Review economics
ultraworkers/claw-code
Read from the 100 most recently merged pull requests · · read 4 times
Pull requests with attributed agent authorship took 6.2× the time to merge of the rest.
≥26%
Attributed
a floor
10
Attributed PRs
90
Other PRs
100
Read
Attributed — the latest 5
#3230 docs: add interactive session example to quick start
1 reviews · 37h to merge
#3009 fix: resolve clippy pedantic warnings across workspace
1 round · 1 reviews · 25.3d to merge
#3209 Harden permission enforcement against sandbox bypasses
0 reviews · 4.6d to merge
#2815 fix: resolve EACCES error from incorrect bundled plugins directory
0 reviews · 27.4d to merge
#3010 feat: truncate oversized git diff in system prompt
0 reviews · 15.9d to merge
The rest — the latest 5
#3253 docs: document mlx-lm backend for Apple Silicon and known gotchas
0 reviews · 8.0d to merge
#3180 fix: make cc2 renderer path errors concise
1 reviews · 0h to merge
#3040 fix: recognize OPENAI_API_KEY as valid auth for OpenAI-compatible endpoints
0 reviews · 10.6d to merge
#3227 feat: wizard entry points — /setup command, claw setup subcommand (rebased)
0 reviews · 3.1d to merge
#3232 fix(providers): strip provider prefix from model names for openai_com…
0 reviews · 17h to merge
How this was measured
26% 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 140 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, GitHub Copilot coding agent.
“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 ultraworkers/claw-code 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 ultraworkers/claw-code — 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