Review economics
basecamp/fizzy
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.9× the reviews submitted of the rest.
≥8%
Attributed
a floor
12
Attributed PRs
88
Other PRs
100
Read
Attributed — the latest 5
#3024 Add a Kamal query alias for read-only database queries
1 reviews · 0h to merge
#2980 Bump trilogy to 2.12.6
0 reviews · 1h to merge
#2967 Address Copilot review on Rails-edge PR (#2965 follow-up)
2 reviews · 5h to merge
#2965 Upgrade rails to edge (813301c1)
13 reviews · 17h to merge
#2962 Bump json to 2.20.0 (CVE-2026-54696)
1 reviews · 0h to merge
The rest — the latest 5
#3021 Upgrade rails to d0e506f1
1 reviews · 18h to merge
#3023 Prefix Action Text attachment URLs with the account slug
1 reviews · 0h to merge
#1998 Test Notifications::SettingsController
1 reviews · 3h to merge
#3019 Pair the negative control's real and mutant probes under one setting
1 reviews · 11h to merge
#3018 Force activate_aggressive off for the mutated-hook checks only
1 reviews · 0h to merge
How this was measured
8% 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 100 of 1977 merged PRs — the rest have not been analyzed yet.
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 basecamp/fizzy 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 basecamp/fizzy — 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