Glossary · term188 of 202
token budget
A fixed cap on how many tokens a prompt may use, the objective a compression algorithm optimizes toward without regard for which tokens an action actually depends on.
At a glance
- cited by
- 4 posts
- categories
- 3
- first used
- apr 2026
Token-Compression Skills Do Not Survive MeasurementToken compression skills report savings the invoice never shows. Cache reads carry 87 percent of an agent bill, and cutting tokens can push the cost up.
6 Critics Grade My Post, Then Fix the Skill That Wrote ItSix critics grade the draft, then patch the SKILL.md that wrote it. The merge code, verdict ladder, and guardrails behind a self-improving Claude Code skill.
AI Agents in Production: What Actually Works After 6 MonthsMost AI agent projects die between demo and production. After 6 months running agents at scale, these are the patterns that survived: model routing, trace-based debugging, loop detection, and hard cost ceilings.
Building an MCP Server From Scratch (The Parts Nobody Explains)Build an MCP server in TypeScript from zero. Covers the handshake, Streamable HTTP transport, OAuth 2.1 auth, error codes the SDK swallows, and production deployment patterns.