Skip to content
  1. Home
  2. Tracks
  3. Setup

SETUP

Setup

Most agent failures are decided before the first prompt: what the agent is told about the repo, what it may run without asking, which tools it can reach and what it remembers next session. These guides cover the setup that makes an agent finish work instead of stopping to ask.

  1. SETUPHow to Add MCP Servers to Claude Code and Keep Their Tools Safe to CallA Claude Code MCP guide to adding remote servers, choosing scope, checking connection status, and containing calls with server- and tool-level permission rules.
  2. SETUPHow to Configure Codex CLI for Repository Work: config.toml, Sandbox, Hooks, and MCPUse Codex config.toml to control repository-scoped settings, workspace network access, hook trust, and MCP servers, then verify every layer before agent edits begin.
  3. SETUPCursor vs Claude Code for Repository Work: A Practical Operator ComparisonA practical Cursor vs Claude Code comparison for repository work, including Cursor's isolated cloud agents and Claude Code's multi-surface workflow.
  4. SETUPHow to Design AGENTS.md Files That Carry Instructions Across Coding AgentsA practical AGENTS.md design uses root guidance, nested package files, explicit ownership, and loader-specific checks to carry one reliable instruction system across coding agents.
  5. SETUPHow to Set Up Playwright MCP for Repeatable Browser VerificationSet up Playwright MCP with npx, verify actions through accessibility snapshots, and isolate browser state so concurrent checks do not share one profile.

The first guides in this track are being written and checked against the tools' own documentation.