Review economics
agentscope-ai/QwenPaw
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 1.0× the reviews submitted of the rest.
≥0%
Attributed
a floor
3
Attributed PRs
97
Other PRs
100
Read
Attributed — the latest 3
#6653 fix(ci): fence-aware section extraction in real-behavior-proof (fixes #6626)
1 reviews · 1h to merge
#6570 fix(ci): skip label operations for fork PRs in real-behavior-proof
1 reviews · 6h to merge
#6489 test(drivers): add Driver unit tests + enable fail_under=50 coverage gate
2 reviews · 47h to merge
The rest — the latest 5
#3874 feat(model): refine retry logic
1 reviews · 0h to merge
#6718 feat: unify app market listings
1 reviews · 1h to merge
#6713 fix(router): add audit visibility for sensitive directory exclusion
2 reviews · 1h to merge
#6711 fix(chat): implement loop mode detection and sync with available modes in chat input
1 reviews · 1h to merge
#6503 feat(agent-stats): add current-agent token usage from turn metadata
1 reviews · 8.7d to merge
How this was measured
0% 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 2057 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 agentscope-ai/QwenPaw 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 agentscope-ai/QwenPaw — 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