Review economics
actualbudget/actual
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.5× the review rounds of the rest.
≥12%
Attributed
a floor
20
Attributed PRs
80
Other PRs
100
Read
Attributed — the latest 5
#8644 [AI] Add blog post: sidenav design competition voting is open
1 round · 9 reviews · 11h to merge
#8624 [AI] Fix missing payee on schedule previews if the schedule has a split
3 reviews · 4h to merge
#8609 [AI] Show schedule name in mobile notes in upcoming schedules
4 reviews · 2h to merge
#8611 [AI] Add Discord notifications for new tags and published releases
1 round · 5 reviews · 1h to merge
#8580 [AI] Add a column manager to the transaction table
1 round · 13 reviews · 5.7d to merge
The rest — the latest 5
#8523 fix(crossover-report): render empty state when no accounts exist (#8512)
1 round · 7 reviews · 15.3d to merge
#8630 Bump the npm_and_yarn group across 1 directory with 5 updates
2 reviews · 24h to merge
#8551 :bar_chart: Monte Carlo Analysis report
1 round · 11 reviews · 12.0d to merge
#8385 [AI] Drag-and-drop reordering for upcoming scheduled transactions
2 rounds · 5 reviews · 31.8d to merge
#8559 feat: Add ILS currency
2 reviews · 10.3d to merge
How this was measured
12% 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; 1 PR came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 3946 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Cursor agent, GitHub Copilot coding agent, Gemini CLI, OpenAI Codex.
“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 actualbudget/actual 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 actualbudget/actual — 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