Review economics
cobusgreyling/loop-engineering
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.2× the reviews submitted of the rest.
≥7%
Attributed
a floor
6
Attributed PRs
94
Other PRs
100
Read
Attributed — the latest 5
#452 fix(skills): move mirror note below frontmatter in budget-negotiator
1 reviews · 17h to merge
#451 fix(docs): stop Live Telemetry charts from growing endlessly + pin CDN script versions
1 reviews · 19h to merge
#448 fix(loop-sandbox): use loop-worktree's public lock subpath instead of a dist/ deep import
1 reviews · 44h to merge
#446 fix(loop-sandbox): don't claim a lock was released when it was never acquired
1 reviews · 3.0d to merge
#399 feat(loop-sandbox): add opt-in advisory lock for scheduled-loop safety
1 round · 2 reviews · 28h to merge
The rest — the latest 5
#464 chore: update star-history chart 2026-08-06
0 reviews · 0h to merge
#461 chore(loop): daily triage STATE.md 2026-08-05
0 reviews · 0h to merge
#460 chore: update star-history chart 2026-08-05
0 reviews · 0h to merge
#457 chore(loop): daily triage STATE.md 2026-08-04
0 reviews · 0h to merge
#455 chore: update star-history chart 2026-08-04
0 reviews · 0h 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; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 291 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 cobusgreyling/loop-engineering 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 cobusgreyling/loop-engineering — 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