📎 Claude Code в больших кодовых базах: практики и старт Если вы пробовали дать ИИ-агенту большой репозиторий и получали хаос, проблема часто не в модели. Большим проектам нужна подготовленная среда: короткие CLAUDE.md, локальные команды тестов, исключения для шумных файлов, LSP, хуки, Skills и MCP. Перевёл и адаптировал статью Anthropic о том, как Claude Code работает в монорепозиториях, старых системах и больших инженерных организациях. Получился практичный разбор: с чего начать, что держать в
Pulling top comments from 5 nearest past posts and asking the model to mirror their style — about 8 seconds.
ForesynClosest the rewriter got vs your draft (32 pts) — none beat it; here's what was tried
Generating 8 candidates across strategies, scoring each, then a 2nd round if fewer than 3 beat your draft — up to ~20 seconds.
ForesynAuto-improve — branch out, keep climbing, stop on plateau
Greedy hill-climb: each iteration generates 8 rewrites, picks the highest-scoring one, then rewrites from THAT. Stops on plateau or after 5 iterations. Free, ~30–60 sec, rate-limited to 3 runs per minute.
Edit & re-score
YC S26Help us get into Y Combinator Summer 2026
This HN tool is a weekend side project. The real Foresyn is the company brain behind it — agents that ship reviewable AI work for real B2B teams. We're applying to YC Summer 2026 right now.
Know a YC partner? Please tell them about us — even a “hey, look at this team” message means a lot.
Why we think we deserve a look: founder is ex-Stripe, worked on AI review tooling for high-context fraud/rules workflows. Live product with reviewable workflows, agent workers, and a memory loop that compounds corrections. This HN microsite is a 3-day demo of the same engine — pixel-faithful HN clone with a virality predictor that beats the 2014 baseline. We ship fast and we ship real.