Review economics
Wilfred/difftastic
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.2× the time to merge of the rest.
≥1%
Attributed
a floor
4
Attributed PRs
96
Other PRs
100
Read
Attributed — the latest 4
#1022 Use std::io::IsTerminal instead of crossterm's IsTty
0 reviews · 14h to merge
#1023 Update crossbeam-epoch to 0.9.20 for RUSTSEC-2026-0204
0 reviews · 0h to merge
#1019 Track and report position of first parse error
0 reviews · 7.0d to merge
#1011 Update comments to match the code
0 reviews · 4.2d to merge
The rest — the latest 5
#1013 Switch to tree-sitter-java-orchard
0 reviews · 12h to merge
#1012 README: note release date when mentioning v0.50
0 reviews · 3h to merge
#985 Update tikv-jemallocator from 0.6 to 0.7
0 reviews · 7.3d to merge
#988 Add Fish parser support
2 reviews · 17.4d to merge
#977 Fix hunk alignment for inline display
0 reviews · 38.3d to merge
How this was measured
1% 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 159 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 Wilfred/difftastic 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 Wilfred/difftastic — 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