Post-Agent Era: Strict Code Quality Control via Massive AST Rules
mattrickard · x · 2026-07-07
The author's team, corigin, built an extremely strict and opinionated "Post-Agent" code quality gate internally. They use a massive number of custom AST rules and auto-fixes to constrain code generated by AI agents, acting far beyond a regular linter—every agent code smell corresponds to a regression rule, some deterministically fixable, others handed back to the agent. The team also disables many legitimate syntaxes by default, including TS's any/unknown and Rust's unsafe, enabling them only in isolation when necessary, alongside strict restrictions on code styles and CSS files.
More from coding & agent
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11