Pawel Huryn ships open-source AI review kit: document intent, then audit code against it
PawelHuryn · x · 2026-09-16
Pawel Huryn updated his pm-skills repo (26.3k stars) with a free pm-ai-shipping kit for PMs and founders accountable for AI-built code.
Core idea: agents write code fast but leave no record of intent—what the system should do, who may do what, where secrets live. Without that record, no human or auditing agent can tell if code is safe to ship. The kit documents the system, then audits the gap between docs and code—the class of bugs generic scanners miss because they lack a model of intent.
Commands include documenting intent, deriving tests, and code/security/performance reviews. His "7 truths": /goal alone isn't enough—explain the why plus strategic context (market segments, value proposition, revenue model) via progressive disclosure so agents make better autonomous decisions. Start with /ship-check.
More from coding & agent
- Cartwheel MCP connects AI animation to Unreal Engine — andrew_n_carr · 2026-09-16
- Burkov uses Codex, Claude Code and Grok interchangeably — and says that's bad news for all three — burkov · 2026-09-16
- Four LLM mayors, one deterministic city: open-source loop-design experiment wins CoreWeave Hacks top prize — hackgoofer · 2026-09-16
- ComfyUI Music Toolkit 3.0 adds YuE2-powered audio covers via SheetSage2 and ABC scores — Vivid_Promise1700 · 2026-09-16
- Steve Yegge: only Claude Fable is worth a damn, and it's too expensive — orchestrators won't work for a year — Steve_Yegge · 2026-09-16
- Running Grok Bot and Hermes as Project Managers, Then Stacking One Agent on Top of the Other — mazzaTalk · 2026-09-16