Pawel Huryn open-sources pm-ai-shipping kit to make vibe-coded apps reviewable
PawelHuryn · x · 2026-10-17
AI commentator Pawel Huryn released pm-ai-shipping, an open-source kit for PMs and founders accountable for AI-built code.
The premise: agents write code fast but leave no record of intent — what the system should do, who may do what, where secrets live. The kit restores reviewability in two stages: document the system, then audit the gap between docs and code — the bug class generic scanners miss because they lack a model of intent.
Entry point is /ship-check, with specialist commands for single stages; it follows the repo's own setup and falls back to sensible defaults. Huryn also plans to test it against Opus 5.5 on his bug hunt bench, noting the skill's main value is self-critiquing findings before presenting them, not teaching the model to find bugs.
Related event: Pawel Huryn Open-Sources pm-ai-shipping, Boosting AI Code Review(2 posts)→
More from coding & agent
- Monid ranks agent tools by real usage: TinyFish leads with 754K weekly transactions — HeyAmit_ · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- Capy 0.5.0 lets Claude Pro/Max subscribers reuse their plan quota, adds OIDC cloud access — garrytan · 2026-10-23