Inspired by karpathy/autoresearch. Put this in a Ralph Loop.

Use each mode-specific prompt together with the common element block.

Auto Refactor

Prompt

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

--completion-promise "KARPATHY_WILL_APPROVE_EVERY_SINGLE_LOC_FOR_SURE"

Auto Fixer

Prompt

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

--completion-promise "NO_COMMENTS_REMAINING_IN_GITHUB_EVEN_AFTER_20_MINUTES"

Auto Builder

Prompt

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

--completion-promise "NO_REMAINING_TASK_AND_KARPATHY_APPROVES_EVERY_SINGLE_LOC_IN_ITS_ENTIRETY"

Common Element

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>

Why? Multi-tenant environments. First, we need to understand a few differences between environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

So

• When you run Claude Code on your local MacBook, the first two are always local. The third is usually the Claude.ai server.
• When you ssh to a virtual private server (VPS) and install Claude Code there, the first two are your remote server. The third is still the Claude.ai server.
• When you run Claude RC on your virtual private server and code from your iPad using the Claude app, the end-user UI is on your iPad, the agent runtime environment is on your VPS, and the server is still Claude.ai.

Most people physically separate their tenancy, such as Claude Code, from their personal vs. work laptops. So in most cases, it's not a big deal.

But when you need multi-tenancy, it becomes super stressful. For example, say you have two different toolkits:

• personal toolkits (personal Notion, personal Sentry, personal Linear)
• workplace toolkits (company Notion, company Sentry, company Linear)

Most MCP auth states or code harnesses don't support profiles, so you can only log in to one.

So therefore... a natural evolution was to have both:

• a personal VPS with all personal toolkits set up
• a workplace VPS with all workspace toolkits set up

to physically isolate tenancies.

Now we've solved the multiple-profile issue, but the client's problems persist. Now let's get back to the environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

All MCP auth or toolkit auth info should always be saved in the Agent Runtime Environment IMHO. However, a surprising number of harnesses tie them to the LLM server (such as Codex Apps or Claude.ai Plugins) or put them in the end-user UI (Claude Desktop or Codex Desktop).

Now the problem is:

• If the auth data is put on the LLM server, you cannot reuse LLM accounts across tenants
• If the auth data is put on the end-user UI, you cannot use the same app to access multi-tenants.

The only way to reliably isolate different auth information is thus:

• You ssh to a virtual private server (VPS) and run Claude Code there. Never use LLM server plugins.

Then

• End-user UI
• Agent Runtime Environment

are both isolated VPS, and

• LLM Server holds no information on the tenancy

This way, you can provide different toolkits, creating multiple dev environments.

인생은 특이하다. 우리는 선택하지 않은 세상에 태어나고, 공허로 돌아가기 전 찰나의 시간에 존재한다. 많은 사람들은 이 터무니없는 삶을 이해하기를 바라며 의미와 목적을 찾으며 시간을 보낸다. 하지만 모든 것이 궁극적으로 무의미하다면...

긍정적 허무주의는 삶을 살 가치가 있게 만드는 작은 순간에서 기쁨과 목적을 찾으면서 존재의 무의미함을 인정한다. 생명체는 본질적인 의미나 목적이 없으며 우리가 무한한 우주의 먼지일 뿐이라는 것이다. 좀 슬프긴 한데, 이 깨달음에서 자유를 찾는 것이 핵심이다. 우리가 뭘 하든 우주에 중요하지 않기 때문에 우리가 하고 싶은 의미와 목적을 자유롭게 창조할 수 있다는 것. 우리를 행복하게 하고 성취감을 주는 것들에 집중하자. 비록 그것들이 더 큰 의미를 지니지 않더라도.

마찬가지로 "존재의 부조리"는 삶에 내재된 의미나 목적이 없으며 세상이 인간의 이성으로 완전히 이해될 수 없다는 생각이다. 그것은 또한 의미를 찾는 우리의 자연적인 욕구와 우주의 명백한 무의미 사이의 갈등이나 불일치를 설명하기 위해 사용되는 용어이다.

물론, 어떤 사람들은 삶이 더 큰 목적을 가지고 있고 그들의 행동이 즉각적인 영향을 넘어서는 의미를 가지고 있다는 생각에서 동력을 얻는다. 그것도 좋다. 긍정적 허무주의의 장점은 그것이 무엇이든 간에 우리가 삶의 의미를 찾을 수 있게 해준다는 것이다. 목적을 창조하고 중요한 것들에서 기쁨을 찾을 수 있다면 그야말로 최고이다.

어쩌면 우리는 우리가 통제할 수 없는 것들에 대해 걱정하는 데 너무 많은 시간을 보내는 중일지도 모른다. 그보다 우리는 현재의 순간에 집중하고 우리에게 행복을 가져다주는 작은 것들을 즐기면 더 좋을 것이다. 거대한 전통을 남기거나 영구적인 변화를 일으키지 못해도 뭐 어떤가. 지금 현재 우리에게 중요한 것들에 집중하자.

사랑받지 못하는 것은 불행한 것이다. 하지만 사랑하지 않는 것은 수치스러운 것이다.

-- 알베르 카뮈 (1913-1960)