Tools

Browser automation plugin from Vercel Labs: agents drive Chrome through accessibility tree snapshots and element refs to navigate, click, fill forms and take screenshots, for web testing and exploratory QA. Install the agent-browser CLI first (npm, Homebrew or Cargo).

Package manager for macOS and Linux: agents can brew install CLI tools and desktop apps (casks), or use brew bundle to restore a dev environment from a Brewfile.

Terminal multiplexer: run multiple sessions and panes in one terminal, with processes surviving disconnects. Agents use it to host long-running tasks and drive interactive programs, and many parallel multi-agent session tools build on it.

Microsoft's open-source AI quant investment research platform: the qrun command runs dataset building, model training, backtesting and evaluation from a YAML config, with many benchmark models. The official dataset is paused, so prepare market data per the README first.

Alibaba's open-source AI code review CLI (ocr): a deterministic pass filters and groups files and matches rules, then an agent reads the context and writes line-level comments; ocr scan reviews a whole directory. Needs an LLM endpoint, or delegate mode to hand off to your coding agent.

AI pair programming in your terminal: builds a repo map of the whole codebase, auto-commits changes to git, works with Claude, DeepSeek, OpenAI and almost any other model including local ones, and can run lint and tests after edits.

Write slides in Markdown with built-in code highlighting, LaTeX math and Mermaid diagrams; slidev export outputs PDF, PPTX or PNG. Install playwright-chromium in the project before exporting.

Free, open-source offline OCR desktop app for screenshots, batch images, scanned PDFs and QR codes, callable via the umi-ocr CLI or an HTTP API (the CLI relies on the app's local HTTP service, on by default). Windows and Linux only.

Indexes a codebase into a persistent knowledge graph with tree-sitter so agents can query call chains, impact, architecture and dead code across 162 languages. A single native binary that runs fully locally with no API key; the installer configures detected clients automatically.

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.

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.

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.

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.

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.

Official Anthropic plugin that builds a shareable status page for big multi-track projects such as migrations, launches or research: goals, workstream order, next steps and risks; say 'refresh' to update the same link. Needs a claude.ai login; Artifacts are a beta for Team and Enterprise plans.

Wraps Microsoft's Playwright MCP so agents can drive a real browser to navigate, click, fill forms and take screenshots for end-to-end tests and page checks. In Anthropic's official marketplace; needs Node.js.

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.

Official Anthropic plugin that solves competition math such as IMO and Putnam problems, with adversarial checks by an independent verifier that only sees the clean proof. Gives up explicitly rather than bluffing when unsure, and outputs LaTeX/PDF once verified.

Connects GitHub's official remote MCP server to manage issues and PRs, review code, search repos and call the GitHub API from Claude Code. Requires GITHUB_PERSONAL_ACCESS_TOKEN.

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.

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.

Scans your codebase and recommends the best hooks, skills, MCP servers, subagents and slash commands by category. Analysis only, no file changes; a quick way to set up Claude Code for a project. 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.

Google's official Firebase plugin: starts the Firebase MCP via firebase-tools to manage projects, Firestore data, Auth users and security rules, and view Crashlytics and Cloud Functions logs. Needs Node.js and a Firebase CLI login.