Claude Code Guide: Agentic Engineering Workflow

Learn to understand an unknown repo by cloning a GitHub project, asking clear questions, and using Cloud Code to explain the code base and provide a concise overview.

Explore an optional exercise that prompts you to ask three questions about a repo, clarifying the language, a skill, and a hook, recognizing markdown as the content format.

Explore how models, tokens, and the context window drive Cloud Code usage, with practical guidance on resetting context, choosing Opus, Sonnet, or Haiku, and managing plan limits.

Learn to convert csv data to pdfs with cloud code in a one-shot workflow, then build a Node.js script to generate invoices as pdfs.

contrast vibe coding, where code is treated as ai's problem and lacks documentation, with agentic engineering that requires planning, documentation, tests, and code reviews to establish conscious decisions.

Learn how to use CloudMD to guide agent behavior with per-project and local overrides, manage multiple CloudMD files, and apply concise conventions for the generated code.

Learn to craft a project-specific CloudMD file by merging Karpathy’s guidance with practical CloudCode insights, using init to analyze code, emphasize TypeScript, and test with unit tests rather than mocks.

See how updating a CloudMD governed project converts code to TypeScript, adds unit tests with VTest, and clarifies rules through the coding agent to ensure secure, verifiable changes.

Explore voice input in Claude Code to sharpen prompts, featuring a live demo of slash voice, hold the space to record, and using the open-source Whisper model.

Explore how Claude integrates Git to track changes, stage, commit, push, craft commit messages, and manage rebases and stashing, then leverage Git worktrees to work on multiple branches simultaneously.

Initialize the repository, stage files, and commit the first changes. Create a remote on GitHub, set up SSH keys, and push, while using Cloud to run Git commands.

Configure tool permission rules in cloud code to whitelist safe commands, deny sensitive access, and require prompts; manage per-project settings via the UI or .cloud/settings.json.

Learn how to set up a remote repository on GitHub, choose between SSH or HTTPS, and push your code while managing git ignore and co-author settings.

Disable co-authoring by setting include-co-authored-by to false in settings.local.json or .claude-settings.json, then clean history with git rebase or a bash script and verify with git log for sole authorship.

Explains cloud code's plan mode, showing how planning with dry principles and agent context yields a plan before building, and discusses pushing back, customization, and alternatives like superpowers.

Explore plan mode in cloud code to convert coding tasks into a validated plan for pdf pipeline, parse invoices into sqlite, and produce top five vendors by total spend.

Learn how sub-agents offload tasks from the main context to parallel, specialized agents, enabling code exploration, testing, and review with cost-aware model selection.

Build an automatic code-review sub-agent that focuses on security, best practices, and readable, reusable code; triggers after a chunk of work and only reviews uncommitted code, without running tests.

Learn to create and reuse agent skills with markdown files and terminal commands for on-demand review. Compare skills with sub-agents, where skills describe tasks and sub-agents execute them.

Create a custom code-review skill for Cloud Code that runs on demand with the CodeReviewer sub-agent, reviewing uncommitted changes or specified files, stored under .cloud/skills, and renamed to CodeReview.

Explore the skills.sh marketplace by Vercel to find and install skills via npx, ensure Node.js installed, and review security audits to avoid prompt injection and unmaintained tools.

Build a static Next.js landing page demo for a money pools personal finance dashboard using the frontend design skill by Antropic, showcasing the user interface, diagrams, and cash flow insights.

Learn how hooks enforce non negotiable rules in Cloud Code, reacting to events before or after tools, protecting .env secrets, tests, and code formatting by managing context and prompts.

Build hooks for cloud code: run tests after stop and block edits to invoices CSV, then enforce dead code removal and formatting with hard stop protection for the secrets file.

Discover MCP, the model-context-protocol that lets CLOD code call typed tools instead of shell commands. See how MCP servers streamline integrations with services like Postgres and GitHub.

Learn practical MCP with Playwright by installing a Playwright MCP server to control a real Chrome session against the MoneyPools app. Validate front-end behavior with end-to-end tests and page descriptions.

Bundle skills, hooks, subagents, and MCP servers into a plugin installed with one command. Explore the Cloud Code marketplace and examples like the Superpowers plugin to see an integrated workflow.

Install the superpowers plugin for the Money Pools project, explore plugin scopes, run a hands-on design and verification flow with cloud code, Playwright MCP, and auto-generated design docs.

Explore cloud code permission modes, from default least permissive to accept edits, plan mode, auto mode, classifier, and bypass. Start with least permissive settings and advance only after pre-approval.

Understand bypass permission mode in Cloud Code, its risks, prompts, and how it bypasses project permissions. Use container isolation or virtual machines to contain it and guard against prompt injection.

Auto mode provides a safer, classifier-driven alternative to bypass permissions, blocking risky commands by default when enabled on max team or enterprise plans.

Enable don't-ask mode in restricted environments by denying prompts until explicitly permitted, using fine-grained permissions in settings or JSON, ideal for CI pipelines.

Cloud Code sandboxing creates a physical wall around your project, blocking shell commands from leaving the current directory and preventing unauthorized network requests, while enabling auto mode provides extra protection.

Explore git worktrees, letting your coding agent work on multiple branches in separate MoneyPools folders and merge back to main when finished.

Learn to use cloud code git worktrees to run two Claude agents on parallel worktrees, develop separate features concurrently, test independently with SQLite, and merge changes into main.