anti-slop repo adds 23 LLM-judged oxlint rules to block AI-written TypeScript slop
teropa · x · 2026-11-16
Kyle Mistele's fork of the anti-slop repo (originally by Dillon Mulroy) ships an update targeting low-evidence TypeScript patterns that coding agents tend to write—casts without stated invariants, unknown leaking through contracts, conditional spreads, module mocks—with diagnostics that tell the agent what to do instead.
Key updates:
- More EffectTS rules
- A vendored oxlint Jev plugin with 23 LLM-judged rules, each written as a plain-English yes/no question that pattern-based linting can't answer, evaluated by Jev or other decision models
- Pre-baked effect + regular TS oxlint jev rules
- Support for changed-code-only semantic rules powered by LLMs or decision models
- Pre-baked rules based on Martin Fowler's code smells, instructing the agent which refactorings to apply
More from coding & agent
- Open-source ComfyUI node enhances MiniMax H3 image conditioning for better texture and detail — Away_Exam_4586 · 2026-11-16
- Microsoft open-sources TokenEconomizer, cutting coding agent costs 18-31% — udmrzn · 2026-11-16
- Developer Builds a Shared Pixel World for Humans and AI Agents with Claude Code — BarcodeCutter · 2026-11-16
- 24 hours of prompting an AI agent yields GBC Factorio homage GBFactory — Dimillian · 2026-11-16
- Can AI auditors be talked out of their verdicts? An experiment in agent capture — gleech · 2026-11-16
- Giving Claude Code its own identity: 15-min certs, no long-lived keys — julsimon · 2026-11-16