Review economics
anthropics/claude-code-action
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.7× the reviews submitted of the rest.
≥73%
Attributed
a floor
65
Attributed PRs
35
Other PRs
100
Read
Attributed — the latest 5
#1594 Invoke the formatter directly from the format hook
4 reviews · 23h to merge
#1590 Check collaborator permissions for workflow_run events
2 reviews · 18h to merge
#1588 Match downloaded images to their source URLs by asset identifier
2 reviews · 18h to merge
#1589 Pin bun config for MCP server processes
2 reviews · 18h to merge
#1592 Derive trigger timestamps for issues and pull_request events
2 reviews · 3h to merge
The rest — the latest 5
#1407 fix: share one exchanged WIF credential across spawned Claude processes
1 round · 2 reviews · 40.9d to merge
#1490 fix: handle null comment/review author from deleted accounts
1 reviews · 6.3d to merge
#1479 fix(format): filter out thinking_tokens system messages from step summary
1 reviews · 7.9d to merge
#1474 fix: map claude_args model to SDK options
1 reviews · 9.2d to merge
#1492 fix: sanitize {{label}} in branch name templates
1 reviews · 6.2d to merge
How this was measured
73% 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; 6 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 377 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 anthropics/claude-code-action 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-code-action — 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