contextburn for Gemini CLI

ai.arsentev/contextburn

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

client:Gemini CLI transport:stdio runtime:pypi

Install contextburn in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

{
  "mcpServers": {
    "contextburn": {
      "command": "uvx",
      "args": [
        "contextburn"
      ]
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs