Browse plugins

Hookify creates custom hooks to prevent unwanted behaviors by analyzing conversation patterns or explicit instructions, using simple markdown configuration files with regex pattern matching. It supports four hook events (PreToolUse, PostToolUse, UserPromptSubmit, Stop) and provides commands to generate rules, list configurations, and interactively manage hook behavior without requiring restarts.

This plugin provides .NET development tools for Claude Code, including automatic CSharpier formatting for C# files after edits and a dotnet-run-file skill to execute C# code directly without projects (.NET 10+). It also offers coverage report generation scoped to branch changes, integrating seamlessly via post-tool-use hooks.

This skill audits any project for security vulnerabilities (OWASP Top 10, CWE Top 25, CVSS scoring) and GitHub repositories, with deep PHP/TYPO3 scanning across 80+ checkpoints and 19 reference guides. It hooks into PreToolUse events to warn about risky commands before execution.

This plugin automatically loads credentials from a CLAUDE_ENV_FILE environment variable on session start and redacts secrets from CLI output in real-time using the nopeek CLI tool. It intercepts both session initialization and tool execution to prevent sensitive data from being exposed in logs or terminal output.

Pro Workflow is a complete AI coding system with self-correcting memory, persistent SQLite-indexed research wikis, and an auto-research loop that learns from corrections across sessions. It provides 41 skills, 8 agents, 23 commands, and intelligent hooks that inject relevant knowledge and enforce quality gates without requiring API keys or external services.

Claude-mem is a memory compression system that persists context across Claude Code sessions using 18 skills, 6 hooks, and an MCP server integration. It intercepts session and tool-use events to manage and compress conversation history, enabling continuity between separate coding sessions.

This skill prevents dangerous GitHub release commands (like unsigned tags and bypassed CI) by intercepting them via hooks, then orchestrates safe releases with version bumps, signed tags, and CI-driven workflows across multiple ecosystems (TYPO3, PHP, Node.js, Go, Python, Rust). It auto-detects project type, manages versioning from conventional commits, and ensures supply chain security through signed tags and attestations.

This plugin integrates the PageRangers Monitoring API into AI assistants, enabling keyword analysis, ranking tracking, KPI reporting, and prospect identification directly within agent workflows. It runs as a hook on user prompt submission and requires PageRangers API credentials and Python 3.10+ to execute SEO monitoring commands.

This plugin acts as a security reminder hook that warns developers about potential security vulnerabilities—including command injection, XSS, and unsafe code patterns—when they edit files. It uses a Python-based analysis triggered by PreToolUse events to flag risky code patterns before they're executed.

Three-layer security review for Claude-generated code: pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that traces data flow across files to catch injection, XSS, SSRF, hardcoded secrets, and 25+ vulnerability classes. Uses Anthropic's Claude models (Opus 4.7 by default) to review diffs and trace security issues before code is committed.

Claude Code plugin that extracts video frames via ffmpeg and processes audio through configurable backends (Gemini API, local Whisper, or OpenAI) to give Claude direct visual and audio understanding of videos. The plugin supports local files and YouTube URLs, automatically adapting frame extraction parameters based on user queries.

This plugin provides an MCP server for searching and fetching official Microsoft Learn and Azure documentation directly within Claude Code. It includes tools for documentation search, code sample discovery, and full-page retrieval covering Microsoft, Azure, .NET, C#, and Visual Studio resources.

This plugin provides a Playwright MCP server that integrates browser automation and QA testing capabilities, exposing tools to navigate pages, take screenshots, interact with elements, and fill forms across Chromium, Firefox, and WebKit. It requires npx to run the Playwright-based MCP server for automated testing and web interaction workflows.

Ars Contexta generates a personalized knowledge management system through conversational setup, creating markdown vaults with wiki links, processing pipelines, automation hooks, and domain-native documentation—all derived from how you describe your thinking and work. The plugin provides 10 skills for extracting insights, finding connections, and maintaining your vault, plus a 6-phase pipeline that mirrors Cornell note-taking with a meta-cognitive layer for continuous system evolution.

Ponytail injects a minimalist decision ladder into Claude Code sessions, forcing the agent to question whether code is needed at all before building solutions. It works by hooking session start and prompt submission to apply YAGNI principles, prefer stdlib, and avoid unrequested abstractions.

This Jira integration plugin provides two specialized skills—jira-communication for API operations and jira-syntax for wiki markup handling—that auto-detect issue keys and enable comprehensive Jira actions through Python CLI scripts. It supports both Jira Server/DC and Cloud deployments with zero MCP overhead, running scripts directly via Bash for fast execution.

Reins intercepts tool calls via pre/post hooks to block destructive actions, route high-risk operations to human approval, and maintain an immutable audit trail of all decisions. It protects against vulnerabilities covered in OWASP MCP, ASI, and Agentic Skills Top 10 threat models by analyzing commands before execution and logging outcomes to a local decision log.

