Review economics
paperclipai/paperclip
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.7× the reviews submitted of the rest.
≥24%
Attributed
a floor
33
Attributed PRs
67
Other PRs
100
Read
Attributed — the latest 5
#10873 fix(adapter-utils): carry the workspace origin remote into transported git workspaces
1 reviews · 13h to merge
#10843 feat(issues): explain cross-task agent writes with attribution, audit receipts, and actionable denials
1 reviews · 8h to merge
#10833 feat(claude): environment-aware test-environment probe and claude-local CI coverage
3 reviews · 1h to merge
#10795 db: env-configurable client options; parallelize attention feed queries
2 reviews · 11h to merge
#10805 fix(daytona): replace bwrap user-namespace with su privilege drop
1 reviews · 0h to merge
The rest — the latest 5
#10907 chore(plugin-daytona): pin @daytonaio/sdk to 0.203.0
1 reviews · 1h to merge
#10875 fix(ui): use HTTP-safe clipboard copy everywhere
0 reviews · 11h to merge
#10891 Remove decision and review summaries from issue headers
0 reviews · 1h to merge
#10893 fix(auth): clarify protected-agent assignment blocks
1 reviews · 1h to merge
#10892 fix(decisions): retire completed-target decisions and link targets from the card
2 reviews · 1h to merge
How this was measured
24% 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 1513 merged PRs — the rest have not been analyzed yet.
Detected: Devin, Claude Code, Cursor agent, GitHub Copilot coding 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 paperclipai/paperclip 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 paperclipai/paperclip — 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