Review economics
xbtlin/ai-berkshire
Read from the 14 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.3× the time to merge of the rest.
≥23%
Attributed
a floor
3
Attributed PRs
11
Other PRs
14
Read
Attributed — the latest 3
The rest — the latest 5
#59 Sync investment-team Codex skill
0 reviews · 24.4d to merge
#73 [NEW SKILL] Add income investment skill and update README sections
0 reviews · 2.2d to merge
#44 feat: investment thesis drift detection skill (resubmission of #29)
0 reviews · 5h to merge
#45 docs: add token cost and model selection guidance (resubmission of #32)
0 reviews · 5h to merge
#50 fix: make eastmoney search token configurable via env var
0 reviews · 8h to merge
How this was measured
23% 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; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher.
Detected: OpenAI Codex, 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 xbtlin/ai-berkshire 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 xbtlin/ai-berkshire — 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