At a glance Claude Corner tip Claude Code v2.1.288 and later accept –max-findings on the local /code-review command, with a number N, all, or default. The value is sticky: later reviews reuse it until you pass default, so reset when you are done. On the morning of 7 October 2026, npm latest and next were … Read more
Monday is a defaults day rather than a launch day, because the two changes worth your time both alter what happens when nobody touches a setting. Codex shipped v0.158.0 overnight and now asks before it types into a terminal running with elevated permissions, while GitHub’s 28 Aug…
At a glance Gemini Tip Gemini Tip: Inconsistent Code Reviews → Encode a Rubric Gem Turn a one-off review checklist into a reusable Gem you open from gemini.google.com or the Workspace side panel. Encode severity, blocking rules, and output format once so every PR gets the same review shape. Optionally attach a Drive rubric Doc … Read more
Saturday is an interoperability and cleanup morning, so the useful work is how these four moves fit together. Anthropic stops making dual-agent repos maintain a CLAUDE.md symlink just to share AGENTS.md, GitHub makes Copilot review progress readable across commits, Copilot admins…
The coding stack is no longer a neutral layer sitting under whoever ships the best model this week. Over the weekend OpenAI notified SpaceX that it will wind down the contract that puts OpenAI models inside Cursor, proposing a November 12 shutoff—the longest notice its…
AI agent tooling crossed another practical threshold this week. GitHub’s July 29 general availability of agent skills and MCP integration in Copilot code review lets teams inject repository-specific standards and external context directly into automated reviews without custom…
