Review economics
zarazhangrui/frontend-slides
Read from the 8 most recently merged pull requests ·
Pull requests with attributed agent authorship took 3.5× the time to merge of the rest.
≥55%
Attributed
a floor
5
Attributed PRs
3
Other PRs
8
Read
Attributed — the latest 5
#85 docs: complete truncated description in Architecture table
0 reviews · 10h to merge
#2 Add CSS function negation gotcha to docs
1 reviews · 19.3d to merge
#48 Fix: clear navDots container and strip edit state in exportFile
0 reviews · 1h to merge
#44 feat: add Claude Code plugin marketplace support
0 reviews · 41h to merge
#23 feat: add inline editing feature documentation
0 reviews · 19h to merge
How this was measured
55% 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; 1 PR came off an agent branch with no commit attribution, so the real share runs higher.
Detected: 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 zarazhangrui/frontend-slides 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 zarazhangrui/frontend-slides — 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