Review economics
felixrieseberg/windows95
Read from the 58 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.0× the time to merge of the rest.
≥51%
Attributed
a floor
33
Attributed PRs
25
Other PRs
58
Read
Attributed — the latest 5
#383 Bump all dependencies, version to 6.0.0
0 reviews · 0h to merge
#382 Image tooling and prep for the v6 disk image release
0 reviews · 5h to merge
#380 Run QEMU with vmport=off so the mouse is usable
0 reviews · 0h to merge
#379 Fix stale state-v4.bin references in probe docs and probe-tcp.sh
0 reviews · 0h to merge
#378 Degrade gracefully when the shared folder no longer exists
0 reviews · 0h to merge
The rest — the latest 5
#373 Bump ip-address from 10.1.0 to 10.2.0
0 reviews · 28.6d to merge
#372 Bump @xmldom/xmldom from 0.8.12 to 0.8.13
0 reviews · 42.5d to merge
#374 Bump fast-uri from 3.1.0 to 3.1.2
0 reviews · 26.5d to merge
#375 Bump @tootallnate/once from 2.0.0 to 2.0.1
0 reviews · 13.4d to merge
#381 Bump postcss from 8.5.9 to 8.5.15
0 reviews · 22h to merge
How this was measured
51% 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 felixrieseberg/windows95 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 felixrieseberg/windows95 — 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