Seroter Daily #864: behavioral evals for coding agents, Skills CLI 1.0, AI cost tools
rseroter · x · 2026-09-11
Richard Seroter's daily reading list (#864) covers: evaluating AI coding agents via behavioral evals rather than end-to-end benchmarks; Skills CLI 1.0 for bundling and distributing agent skills with packages; a new Google Cloud developer plugin for coding agents; five tools for controlling AI costs; the argument that AI accelerates output, not innovation; and Shopify's Shop app migrating from React Native to native code.
More from coding & agent
- Notion's bet: own your context, rent the intelligence as agents come and go — ivanhzhao · 2026-09-11
- Notion positions itself as the database layer every AI agent plugs into — ivanhzhao · 2026-09-11
- Users restructure years of personal data into AI-queryable formats, with Notion a top pick — ivanhzhao · 2026-09-11
- Dev argues MCP is unnecessary: hand agents an API key and they'll get the job done — sull · 2026-09-11
- Dev to add AI-friendly collision checking CLI to OpenSCAD — _Stocko_ · 2026-09-11
- Cadenya: a year-long indie build of an MCP-powered agent runtime — littlebobbyt · 2026-09-11