Review economics
vercel-labs/skills
Read from the 99 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.4× the time to merge of the rest.
≥2%
Attributed
a floor
3
Attributed PRs
96
Other PRs
99
Read
Attributed — the latest 3
The rest — the latest 5
#1743 fix: store local path sources in lockfile using portable source
0 reviews · 14.6d to merge
#1865 fix(update): normalize GitHub shorthand for project deletion checks
0 reviews · 1h to merge
#1748 fix(find): show all registry results in non-interactive search
0 reviews · 14.3d to merge
#1837 fix: preserve locked GitHub host during updates
0 reviews · 4.1d to merge
#1866 fix: discover skills nested under two categories
0 reviews · 0h to merge
How this was measured
2% 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; reads 99 of 231 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Cursor agent.
“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 vercel-labs/skills 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 vercel-labs/skills — 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