Review economics
max-sixty/worktrunk
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.3× the reviews submitted of the rest.
≥45%
Attributed
a floor
45
Attributed PRs
55
Other PRs
100
Read
Attributed — the latest 5
#3746 fix(output): don't panic when a --format=json consumer closes the pipe
8 reviews · 7h to merge
#3727 fix(shell): don't panic on a multibyte shell name
1 reviews · 0h to merge
#3714 fix(shell): use command rm in wrapper cleanup to bypass rm aliases
2 reviews · 15h to merge
#3719 fix: strip only the executable suffix when naming wt from argv[0]
1 reviews · 8h to merge
#3712 test: fold the mock stub into the wt binary
4 reviews · 10h to merge
The rest — the latest 5
#3747 feat(list): publish a JSON Schema for the schema-2 envelope
3 reviews · 4h to merge
#3734 fix(shell): catch a failing --execute body in the nushell wrapper
2 reviews · 37h to merge
#3732 fix(shell): bypass rm aliases in the nushell wrapper's cleanup
1 reviews · 36h to merge
#3721 Consolidate benchmark recipes and cases
2 reviews · 2.5d to merge
#3731 fix(docs): convert a config-example link whose text holds a bracketed span
2 reviews · 34h to merge
How this was measured
45% 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; reads 100 of 2922 merged PRs — the rest have not been analyzed yet.
Detected: 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
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read max-sixty/worktrunk 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 max-sixty/worktrunk — 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