What is optimize-agents-md?
Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective. Source: plaited/agent-eval-harness.
Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective.
Quickly install optimize-agents-md AI skill to your development environment via command line
Source: plaited/agent-eval-harness.
Apply Boris Cherny's compression principles to AGENTS.md and rules files.
| Context stuffing | Repeating info agents already know | Delete obvious instructions | | Static memory | No learnings section | Add ## Learnings with dates | | Format drift | Inconsistent structure | Use consistent headers | | Missing verification | No way to check work | Add Verify: patterns to rules |
| Verbose rules | Paragraphs instead of patterns | Compress to pattern + verify + fix |
Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective. Source: plaited/agent-eval-harness.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/plaited/agent-eval-harness --skill optimize-agents-mdOptimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective. Source: plaited/agent-eval-harness.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/plaited/agent-eval-harness --skill optimize-agents-md Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/plaited/agent-eval-harness