Cursor shares a prompt for reducing token cost in agent harnesses
here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy
AISummary
Cursor's Eric Zakariasson shared a prompt for improving an LLM agent harness to lower token cost per completed task without losing quality. The prompt covers the system prompt, tool definitions, cache layout, tool results, compaction, and subagents, and reports that one team's round of these changes cut overall token cost about 7%.
AIWhy it matters
The prompt gives a concrete checklist for cutting agent token cost per completed task, with tested figures on cache layout, tool offloading, and compaction.
Source: eric zakariasson · x.com