claudeers.

🔓 unclaimed — this page was auto-generated from GitHub. Are you the creator?

Claim this page →
// Claude Skills

product-mode

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A CLAUDE.md for PM + eng teams using Claude Code- 7 principles for problem…

Slowing down
77/100
last commit 3 months ago
last release none
releases 0
open issues 0
// install
git clone https://github.com/sohaibt/product-mode

product-mode

product-mode

A CLAUDE.md for product teams who ship the right thing- not just ship fast.

The PM-team counterpart to andrej-karpathy-skills. Credit to @karpathy for naming the failure modes that inspired this work.


The Two Problems

Karpathy named the problem for engineers working with LLMs:

"The models make wrong assumptions on your behalf and just run along with them... They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should."

His CLAUDE.md fixes this for solo engineers. It's excellent.

But there's a failure mode it doesn't touch, the one that kills product teams:

Shipping the wrong thing, well.

A beautifully implemented feature for a problem that doesn't matter is still waste. And in mixed PM + engineering teams working with Claude Code, that's the more expensive mistake.

product-mode adds the missing layer: problem framing, scope discipline, tradeoff articulation, outcome measurement, and decision logging- applied before the code gets written.


The Seven Principles

#PrincipleWhat it prevents
1Frame the Problem Before the SolutionBuilding for the wrong user
2Make Assumptions & Unknowns VisibleSilent guessing
3Ship the Minimum Viable ChangeScope creep, gold-plating
4Name the TradeoffsInvisible costs, political decisions
5Define Done by Outcome, Not Output"Merged" mistaken for "done"
6Instrument Before You ShipShipping blind
7Log the Decision, Flag ReversibilityRepeating mistakes, calcifying defaults

Plus a pre-flight checklist (5 questions before any non-trivial change) and a when-to-skip-this-rigor table: because not every typo needs a decision log.

Full file: CLAUDE.md


Install

New project:

curl -o CLAUDE.md https://raw.githubusercontent.com/sohaibt/product-mode/main/CLAUDE.md

Existing CLAUDE.md (append):

echo "" >> CLAUDE.md
curl https://raw.githubusercontent.com/sohaibt/product-mode/main/CLAUDE.md >> CLAUDE.md

Who This Is For

  • PMs who vibe-code with Claude Code, Cursor, or Lovable and want their AI to think like a product partner
  • Engineering teams working alongside product, tired of re-shipping because the problem was wrong
  • Solo founders building SaaS who want guardrails against their own scope creep

If you're shipping with AI and your bottleneck is what to build, not how to build it this is for you.


Why This Exists

I've spent 20+ years in product leadership (Booking.com, Foodics, Eneco, Tamatem Games). I am now building products, one specifically to help solve the problem of not building the right thing (not announced yet) and write about Product Management and AI-assisted product building at Mastering Product HQ.

Every week I see the same pattern: teams using Claude Code to ship faster- and shipping the wrong thing faster. Karpathy nailed the engineering half. This file tries to nail the product half.


Customization

These principles are meant to be merged with your project's own CLAUDE.md. Add project-specific context below the seven principles:

## Project-Specific Context

- Our primary user is [X]
- Success metric for this quarter is [Y]
- We intentionally avoid [Z]

Tradeoff Note

These guidelines bias toward rigor over speed. For trivial changes (typos, obvious fixes), use judgment- the file includes a when to skip this rigor table at the end.


License

MIT. Fork, adapt, make it your team's own. If it helps, a star is appreciated.


Inspired by andrej-karpathy-skills and Andrej Karpathy's observations on LLM coding pitfalls.

// compatibility

Platformsapi
Operating systems
AI compatibilityclaude
LicenseMIT
Pricingopen-source
Language

// faq

What is product-mode?

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A CLAUDE.md for PM + eng teams using Claude Code- 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.. It is open-source on GitHub.

Is product-mode free to use?

product-mode is open-source under the MIT license, so it is free to use.

What category does product-mode belong to?

product-mode is listed under other in the Claudeers registry of Claude-compatible tools.

0 views
44 stars
unclaimed
updated 15 days ago

// embed badge

product-mode on Claudeers
[![Claudeers](https://claudeers.com/api/badge/product-mode.svg)](https://claudeers.com/product-mode)

// retro hit counter

product-mode hit counter
[![Hits](https://claudeers.com/api/counter/product-mode.svg)](https://claudeers.com/product-mode)

// reviews

// guestbook

0/500

// related in Claude Skills

🔓

An agentic skills framework & software development methodology that works.

// skillsobra/Shell249,840MIT[ claude ]
🔓

Public repository for Agent Skills

// skillsanthropics/Python159,495[ claude ]
🔓

💫 Toolkit to help you get started with Spec-Driven Development

// skillsgithub/Python117,790MIT[ claude ]
🔓

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…

// skillsGraphify-Labs/Python77,228MIT[ claude ]
Connectorlinks several projects together across the ecosystem · 12 connections
→ see how product-mode connects across the ecosystem