Your AGENTS.md is a Liability
Frontier models top out at 68% compliance with 500 instructions. Every rule you add makes every other rule less likely to be followed. The research explains why.
Read more →The Context Wars: Why Your Browser Tools Are Bleeding Tokens
Playwright MCP's 26 tools are killing your context window. Vercel's agent-browser shows a better way: fewer tools, smarter snapshots, 93% less overhead.
Read more →Claude Code's Hidden MCP Flag: 32k Tokens Back
ENABLE_EXPERIMENTAL_MCP_CLI eliminates MCP tool schema overhead entirely. Undocumented, untested in the wild, but it works. Here's what I found.
Read more →12 Factor Agents: Principles for AI That Actually Work
HumanLayer's 12-factor agents codifies what works in production AI: own your context, keep agents small, stay out of the dumb zone.
Read more →Opus 4.5 and Tool Search: The Native Fix for MCP Context Bloat
Claude's new model ships with defer_loading for tools. The MCP isolation patterns I built are now (mostly) obsolete.
Read more →Expressing MCP Tools as Code APIs (96% Less Context)
From Chrome DevTools experiment to universal MCP wrapper: progressive discovery works with any server, Skills integration, and smart deduplication
Read more →Isolating MCP Context in Claude Code with Slash Commands
How to use slash commands to keep specialized MCP tools isolated from your main conversation context.
Read more →