Microsoft Paper Reveals Hidden Costs of Bad Skills in AI Agent Harnesses
omarsar0 · x · 2026-08-13
Major agent harnesses rely on skill libraries for extra guidance, assuming it's free. A new paper from Microsoft and colleagues measures what a bad skill actually costs.
Researchers attributed 307 agent failures to specific loaded skills (125 functional failures and 182 efficiency regressions) by comparing each skill-guided run against a matched reference run.
- Root of failures: Failures rarely come from irrelevant skills. Seemingly relevant skills often push the agent to incorrectly implement or omit task requirements.
- Efficiency costs: Cost regressions aren't explained by prompt length alone. The largest source is excessive verification (67 cases), followed by heavy implementation pipelines (30 cases). Skills quietly turn validation checklists into mandatory work.
More from coding & agent
- HolaOS Tops GitHub Trending as Open-Source Desktop Agent with Model Flexibility — alifcoder · 2026-08-14
- Building 3D Action Games with Claude: 'Dark Souls' in 7 Hours — vrdrift · 2026-08-14
- DeepSeek V4 Flash Makes AI Agents Affordable for Everyone — Teknium · 2026-08-14
- Workflow for Building iOS Apps Entirely via Claude Mobile — EricBuess · 2026-08-14
- DeepSeek Ships V4 Pro, Open-Sources Agent Software, Raises API Prices — The Decoder · 2026-08-14
- Are Agent Harnesses the Boring Way to Continual Learning? — scaling01 · 2026-08-14