Review economics
rtk-ai/rtk
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 1.0× the reviews submitted of the rest.
≥12%
Attributed
a floor
15
Attributed PRs
85
Other PRs
100
Read
Attributed — the latest 5
#3179 fix(hook): detect Copilot CLI shell tool on Windows
1 round · 2 reviews · 3.9d to merge
#3093 fix(copilot): support IDE terminal hooks
2 rounds · 5 reviews · 6.4d to merge
#3211 fix(permissions): stop extra whitespace from evading deny rules
1 reviews · 12h to merge
#3149 fix(hooks): emit permissionDecision allow for simple Copilot CLI rewrites
1 round · 4 reviews · 3.0d to merge
#2791 docs(windows): document native binary hook support
1 reviews · 12h to merge
The rest — the latest 5
#3319 feat(rewrite): rewrite multiline blocks
1 round · 4 reviews · 3.8d to merge
#3212 fix(hooks): stop Copilot from silently deciding permission on unconfigured commands
1 reviews · 7.7d to merge
#3358 chore(master): release 0.44.2
1 reviews · 1h to merge
#3285 Next Release
1 reviews · 3.9d to merge
#3356 fix(security): address followup review comments on private-file hardening
1 reviews · 1h to merge
How this was measured
12% 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 539 merged PRs — the rest have not been analyzed yet.
Detected: 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 rtk-ai/rtk 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 rtk-ai/rtk — 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