This plugin restores the deprecated Explanatory output style by injecting a SessionStart hook that instructs Claude to provide educational insights about implementation choices and codebase patterns throughout each session. It formats these insights in a consistent "Insight" block before and after code generation to explain design decisions and conventions.

This plugin provides five core skills for ecosystem navigation, skill creation, research pattern analysis, session reflection, and plugin development, with a UserPromptSubmit hook that forces skill evaluation on user input. It integrates via a shell-based activation script to enable automated skill assessment workflows.

memsearch automatically captures and indexes your Claude Code session history as semantic memories, allowing Claude to recall past work across sessions without manual saving. It runs entirely locally using ONNX embeddings and shell hooks, integrating with Claude Code's native skill and hook system.

Hivemind provides cloud-backed persistent memory using Deeplake, allowing you to read, write, and share memory across Claude Code sessions and agents through hooks that capture session events and tool usage. The plugin integrates with your workflow via Node.js commands and skills, enabling collaborative memory management across multiple Claude instances.

This plugin activates an interactive learning mode via SessionStart hook that prompts Claude to request meaningful code contributions at decision points while also providing educational insights about implementation choices. It combines the unshipped Learning output style with explanatory functionality to transform passive observation into hands-on learning experiences.

brooks-lint performs AI-powered code reviews grounded in twelve classic engineering books, diagnosing code against six decay risk dimensions with book citations and severity labels. It offers six analysis modes (PR review, architecture audit, tech debt, test quality, health dashboard, and auto-fix) that produce structured findings with symptoms, sources, consequences, and remedies.

Octopus orchestrates code review, research, and development workflows across up to ten external LLM providers (Codex, Gemini, Copilot, Ollama, Qwen, OpenRouter, and others) alongside Claude, using consensus gates and multi-agent deliberation to catch blind spots before shipping. It bundles 50 commands, 58 reusable skills, 50 specialized personas, and persistent session memory to run autonomous pipelines from spec to delivery with quality checks at each phase.

Safety Net intercepts and blocks destructive git and filesystem commands before AI agents execute them by analyzing command semantics, making it immune to flag reordering and shell wrappers. It runs as a PreToolUse hook across seven coding agent CLIs (Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Kimi Code, OpenCode, and Pi) and works on Windows, macOS, and Linux.

Ralph Wiggum implements continuous self-referential AI loops that repeat the same prompt through a Stop hook until task completion, allowing iterative refinement within a single Claude Code session. The technique runs Claude in a while-true pattern with persistent file state, letting the model read its own past work and fix failures autonomously.

This plugin adds audio feedback to Claude Code on Windows by playing system sounds when Claude finishes responding or when notifications occur using PowerShell. It provides non-blocking background playback and is configurable via environment variables to select different Windows system sounds or disable the feature entirely.

This skill provides expert Git workflow patterns including branching strategies (Git Flow, GitHub Flow, trunk-based), commit conventions, pull request processes, and CI/CD integration through a portable Agent Skill. It includes a `/pr-finish` command to automate pull request merge workflows and pre-commit hooks for validation.

This plugin provides Git workflow automation including worktree management, branch cleanup, secret scanning, and configuration validation through hooks and guardrails. It uses a PreToolUse hook to inspect and control tool execution decisions, with built-in shell integration for Git operations.

This agent skill automatically detects missing CLI tools (77+ supported) and installs them via optimal package managers, while also providing proactive environment auditing and batch tool updates. It reacts to "command not found" errors and user requests to maintain development environments across multiple platforms.

Engram is a learning system that turns your AI assistant into an evidence-based tutor using first-principles Socratic questioning, blind-graded recall verification, and FSRS-based spaced repetition scheduling to ensure you retain knowledge. The plugin stores your learning state locally as plain JSON, works across six agentic platforms, and requires only Python 3 (no external APIs or accounts).

This MCP server fetches the latest official library documentation from authoritative sources to ground Claude's responses in current API references. It supports popular libraries and frameworks, helping prevent outdated information and reduce hallucinations by providing real-time documentation access.

This skill equips Claude Code and other AI agents to create and maintain TYPO3 extension documentation in reStructuredText format, including RST validation, TYPO3-specific directives, and Docker-based local rendering. It provides extraction patterns, gap analysis workflows, and automated deployment guidance aligned with official TYPO3 documentation standards.

NotFair is a goal-driven marketing automation platform that runs autonomous agents on your machine to achieve and maintain business metrics across Google Ads, Meta Ads, and SEO. It connects to Google Search Console, Google Ads, and Meta Marketing APIs through PKCE OAuth, measures results server-side, and executes one disciplined action per check cycle with full auditability.

dev-flow provides code review, automated fixes, commit management, and linting for development workflows through 2 agents and 6 skills integrated via hooks. It uses local tools (node, bash, python3) to run shell-based linting and code quality checks without external API dependencies.