Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Lets the agent read DeepWiki's AI-generated documentation of any public GitHub repository and ask questions about a codebase. Runs locally from the deepwiki-mcp npm package.
An agent that checks proposed project work against the project’s written mission, principles, architecture rules, and working methods. It also checks whether the proposal keeps people involved in important decisions.
An AI agent role for product management, focused on writing product requirement documents (PRDs). A PRD records the problem, users, requirements, success measures, scope, release plan, risks, and open questions.
A software-engineering work process for clarifying requirements, planning milestones, testing changes, and preparing pull requests. TDD means writing tests before the code they check.
An AI agent that reviews technical decisions as a chief technology officer would. It checks proposals against engineering principles, risk checks, organisational standards and business goals.
A command for carrying out a planned feature in several stages, with review and validation points along the way. It uses a feature plan stored under the project’s rpi folder and places implementation work in a matching output folder.
A research command for deciding whether a proposed software feature should proceed, based on product value, technical feasibility, risks, and alternatives.
★not rated 2 5mo agoA18 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: