Review economics
smtg-ai/claude-squad
Read from the 75 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.1× the commits after first review of the rest.
≥13%
Attributed
a floor
7
Attributed PRs
68
Other PRs
75
Read
Attributed — the latest 5
#315 fix: record base commit for existing-branch sessions
1 reviews · 41h to merge
#302 chore: remove unused go-git dependency and transitive security advisory
1 round · 3 reviews · 1h to merge
#279 perf: compute full diff only for the selected instance
0 reviews · 34.5d to merge
#285 fix: prevent inconsistent state when Pause() encounters IsDirty error
0 reviews · 28.1d to merge
#253 fix: move expensive operations off UI event loop and fix stale preview pane
6 reviews · 30.0d to merge
The rest — the latest 5
#304 chore: bump Go toolchain to 1.25.8 (GO-2026-4602)
0 reviews · 0h to merge
#294 test: cover orphaned worktree directory cleanup in Setup
0 reviews · 0h to merge
#286 feat: add instance reorder with Shift+J/K
0 reviews · 28.1d to merge
#289 fix: use actual binary name in completion scripts
1 reviews · 14.9d to merge
#264 feat: Allow configuring preset profiles for creating sessions
0 reviews · 0h to merge
How this was measured
13% 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.
“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 smtg-ai/claude-squad 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 smtg-ai/claude-squad — 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