Review economics
mindfold-ai/Trellis
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.2× the reviews submitted of the rest.
≥4%
Attributed
a floor
13
Attributed PRs
87
Other PRs
100
Read
Attributed — the latest 5
#472 feat(workflow): per-task selection + layered config/personal default
0 reviews · 3.7d to merge
#468 feat(hooks): path-scoped on-demand spec injection
1 reviews · 4.0d to merge
#463 chore: refresh WeChat 十群 QR (valid until 2026-07-30)
0 reviews · 0h to merge
#439 fix(hooks): adapt SessionStart acknowledgment language
1 reviews · 3.3d to merge
#432 chore: refresh WeChat group QR to 十群
0 reviews · 0h to merge
The rest — the latest 5
#519 fix(cli): validate archived task context paths
4 reviews · 26h to merge
#506 fix(beta): sync v0.6.11 stability fixes
0 reviews · 5.8d to merge
#515 chore: prepare v0.6.12 release
3 reviews · 0h to merge
#513 fix(pi): isolate Trellis context by native session
3 reviews · 2h to merge
#509 docs: refresh WeChat community QR code
0 reviews · 0h to merge
How this was measured
4% 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; 8 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 181 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 mindfold-ai/Trellis 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 mindfold-ai/Trellis — 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