[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3

Autonomous Execution Modes

💻 Claude Code CLI⏱ 20 min⭐ 900 BASE XP⌨ HANDS-ON LAB

The Local Agentic Interface

Claude Code (@anthropic-ai/claude-code) is Anthropic's official agentic CLI that lives in your terminal. It executes a continuous ReAct (Reasoning + Action) loop. You give it a task (e.g., "Refactor the authentication flow"), and it autonomously navigates your repository, reads code, edits files, runs tests, and applies fixes until the task is verified.

CLAUDE.md - Project Memory

The CLAUDE.md file in your project root serves as persistent memory across sessions. This markdown file contains project-specific guidelines: coding conventions, build commands, test instructions, architecture patterns, and constraints. Claude reads this file at session start to ensure every modification complies with your standards.

// Example CLAUDE.md
# Project Guidelines
- Framework: Next.js 15 with App Router
- Build Command: npm run build
- Testing: vitest run
- Coding Style: Strict TypeScript, vanilla CSS
⌨ HANDS-ON LABInstall & Drive Claude Code
⭐ +200 XP

Set up the Claude Code CLI from scratch, launch an interactive session, then run it headless - the exact workflow used in CI pipelines.

1Install the Claude Code CLI globally using npm.
2Launch an interactive session by running the CLI's base command in your project directory.
3Now run it headless: use the -p (print) flag with a one-shot prompt for scripting/CI usage.
lab-sandbox — simulated environment
INFINITY LAB SANDBOX v2.6 — simulated shell
Type the command for the current objective. Helpers: "hint", "solution", "clear".
$
OBJECTIVE 1 / 3 — type "hint" if stuck
SYNAPSE VERIFICATION
QUERY 1 // 2
How does Claude Code interact with your local repository?
You upload a ZIP archive manually
It autonomously navigates local directories, reads files, and runs terminal commands using local tool execution
It reads your browser history
It only operates on pasted text