Review economics
Gitlawb/openclaude
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.6× the review rounds of the rest.
≥5%
Attributed
a floor
12
Attributed PRs
88
Other PRs
100
Read
Attributed — the latest 5
#2069 docs(readme): add npm monthly downloads badge
1 reviews · 0h to merge
#2065 feat(web): replace favicon/logo with Ember Block O brand mark
1 reviews · 0h to merge
#2061 fix(web): make web/ build standalone — stop importing the repo-root p…
1 round · 3 reviews · 0h to merge
#2060 feat(web): v0.26 refresh — buddy page, changelog, partners, provider …
3 rounds · 4 reviews · 2h to merge
#2053 feat(ui): single-row centered startup logo with ANSI Shadow wordmark
1 round · 2 reviews · 0h to merge
The rest — the latest 5
#2075 fix(web): add v0.27.0 changelog entry and clarify release-data ownership
2 rounds · 6 reviews · 2.4d to merge
#2011 refactor(openai-shim): extract request executor helpers
7 rounds · 13 reviews · 13.0d to merge
#2055 chore(main): release 0.27.0
1 reviews · 2.8d to merge
#2068 fix(minimax): mark MiniMax-M2.7 as text-only input
2 reviews · 9h to merge
#2063 fix(agents): allow subagents from multi-repo parent sessions
3 rounds · 7 reviews · 22h to merge
How this was measured
5% 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 967 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Cursor agent, 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 Gitlawb/openclaude 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 Gitlawb/openclaude — 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