Review economics
anthropics/claude-quickstarts
Read from the 71 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.2× the reviews submitted of the rest.
≥79%
Attributed
a floor
48
Attributed PRs
23
Other PRs
71
Read
Attributed — the latest 5
#448 docs: link the Vercel KB guide from the Chat SDK quickstart README
1 reviews · 0h to merge
#438 Add Managed Agents quickstart with CopilotKit and AG-UI
1 reviews · 26.1d to merge
#441 Add Managed Agents knowledge-wiki cookbook quickstart
3 reviews · 10.0d to merge
#437 Add Managed Agents Chat SDK quickstart
1 reviews · 5.3d to merge
#352 Update computer-use-demo to use text_editor_20250728 exclusively with correct insert_text parameter
1 reviews · 1h to merge
The rest — the latest 5
#411 Add adaptive thinking support to the computer-use demo
2 reviews · 4h to merge
#402 Add computer-use-best-practices quickstart
1 reviews · 0h to merge
#279 [agents] Add server tools
1 reviews · 42h to merge
#242 replace 3.5 with 3.7
1 reviews · 4h to merge
#241 Updated computer use demo for new model/tools
2 reviews · 1h to merge
How this was measured
79% 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 anthropics/claude-quickstarts 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 anthropics/claude-quickstarts — 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