates, and code health, then reviews changes. Fires on session start, tool use, and session end.
@jx-hxxxSee the hooksA Claude Code and Codex plugin that scaffolds AI-native development practices into new projects. jig adds a repeatable spec, implementation, review, and memory workflow to AI-assisted software projects.
@rambozSee the hooksOrchestrates subagent pipelines for sprint planning, QA retesting, and contract review with Playwright browser automation. Fires through plan, build, qa, and harness commands and lifecycle hooks.
@redker56See the hooksLanguage: English | 繁體中文 | 简体中文 | 日本語 | 한국어 | Español The harness layer for Claude Code. Let the model choose the path. Keep "done" verifiable. Full control plane on Claude Code. Skills-only distribution for Codex CLI and other compatible agents.
@sd0xdevSee the hooksGuardrails + an overnight autopilot for your AI coding agent — one that plans before it codes, won't ship work that fights your strategy, and gets sharper every run.
@swapnil-agrimSee the hooksTracks project roadmaps, tasks, and decisions across Claude Code sessions. Fires on session start, task creation and completion, and before and after tool use.
@v-songbirdSee the hooksScans and guards file encodings and line endings in a repository. Fires during tool use, session start and end, and stop events to preserve encoding integrity.
@ymonsterSee the hooksTracks token budget and builds a code graph to compress context for planning, review, debugging, and git commits. Fires via session start, prompt submit, tool use, and stop hooks.
@abhisekjhaSee the hooksRoutes Claude Code tasks to specialized subagents to cut costs. Hooks trigger on tool use, session start, and subagent completion.
@adityaraj0421See the hooksAudits repositories for duplicate code and canonical mismatches, and plans refactors before changes. Runs pre-write and post-write gates on prompt submission, tool use, and stop.
@annyeong844See the hooksFour-layer long-term memory (L0 Conversation → L1 Atom → L2 Scene → L3 Persona) for Claude Code, inspired by Tencent/TencentDB-Agent-Memory. Fully local — no external Gateway, no paid API, no Python.
@baodq97See the hooksCaptures corrections you make mid-session into a memory queue, then surfaces matching skills before you repeat them. Hooks fire on prompt submit, precompaction, tool use, and session start.
@bayramannakovSee the hooksBuilds agent loops that verify evidence before completing tasks, with research, slide, and Korean text skills. Hooks fire at session start, prompt submission, stop, and subagent stop to check work.
@beefikerSee the hooksMy global Claude Code setup, mirrored from ~/.claude: the rules, the hook scripts that enforce them, and the global CLAUDE.md.
@chancegraffSee the hooks