Review economics
bmad-code-org/BMAD-METHOD
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.5× the reviews submitted of the rest.
≥14%
Attributed
a floor
20
Attributed PRs
80
Other PRs
100
Read
Attributed — the latest 5
#2635 refactor(quick-dev,dev-auto): minimal handoff, drop Code Map nudge
2 reviews · 1h to merge
#2629 feat(quick-dev): nail down implementation handoff to keep dispatch thin
1 reviews · 24h to merge
#2509 chore(bmm): retire bmad-investigate skill and its documentation
1 reviews · 3h to merge
#2579 docs(zh-cn): add missing translations for forge-idea, web-bundles, and dev-auto
1 reviews · 3h to merge
#2281 feat(quick-dev): render templates via stdlib Python at skill entry
2 reviews · 80.4d to merge
The rest — the latest 5
#2683 fix(review): clarify weak test evidence
0 reviews · 0h to merge
#2680 fix(installer): plain-text directory prompt, retire WDS, position on AiDD
1 reviews · 19h to merge
#2679 Remove the adversarial-review explanation page
3 reviews · 5h to merge
#2674 feat: bmad-project-context skill — verified kernel + bundle context system
4 reviews · 4h to merge
#2675 refactor(review): slim adversarial hunter prompt
3 reviews · 2h to merge
How this was measured
14% 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 803 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Cursor agent, 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 bmad-code-org/BMAD-METHOD 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 bmad-code-org/BMAD-METHOD — 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