workflowadvancedClaude Code

Production-Ready Claude Code Workflow for Large Monorepos

This document outlines a structured workflow that uses the Claude Code AI assistant to manage large software development tasks from start to finish. By breaking down work into planned steps with human approval checkpoints, developers can automate up to 90% of the coding, resulting in significant productivity gains while maintaining quality control.

AI SETUP PROMPT

Paste into Claude Code — it will scan your project and set everything up

# Set Up Workflow: Production-Ready Claude Code Workflow for Large Monorepos

## What This Is
This document outlines a structured workflow that uses the Claude Code AI assistant to manage large software development tasks from start to finish. By breaking down work into planned steps with human approval checkpoints, developers can automate up to 90% of the coding, resulting in significant productivity gains while maintaining quality control.

Source: https://www.f22labs.com/blogs/10-claude-code-productivity-tips-for-every-developer/

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)

Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?

## Source Access Note

The source URL (https://www.f22labs.com/blogs/10-claude-code-productivity-tips-for-every-developer/) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.

## What to Implement

This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.

- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files

## Additional Context

- Analyze the user's project structure to create a root `CLAUDE.md` file. Populate it with project-level context, architecture overview, style guides, and common commands (e.g., `npm run test`, `docker-compose up`).
- Based on the user's specified task (e.g., a YouTrack or Jira ticket ID), generate a detailed `<ticketId>-implementation-plan.md` file. This plan must outline the proposed code changes, classes/methods to be modified, and any clarifying questions for the user. Halt execution and explicitly request user review and approval of this plan before proceeding.
- Upon receiving user approval for the implementation plan, execute the coding changes as outlined. After implementation, generate a `<ticketId>-implementation-overview.md` file that summarizes all file modifications and cross-references the initial plan. Prepare the changes for commit and request a final human review.

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

3,433 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Analyze the user's project structure to create a root `CLAUDE.md` file. Populate it with project-level context, architecture overview, style guides, and common commands (e.g., `npm run test`, `docker-compose up`).
02Based on the user's specified task (e.g., a YouTrack or Jira ticket ID), generate a detailed `<ticketId>-implementation-plan.md` file. This plan must outline the proposed code changes, classes/methods to be modified, and any clarifying questions for the user. Halt execution and explicitly request user review and approval of this plan before proceeding.
03Upon receiving user approval for the implementation plan, execute the coding changes as outlined. After implementation, generate a `<ticketId>-implementation-overview.md` file that summarizes all file modifications and cross-references the initial plan. Prepare the changes for commit and request a final human review.

FIELD OPERATIONS

Automated Issue Management Bot

Build a bot that integrates with a project management tool (Jira, YouTrack, Linear). When a new 'bug' or 'feature' ticket is assigned to the bot, it automatically executes this workflow: reads the ticket, analyzes the codebase, creates an implementation plan, waits for human approval, writes the code, and creates a pull request for review.

CI/CD Refactoring Agent

Create a CI/CD pipeline step that uses this structured workflow to perform automated code refactoring. The agent would be triggered on a schedule, identify a 'tech debt' issue from a backlog, propose a refactoring plan in an `.md` file, require an engineer's approval, then apply the refactoring and submit it for review.

STRATEGIC APPLICATIONS