Review economics

BoundaryML/baml

Read from the 100 most recently merged pull requests ·

Pull requests with attributed agent authorship took 1.1× the review rounds of the rest.

≥6%

Attributed

a floor

8

Attributed PRs

92

Other PRs

100

Read

Per pull requestAttributedRestRatio
Review rounds0.90.81.1×
Reviews submitted7.13.12.3×
Commits after first review1.51.80.8×
Reverts0.00.0
Time to merge14h14h1.0×

Against other teams

Attributed work here takes 1.1× the review rounds of the rest — above the 0.6× median across 1985 published teams.

Higher than 72% of the 1985 published reports. See the distribution

How this was measured

6% 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; 17 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 2831 merged PRs — the rest have not been analyzed yet.

Detected: Claude Code, OpenAI Codex, Cursor 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

XLinkedInHacker News
Review tax badge for BoundaryML/baml

The badge reads this repo’s current report, so it follows the number.

Tell me when this moves

We re-read BoundaryML/baml 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-tax

Want this continuously on BoundaryML/baml — 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