Originally published on rohitraj.tech
Week 31 of 2026 shipped one story twice. GitHub made agent skills and MCP generally available in Copilot code review, Google added hooks to Gemini Managed Agents — and on the same day, a benchmark showed the best model follows a written policy document just 36.2% of the time, while a self-propagating worm walked through Copilot for Word. Plus what Kimi K3 really costs to run locally (594 GB floor) and the 250B sleeper release you can actually serve.
Read the full version with code samples, diagrams, and architecture details: This Week in AI Dev: Agent Skills Went GA, Then the Benchmark Landed (Week 31 of 2026)
More engineering notes: rohitraj.tech/en/notes
Top comments (0)