here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy # Improve this agent harness's token efficiency You're working on an LLM agent harness: the system prompt,
Why CEREBRO kept it
Token efficiency for agent harnesses, Cursor's production learnings.
The text below is an automated extraction of the article at https://x.com/ericzakariasson/status/2102853511637774551, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
# Improve this agent harness's token efficiency
You're working on an LLM agent harness: the system prompt,
> Token efficiency for agent harnesses, Cursor's production learnings.
here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy
# Improve this agent harness's token efficiency
You're working on an LLM agent harness: the system prompt, tool definitions, request assembly, context caching, compaction, and retrieval, and how work is split across agents. Make the agent's runs cheaper without making it worse at its job.
- Objective: lower price-weighted token cost per completed task. - Constraint: no measurable drop in task quality.
Measure per task, not per request. Every turn resends the prefix (tools, instructions, setup, and th
Backlinks
Appeared in 1 briefing