vaibhav-space/my-ai-coding-workflow
Production-grade AI coding instructions, curated skills, and a 3-stage review pipeline (Planning → Critical Review → Diff Audit) built after 4,500+ hours with AI agents. Agent-agnostic.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
At a glance For Claude Code. Needs bash. Tested on Linux. Restart Claude Code and type /plan. The script adds three slash commands, /plan, /review-plan and /review-prod, and copies the plan page template to /.claude/plan-template.html. It skips any file you already have. Pass --force to replace files, and it keeps a .bak copy. For the global rules, copy CLAUDE.md to /.claude/CLAUDE.md (see the Adoption Guide). If you already have one, merge by hand instead of replacing it. Using Gemini CLI or Cursor? Copy and paste the prompts from prompts/ instead. The routine, in 5 steps Why new chats? An agent that wrote something is the worst judge of it. A fresh chat has to look at the actual code. Good to know This repository is not a speculative prompt collection. It is the setup I arrived at after spending an estimated 4,500+ hours actively building, debugging, refactoring, and deploying software…
Read the full README ↗ · Preview checked 2026-11-21T14:08:44.741Z
Inside the original README — Document outline
- I Spent 4,500+ Hours Coding with AI. This Is the Claude Code Setup I Ended Up With.
- Table of Contents
- Quick start
- Which command, when, and why
- 1. The Story Behind This Setup
- The Tooling Journey
- 2. Core Engineering Philosophy
- 3. The Three-Prompt Review Workflow
- Lifecycle Routing
- Stage 1: Planning (prompts/planning.md)
- Stage 2: Critical Plan Review (prompts/critical-plan-review.md)
- Stage 3: Production Readiness Review (prompts/production-readiness-review.md)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Production-grade AI coding instructions, curated skills, and a 3-stage review pipeline (Planning → Critical Review → Diff Audit) built after 4,500+ hours with AI agents. Agent-agnostic.
Repository facts
- Owner
- vaibhav-space
- Primary language
- HTML
- Stars
- 331
- Forks
- 48
- Open issues + pull requests
- 1
- License
- Not reported — inspect the license file
- Archived
- No
- Default branch
- main
- Created
- 2026-11-14T13:34:16.000Z
- Last push
- 2026-11-18T18:30:28.000Z
Topics and intended use
Owner-supplied topics: agentic-workflows, ai-agents, claude-code, code-review, developer-tools
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-11-21T12:28:44.152Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.