Tools

GitHub's official MCP server: lets agents read and write repositories and code, manage issues and pull requests, and check Actions workflows and code-scanning alerts. Use the hosted remote server or run it locally in Docker; needs a personal access token or OAuth.

Google's open-source database MCP server with ready-made query and SQL tools for dozens of sources, including PostgreSQL, MySQL, BigQuery, Spanner and MongoDB. Define controlled custom queries in tools.yaml.

Cloudflare's official remote MCP servers: manage Workers and bindings such as KV, R2 and D1, and query logs and observability, builds, DNS analytics and Radar data. Authorizes with Cloudflare OAuth; some features need a paid plan.

Figma's official remote MCP: hands components, variables and layout from your designs to the agent to generate code, and can create and edit designs on the canvas. Needs Figma sign-in; Starter plans and View or Collab seats get only 6 read calls a month.

Lets agents call the Stripe API to manage customers, payments, subscriptions, invoices and refunds, and search Stripe docs and support articles. Maintained by Stripe; the remote server uses OAuth, or run it locally via npx with a secret key.

Before finishing a task or merging, dispatches an independent reviewer subagent over a git commit range to check the work against the plan and requirements, then handles feedback by severity: critical, important, minor. Part of obra/superpowers.

Sets up an isolated workspace before feature work: uses the agent's built-in worktree tool when available, otherwise falls back to git worktree, then installs dependencies and runs baseline tests to confirm a clean start. From Superpowers.

A four-phase root-cause debugging method: investigate the root cause, compare against working examples, test one hypothesis at a time, then fix the root cause. Guessing at code changes before locating the cause is not allowed. From the Superpowers workflow.

Once requirements or a spec exist and before touching code, writes multi-step work as a fine-grained implementation plan listing the files, interface signatures and tests to verify each step. A core Superpowers skill.

Before writing code, asks questions one at a time to clarify intent, constraints and success criteria, turning a vague idea into a reviewable design; implementation starts only after you approve it. A core Superpowers skill.

Requires the agent to run the full verification commands and read the output before claiming work is done, fixed or passing, backing claims with evidence and ruling out unverified success reports. From the Superpowers workflow.

Test-driven development in vertical slices: agree on test seams with the user first, verify behavior only through public interfaces, and avoid listed anti-patterns such as implementation coupling and tautological tests. From Matt Pocock's skills collection.

A disciplined process for hard bugs and performance regressions: build a reliable reproduction loop, reproduce and minimize, form hypotheses, instrument to verify, then fix and add a regression test, redacting secrets in output. By Matt Pocock.

Before you build, the agent grills you on your plan or design, offering a recommended answer each round, until every decision branch is resolved. It calls the grilling skill from the same repo, so install both.

Resolves subscription billing issues: checks customer and subscription state, separates duplicate purchases, team seats and failed payments, restores self-serve before refunding, and drafts the reply. Needs Stripe or similar tools connected; refunds move real money, so review them.

A complete harness for coding agents: dozens of subagents, nearly 300 skills, hooks, rules, memory and continuous learning, plus the AgentShield security scanner. Built mainly for Claude Code, with Codex support.

Self-improving agent from Nous Research with built-in memory and a learning loop that turns experience into skills. Works with any model provider; the hermes command has a terminal UI, and a gateway connects it to Telegram, Slack and more and runs scheduled tasks.

Behavior guidelines drawn from Karpathy's observations of how LLMs go wrong when coding: think before acting, keep it simple, make surgical changes only, and drive work by verifiable goals. Can also be used directly as a CLAUDE.md.

Four guidelines based on Karpathy's observations of common LLM coding mistakes: think before coding, prefer simplicity, make only necessary changes, and work toward verifiable goals. Ships as a plugin skill or works as a CLAUDE.md. Community-made, not by Karpathy.

Open-source terminal coding agent that switches freely between model providers. Includes a build agent that edits code, a read-only plan agent for analysis, subagents, and a desktop app. Formerly sst/opencode.

Builds multi-component web pages that need state or routing with React, Tailwind CSS and shadcn/ui, using bundled init and build scripts, then packs them into a single HTML file for a claude.ai Artifact. Official Anthropic skill.

After giving advice, a draft or a data analysis, adds 2-3 targeted follow-up questions that prompt the user to check key facts, test the reasoning and fill in missing context. Fires at most once per conversation. Official Anthropic skill.

Writes internal communications in familiar company formats: 3P updates, leadership reports, project status updates, company newsletters, FAQs and incident reports. Official Anthropic skill.

Reference for the Claude API and Anthropic SDK: model selection and pricing, streaming, tool use, prompt caching, Managed Agents and more, plus workflows for model migration and prompt audits. Official Anthropic skill.