도구

Three layers of security checks on agent-written code: rule-based warnings on about 25 risky patterns during edits, a model review of the diff at turn end, and an agent tracing cross-file bugs like IDOR and SSRF at commit. Official Anthropic plugin; needs Python 3.8+ and model API access.

Designs and builds MCP servers: first picks a deployment model among remote HTTP, MCPB bundles and local stdio, then guides tool design, auth and in-chat interactive components. Maintained by Anthropic.

Has the agent build single-file HTML interactive playgrounds: visual controls on one side, live preview on the other, and a prompt to copy back into Claude. Templates for design tuning, data exploration, concept maps, doc annotation, code review and architecture diagrams. By Anthropic.

Official Anthropic plugin that reads local session logs in ~/.claude/projects and generates an interactive HTML usage report covering tokens, cache hit rate, subagents, skills and the most expensive prompts, with optimization tips. Needs Node.js.

Audits whether CLAUDE.md matches the current codebase and scores its quality, and /revise-claude-md writes lessons from the current session back into project memory. Official Anthropic plugin.

Anthropic's official plugin marketplace, built into Claude Code by default, with 300+ official and partner plugins for development, security, design and office collaboration. Browse and install with /plugin.

HashiCorp's official Terraform plugin: runs the Terraform MCP Server in Docker against the Terraform Registry and HCP Terraform API to look up provider and module docs and help write IaC. Needs Docker; TFE_TOKEN is optional.

Creates or improves Agent Skills from scratch: writes eval cases to test them, runs benchmarks with variance analysis, and tunes descriptions for more accurate triggering. Maintained by Anthropic.

Connects Claude Code to a TypeScript/JavaScript language server for go-to-definition, find references and live type error checking. Install typescript-language-server globally first. Official Anthropic plugin.

Implements the Ralph Wiggum loop with a Stop hook: feeds Claude the same prompt repeatedly so it keeps iterating on its previous file changes until it outputs a completion marker or hits the iteration limit. Official Anthropic plugin.

Connects Claude Code to the Intelephense PHP language server for code intelligence and diagnostics. Install intelephense globally with npm first. Official Anthropic plugin.

Modernizes legacy codebases: assesses the current state, maps dependencies, extracts business rules and plans the migration, then upgrades or rewrites, running old and new code on the same inputs to prove identical behavior. Official Anthropic plugin.

Connects Upstash's hosted Context7 remote MCP to fetch current, version-specific docs and code examples for libraries on demand, reducing outdated or invented APIs. No local Node needed; works anonymously, and an API key raises limits. Maintained by Upstash.

Official Linear plugin in Anthropic's marketplace: connects the hosted Linear MCP to create and update issues, manage projects and states, and search across workspaces from chat. Needs a Linear account and OAuth authorization.

Connects Claude Code to gopls, Go's official language server, for code intelligence, refactoring and analysis. Install gopls with go install and add Go's bin directory to PATH first. Official Anthropic plugin.

Simple, fast alternative to find with intuitive syntax and regex and glob matching, skipping hidden and .gitignored paths by default. Can run commands on results in parallel; handy for agents locating files quickly.

Turns common prompts such as summarizing, extracting insights and rewriting into reusable patterns you pipe text, web pages or YouTube transcripts through, using many model providers or local Ollama. Can also run as a REST API. Run fabric --setup first to configure models.

Lightweight multi-protocol command-line downloader that fetches in parallel segments from multiple sources over HTTP(S), FTP, SFTP, BitTorrent and Metalink. Resumes downloads, reads URLs in bulk from text files and offers a JSON-RPC interface for scripts or agents.

Command-line tool for transferring data by URL over 20+ protocols including HTTP(S), FTP, SFTP, WebSocket and MQTT; a staple for agents calling APIs and downloading files. Preinstalled on macOS and most Linux distributions.

Official daisyUI skill: the agent uses daisyUI 5 component classes, semantic colors and themes whenever it writes HTML or JSX, picking components by intended function, reading their guides and following their exact structure. Includes install, usage, config and color guides. Built on Tailwind CSS 4.

Context-driven development plugin: first captures product vision, tech stack and workflow docs, then generates a spec and phased plan for each feature, executes with TDD and supports per-task rollback. Ported from Google's Conductor for Gemini CLI.

Test-driven development plugin: /tdd-workflows:tdd-cycle and related commands move through red-green-refactor phases with a checkpoint for approval at each, plus TDD orchestrator and code reviewer subagents. Part of the wshobson/agents marketplace.

Python 3.12+ development plugin with python-pro, django-pro and fastapi-pro subagents, a project scaffolding command, and 16 skills on async, type safety, testing, packaging, uv and more. Part of the wshobson/agents marketplace.

Orchestrates multi-agent teams using Claude Code's experimental Agent Teams feature: parallel multi-angle code review, competing-hypothesis debugging and feature work split by file ownership. Enable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS first.