architect
01Agent Claude Code
A software-architecture agent that designs systems, reviews technical choices, and plans changes for maintainability, scale, security, and performance.
Agent Claude Code
A software-architecture agent that designs systems, reviews technical choices, and plans changes for maintainability, scale, security, and performance.
Agent Claude Code
A focused helper for fixing TypeScript, compiler, dependency, and build errors. TypeScript is a programming language that checks JavaScript code before it runs.
Agent Claude Code
A code-review assistant that checks recent changes for correctness, security, maintainability, performance, and test coverage.
Agent Claude Code
A documentation assistant that maps a codebase and keeps its README files and guides aligned with the actual code. A code map is a structured overview of folders, modules, public interfaces, routes, data models, and dependencies.
Agent Claude Code
An end-to-end testing assistant built around Playwright, a tool that controls real browsers to test complete user journeys.
Agent Claude Code
A planning guide for complex software features, architecture changes, and refactors, which are changes that improve code structure without changing its intended behavior. It turns a request into ordered implementation steps with files, dependencies, risks, tests, and success criteria.
Agent Claude Code
An agent for finding and safely removing unused code, duplicate implementations, and unnecessary dependencies from a codebase. It also records removals in a deletion log.
Agent Claude Code
A security-review agent that looks for common weaknesses in web applications and code, including exposed secrets, unsafe input handling, broken access controls, and vulnerable dependencies. It uses security checks and tools described in its instructions.
Agent Claude Code
A guide to test-driven development, or TDD, a method where you write a failing test before writing the code that should pass it. It follows the cycle of writing a test, implementing the smallest fix, and then improving the code.
Command Claude Code
A command workflow for fixing TypeScript and build errors one at a time. It runs the project build, explains each error, applies a fix, and checks the result.
Command Claude Code
A command that reviews uncommitted code changes for security, quality, testing, accessibility, and maintainability issues. It reports each finding with a severity, file location, explanation, and suggested fix.
Command Claude Code
A command for creating and running end-to-end tests with Playwright. End-to-end tests check a complete user journey across the application, such as logging in, searching, or paying.
Command Claude Code
A command that reviews the current coding session and extracts reusable solutions, debugging methods, workarounds, or project patterns into a proposed skill file.
Command Claude Code
A planning command that restates a coding request, identifies risks and dependencies, and creates a step-by-step implementation plan. It requires the user to confirm the plan before any code is changed.
Command Claude Code
A command for finding and removing unused code after checking that the tests still pass. Dead code is code that is no longer used.
Command Claude Code
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
Command Claude Code
A command that examines how much of a codebase is exercised by tests and creates tests for uncovered code. Test coverage measures which code paths run during testing.
Command Claude Code
A command that scans a codebase and updates architecture maps: concise documents showing the project’s structure, dependencies, backend, frontend, and data model.
Command Claude Code
A documentation-update command that builds contributor and operations documents from project configuration files. It uses package.json for scripts and .env.example for environment variables.
Hook Claude Code
Runs before the agent uses a tool for tool == "Bash" && tool_input.command matches "(npm run dev, pnpm( run)? dev, yarn dev, bun run dev)", tool == "Bash" && tool_input.command matches "(npm (install, test), pnpm (install, test), yarn (install, test), bun (install, test), cargo build, make, docker, pytest, vitest…
Hook Claude Code
Runs before the context is compacted, executing pre-compact.sh. From cfrs2005/claude-init.
Hook Claude Code
Runs when a session starts, executing session-start.sh. From cfrs2005/claude-init.
Hook Claude Code
Runs after a tool call finishes for tool == "Bash", tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx, js, jsx)$", tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx)$", tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx, js and jsx)$" tool calls, running #!/bin/bash (4 commands). From…
Hook Claude Code
Runs when the agent finishes a response, executing session-end.sh and evaluate-session.sh (3 commands). From cfrs2005/claude-init.