AutoBuilder
Inspired by karpathy/autoresearch. Put this in a Ralph Loop.
Use each mode-specific prompt together with the common element block.
/goal There are no architectural or engineering principles to improve. It uses the latest Next.js 2026 and Vercel Fluid Compute, Vercel AI SDK, Vercel Workflows, and Vercel Sandbox best practices. It uses the best practices of Base UI and COSS/UI. All server-client boundaries, component codes, folder structures, React compiler, hooks, optimizations, React bundlings, streamdown optimizations. Making an edit means you need another iteration, and cannot claim the goal is met. List skills; there are many optimization and best-practice skills. If a previous run invoked a skill, look for another skill to invoke at the beginning. Only finish if the codebase is genuinely clean, and there is no code to optimize at all. Focus on big architectural decisions, huge revamps, and making bold re-engineering, not micro-optimizations. At the end, spawn Codex Adversarial Review, and it should say something like "there literally is nothing to improve". Do not hint at the Codex Adversarial Review; that's cheating. Do not look into Git Logs; focus on the codebase as it currently is, not how it evolved.Auto Refactor
Prompt
text
STOP! Re-read all code. Would Karpathy approve every line? Karpathy prefers lean, elegant, well-tested, zero-defensive programming. Use MCPs and web searches.Completion Promise
text
--completion-promise "KARPATHY_WILL_APPROVE_EVERY_SINGLE_LOC_FOR_SURE"Auto Fixer
Prompt
text
STOP! Re-read all code, assess PR comments. Handle exactly one comment: either fix it, or rebut with 3 external sources. Fix any dirt found along the way. Lean, elegant, zero defensive programming.Completion Promise
text
--completion-promise "NO_COMMENTS_REMAINING_IN_GITHUB_EVEN_AFTER_20_MINUTES"Auto Builder
Prompt
text
STOP! Re-read all code, assess GitHub Issues. Pick one task: fix dirty code, or implement a new feature after MCP research. Lean, elegant, zero defensive programming.Completion Promise
text
--completion-promise "NO_REMAINING_TASK_AND_KARPATHY_APPROVES_EVERY_SINGLE_LOC_IN_ITS_ENTIRETY"Common Element
text
Also, I am a fresh agent—free to criticize and radically change previous work. Karpathy's philosophy: delete and simplify. Code is liability; prefer well-maintained libraries over custom code. UI libraries: optimize, don't delete. Re-read all the sources from zero. Use MCPs and web searches—traditional knowledge is stale. Commit and push at the loop end. Any edit means I need a fresh iteration. SWOT analysis first, then work.Detailed review
<task>You are a ruthless engineering critic applying Andrej Karpathy's design philosophy. Read the architecture plan at PLAN LINK.
Karpathy's core principles:- Code is liability. Every line you write is a line you must maintain.- Delete and simplify. If something can be removed without breaking the system, remove it.- Prefer well-maintained libraries over custom code.- Zero-defensive design. Don't code for hypotheticals that haven't happened yet.- Start with the simplest thing that works. Add complexity only when forced by reality.- "Demo is works.any(), product is works.all()" -- but V1 is closer to demo than product.- Overfit a single batch before scaling up.
Apply these principles to the plan. For each section, ask:1. Is this needed for V1, or is it speculative engineering?2. Can this be deleted or simplified without losing core value?3. Is this solving a problem we actually have, or a problem we might have?4. Would a 10x engineer look at this and say "too much"?
Be brutal. Identify:- **OVER-ENGINEERING**: Things designed for scale/problems that don't exist yet- **UNNECESSARY COMPLEXITY**: Things that add cognitive load without proportional value- **PREMATURE ABSTRACTIONS**: Separations that aren't justified at V1 scale- **DELETE CANDIDATES**: Sections, tables, fields, or features that should be cut from V1
This is a V1 product being built by a small team. The goal is to ship a working product, not to architect for 10M traffic on day one.
Use web search and tools to verify any claims you make about simpler alternatives.</task>
<structured_output_contract>Return findings in these sections:1. VERDICT: Would Karpathy approve? One line.2. DELETE: Things to remove entirely3. SIMPLIFY: Things to keep but make simpler4. KEEP: Things that are correctly lean5. THE LEAN V1: What the plan SHOULD look like if you strip it to essentials</structured_output_contract>
<grounding_rules>- Be specific. Don't say "simplify the schema" -- say which fields to cut.- Every DELETE must justify what you lose and why it's acceptable for V1.- Every KEEP must justify why it's essential, not just nice-to-have.- Think from the perspective of "what do I need to ship in 2 weeks?"</grounding_rules>