DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run the benchmark from Claude Code with Edit Drift

Install the plugin and let Claude Code drive scoring and reporting.

Short answer: Run /plugin marketplace add MegaTroll222/edit-drift; then run /plugin install edit-drift@edit-drift; point it at your results folder. All steps.

Who it is forA developer who prefers asking an agent over learning a CLI.

The problemBenchmark CLIs have many steps.

The outcomeAgent-run scoring and reports.

What you need first

  • Python with pip
  • Outputs from the image models you want to compare

Steps

  1. Run /plugin marketplace add MegaTroll222/edit-drift
  2. Run /plugin install edit-drift@edit-drift
  3. Point it at your results folder
  4. Ask for scores and a report

Prompt for your agent

Using the edit-drift Claude Code plugin, score results in <folder> and produce the report. Confirm scores.json exists for each model.

Caveat. Masks per step must match your image size; use editdrift mask to generate them.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for MegaTroll222/edit-drift and "Run the benchmark from Claude Code"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer