Review economics

microsoft/semantic-kernel

Read from the 100 most recently merged pull requests ·

Pull requests with attributed agent authorship took 1.3× the reviews submitted of the rest.

≥50%

Attributed

a floor

53

Attributed PRs

47

Other PRs

100

Read

Per pull requestAttributedRestRatio
Review rounds0.00.0
Reviews submitted5.94.51.3×
Commits after first review2.51.41.8×
Reverts0.00.0
Time to merge6.7d20.7d0.3×

How this was measured

50% 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 5597 merged PRs — the rest have not been analyzed yet.

Detected: GitHub Copilot coding agent, Claude Code, 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

XLinkedInHacker News
Review tax badge for microsoft/semantic-kernel

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

Tell me when this moves

We re-read microsoft/semantic-kernel 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 microsoft/semantic-kernel — 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

microsoft/semantic-kernel — the review cost of AI-authored code