sohaibt/product-mode
217 stars · Last commit 2026-10-10
The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.
README preview
# product-mode  **Give your coding agent product judgment before it starts building.** Free, MIT-licensed instructions for framing the problem, cutting scope, naming tradeoffs, and defining success. A drop-in `CLAUDE.md` / `AGENTS.md` for Claude Code, Cursor, Codex, and any coding agent that reads one. The CLI is optional. The PM-team counterpart to [andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills). Credit to [@karpathy](https://x.com/karpathy) for naming the failure modes that inspired this work. ## Recent improvements - **Questions that move the work forward:** inspect existing context first, ask about material decisions, and match unknowns to evidence, a decision, a prototype, or an experiment. Continue authorized, reversible work once the next useful step is clear. - **More conservative CLI advice:** only small edits to existing ordinary documentation can automatically qualify as trivial. Code and agent instructions require review; failed commands return a nonzero status, and interactive commands explain when a terminal is required. - **Checks you can inspect:** [six authored evaluation cases](./examples/uncertainty.md) for the product guidance, plus [CI](./.github/workflows/ci.yml) covering lint, instruction-file consistency, and CLI/package tests on Node 20.19, 22, and 24. The cases are prompts for comparison, not measured evidence of better agent decisions. The updated instruction files are available now through the quick start below. The CLI fixes are merged on GitHub; see [CLI release availability](#installation) before installing from npm. ---