claude-code-plugins

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.

1 skill · 4 commands · 1 agent · hooks

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

1 command · 6 agents

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

3 commands · hooks

Development kit for working with the Claude Agent SDK

1 command · 2 agents

Commands for git commit workflows including commit, push, and PR creation

3 commands

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

1 command

Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)

hooks

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics.

1 skill

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

hooks

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

The diff pane as a plugin: /diff opens the session's uncommitted changes beside the transcript, file by file with their hunks, refreshed as Claude edits and runs commands; the first edit opens it where the terminal is wide enough, and a file's ask button rides its hunks on the next prompt.

Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity.

Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.

Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.