Review economics
vercel-labs/agent-skills
Read from the 63 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.4× the reviews submitted of the rest.
≥17%
Attributed
a floor
12
Attributed PRs
51
Other PRs
63
Read
Attributed — the latest 5
#308 react-view-transitions: field learnings — morphs, isolation, interactivity
1 reviews · 2h to merge
#306 react-view-transitions: isolation, scroll-hang, reveal-flicker, shared-element placement
3 reviews · 2h to merge
#287 fix(vercel-optimize): run vercel via node entry on Windows (execFile can't spawn .cmd)
1 reviews · 2.0d to merge
#231 vercel-cli-with-tokens: correct CLI commands, add Stripe Projects plan changes
6 reviews · 5h to merge
#188 vercel-cli-with-tokens: improve token handling and security
0 reviews · 0h to merge
The rest — the latest 5
#310 Update install command for view transition skill
1 reviews · 0h to merge
#272 Add writing-guidelines skill
1 reviews · 6.6d to merge
#273 Harden Vercel Optimize report safety
1 reviews · 3h to merge
#268 Harden vercel-optimize project scope preflight
1 reviews · 0h to merge
#266 Harden vercel-optimize Workflow guidance
1 reviews · 0h to merge
How this was measured
17% 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 vercel-labs/agent-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/agent-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