Review economics
abi/screenshot-to-code
Read from the 83 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.5× the commits after first review of the rest.
≥13%
Attributed
a floor
20
Attributed PRs
63
Other PRs
83
Read
Attributed — the latest 5
#612 Remove GPT-Image-2 image fallback
1 reviews · 4h to merge
#613 Support Replicate key in settings
0 reviews · 0h to merge
#607 Set up Cursor Cloud dev environment
0 reviews · 0h to merge
#604 Implement new method of converting screenshots to code
1 reviews · 4h to merge
#605 Replace GPT 5.2 Codex with GPT 5.5 models
1 reviews · 0h to merge
The rest — the latest 5
#597 Add Lilo sponsor logo to README
0 reviews · 0h to merge
#576 OpenAI caching
1 reviews · 0h to merge
#570 Hide slow-model banner outside active generation
0 reviews · 0h to merge
#568 Migrate model choice sets to Gemini 3.1 Pro
0 reviews · 0h to merge
#567 Keep create inputs on full request failure
1 reviews · 0h to merge
How this was measured
13% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; 9 PRs came off an agent branch with no commit attribution, so the real share runs higher.
Detected: Cursor agent, Claude Code, OpenAI Codex.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read abi/screenshot-to-code weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on abi/screenshot-to-code — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository