Agent harnesses only read the first 150 lines of your skill file, warns Jhaddix
rez0__ · x · 2026-10-10
Jhaddix shares a little-known detail about agent skill loading:
- Most agent harnesses (including Claude Code) only load a skill's description at startup
- Even when a skill is explicitly invoked, the agent typically reads only the first 150 lines to decide how or whether to use it
- Practical advice: put a table of mandatory steps within the first 150 lines of any skill file
- Instructions or references to scripts/templates placed past that line may be silently skipped
A direct engineering warning for anyone writing skills for Claude Code and similar tools.
More from coding & agent
- Nace AI's sub-10B decision model Drex v1.5 lands on OpenRouter — nischay_twt · 2026-10-10
- Command Center 1.3.0 ships with 40+ improvements for understanding your agent systems — jimmykoppel · 2026-10-10
- Agents kept 'worsen-bettering' her setup — one essay folder hit 862 files, 1M words — every · 2026-10-10
- Theo, zeeg and other founders on agents: they ship code faster, but have no talent or curiosity — zeeg · 2026-10-10
- Celesto Computer MCP now listed on Smithery marketplace — aniketmaurya · 2026-10-10
- Gemini 4 Argon tops deepswe at 77.9% and automationbench, still locked to trusted testers — weswinder · 2026-10-10