Markback Settings

Your key is encrypted at rest on this device and sent only to Anthropic when you grade — never to any other server. If this machine is shared, rotate the key when you're done. Treat a leaked key like a leaked credit card — revoke it on console.anthropic.com.

Off by default. When on, the AI marks passages worth a second look. These flags are observations for your judgment, not evidence — writing-style signals have many benign causes. Nothing is shown to students, and you decide what, if anything, a flag means.

When enabled, PDF pages will be rendered as images and analyzed using Claude's vision capabilities. This is useful for submissions containing charts, diagrams, handwriting, or images that text extraction would miss. Uses more API credits than text-only analysis.

Limit the number of pages sent for vision analysis to control API costs.

Fill the grade input with AI-suggested score after grading.

Automatically post feedback to submission comments.

Hard ceiling on Anthropic spend per day, enforced before every grade (single and batch). Resets at midnight. Blank = unlimited.

"Downgrade" keeps grading past the cap using a cheaper model. Downgraded grades are flagged and held for review (never auto-applied).

Model ID to use once the daily cap is reached, e.g. claude-haiku-4-5.

Absolute daily ceiling — even downgraded grades stop here. Blank = stop at the cap above.

Clears the session tallies; today's cost-cap meter keeps counting and grading history is untouched.

Verbose console output across the extension, including prompt cache hit/miss rates. Leave off unless you're troubleshooting.

Downloads a JSON file with your recent grading events, session totals, and settings (API key redacted). Helpful when filing a bug.

This is the prompt sent to Claude. Edit it to customize your feedback style.

Using default prompt based on settings above.