Review economics
browser-use/video-use
Read from the 9 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥44%
Attributed
a floor
4
Attributed PRs
5
Other PRs
9
Read
Attributed — the latest 4
#29 fix(render): preserve orientation for portrait video sources
1 reviews · 43h to merge
#5 fix(subtitles): raise MarginV to 90 to clear vertical safe zones
1 reviews · 11h to merge
#6 fix(render): tone-map HLG/PQ sources to Rec.709 SDR
1 reviews · 11h to merge
#9 add install.md and one-paste setup prompt
0 reviews · 0h to merge
The rest — the latest 5
#91 Update README.md
1 reviews · 45h to merge
#34 Add Browser Use Box editing note
1 reviews · 0h to merge
#10 fix(pack_transcripts): write output as UTF-8 to fix Windows encoding error
1 reviews · 17.0d to merge
#32 Add MIT license
1 reviews · 0h to merge
#13 docs: add HyperFrames animation option
1 reviews · 9.0d to merge
How this was measured
44% 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.
Detected: Claude Code.
“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 browser-use/video-use 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 browser-use/video-use — 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