Review economics
virattt/dexter
Read from the 39 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.6× the reviews submitted of the rest.
≥7%
Attributed
a floor
3
Attributed PRs
36
Other PRs
39
Read
Attributed — the latest 3
The rest — the latest 5
#283 fix: formatter key mismatch, timer leak in withTimeout, truncation bug
0 reviews · 0h to merge
#280 fix(screener): remove .default() from currency/limit to fix OpenAI strict schema error
0 reviews · 10.5d to merge
#281 fix(x-search): wait for rate-limit reset and retry instead of aborting
0 reviews · 7.7d to merge
#260 fix: waiting for approval when creating rules
2 reviews · 32h to merge
#262 Fix research rules handling: prevent LLM confusion and unnecessary tool cascades
0 reviews · 8h to merge
How this was measured
7% 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.
Detected: Claude Code, Cursor 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 virattt/dexter 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 virattt/dexter — 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