Review economics
BloopAI/vibe-kanban
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.
≥33%
Attributed
a floor
40
Attributed PRs
60
Other PRs
100
Read
Attributed — the latest 5
#3367 fix: scope vendored openssl to linux to unbreak windows-msvc cross-compile (Vibe Kanban)
0 reviews · 0h to merge
#3366 fix: vendor openssl to unblock musl + windows-msvc cross-compile (Vibe Kanban)
0 reviews · 1h to merge
#3365 chore: bump Claude Code to 2.1.112 and add xhigh effort variant (Vibe Kanban)
1 reviews · 1h to merge
#3301 fix: copy patches/ directory in Dockerfile fe-builder stage
0 reviews · 29h to merge
#3318 fix: reap execution process groups on natural exit (Vibe Kanban)
3 reviews · 3h to merge
The rest — the latest 5
#3389 Sort model selector models alphabetically (Vibe Kanban)
2 reviews · 0h to merge
#3388 Replace README hiring banner with sunsetting notice (Vibe Kanban)
0 reviews · 0h to merge
#3387 Sunset project routes to an export-only page (Vibe Kanban)
1 reviews · 0h to merge
#3385 Bump Codex to 0.124.0 and refresh the Codex executor surface (Vibe Kanban)
0 reviews · 0h to merge
#3384 Bump Claude Code CLI pin to 2.1.119 (Vibe Kanban)
0 reviews · 0h to merge
How this was measured
33% 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 1826 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 BloopAI/vibe-kanban 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 BloopAI/vibe-kanban — 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