도구

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.

Drives Alibaba's open-source ocr CLI to review Git changes (working tree, a commit or a branch diff), grouping line-level comments by severity and fixing them on request. Needs an LLM endpoint (Anthropic, OpenAI and other protocols); installs the CLI if missing. By Alibaba.

Official CLI (bru) for the open-source API client Bruno: runs collections stored as plain text in your repo, switches environments, outputs JSON results and imports collections from OpenAPI, making API tests easy to run in CI.

Open-source personal AI assistant and agent harness, formerly chatgpt-on-wechat: plans tasks, runs tools and skills, self-evolving memory and knowledge, multi-agent teams. Channels: WeChat, WeCom, Feishu, DingTalk, QQ, Telegram, Slack; any major model provider. One-line install and web console.

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.

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.

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 the Pyright language server for static type checking and code intelligence in Python. Install pyright first with npm, pip or pipx. Official Anthropic plugin.

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.

Plans teams for seed to Series A startups: which roles to hire at each stage and in what order, org structure, plus salary, equity ranges and headcount budget. Compensation benchmarks are 2024 US market data; adjust for your market and have finance and legal review the plan.

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.

MLOps plugin from the wshobson/agents marketplace: data scientist, ML engineer and MLOps engineer subagents and a /ml-pipeline command that runs the pipeline in phases from data analysis and training to deployment and monitoring, plus ML pipeline and recommender system skills.

Plugin for building LLM apps: LangGraph agents with memory and tool use, hybrid-search RAG, vector index tuning, prompt optimization and LLM evaluation. Includes 3 subagents and 8 skills.

Quant trading plugin from the wshobson/agents marketplace: quant analyst and risk manager subagents plus backtesting and risk metrics skills for strategy backtests, portfolio optimization and risk measures like VaR, Sharpe ratio and max drawdown. Needs local Python; not investment advice.

Accessibility review plugin with an audit command, a UI validation subagent, and WCAG 2.2 and screen reader testing skills. Before design reviews or launch, the agent checks contrast, keyboard use and screen reader support and suggests fixes. For Claude Code; automated checks need Node.js.

Data engineering plugin from the wshobson/agents marketplace: a data engineer subagent, a data pipeline command, and skills for Airflow DAGs, dbt transformations, Spark tuning and data quality, to help build ETL and data warehouses.

Support and sales plugin with two subagents: one handles support replies, ticket triage and help docs; the other writes cold email sequences, follow-up cadences, quote templates and objection handling. Prompts only; no direct CRM connection.

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.

Headless browser written from scratch in Zig for AI agents and automation, using less memory and running faster than headless Chrome in official benchmarks. fetch turns pages into Markdown, and it can serve CDP or MCP. Telemetry is on by default (an env var disables it); Windows needs WSL.

Anthropic's official fund administration plugin covering GL reconciliation and break tracing, accrual schedules, roll-forwards, variance commentary and NAV tie-outs, for fund operations and finance teams.

Official Anthropic finance skill that checks Excel for formula errors like #REF!, numbers hardcoded in formulas, sum ranges that miss rows and mixed units; on full models it also checks the balance sheet balances and cash ties. Lists issues and fixes and asks before changing anything.