Review economics
conductor-oss/conductor
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.6× the reviews submitted of the rest.
≥13%
Attributed
a floor
19
Attributed PRs
81
Other PRs
100
Read
Attributed — the latest 5
#1408 fix(test): pin mcp<2 and gate mcp-testkit readiness
1 reviews · 1h to merge
#1381 test(ai): live media-input integration tests per provider, runnable from GitHub Actions
1 reviews · 5.8d to merge
#1369 Fix #1321: reserve an async system task's queue message while it runs
6 reviews · 6.2d to merge
#1404 ci: publish named test-result checks for unit-test, test-harness and e2e
1 reviews · 2h to merge
#1387 Fix mysql boot crashes
2 reviews · 16h to merge
The rest — the latest 5
#1469 fix: 404 on SSE stream open for nonexistent execution IDs
1 reviews · 5h to merge
#1468 fix: self-hosted models — base_url NPE + OPENAI_BASE_URL silently ignored
1 reviews · 10h to merge
#1470 fix: proper 404/400/409 for common agent API client errors
1 reviews · 4h to merge
#1462 fix: resolve persistence concurrency-limit wiring and add /api/health endpoint
1 round · 6 reviews · 17h to merge
#1456 fix(ui-next): show each agent's own strategy in Agent Execution view,…
0 reviews · 28h 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; reads 100 of 622 merged PRs — the rest have not been analyzed yet.
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 conductor-oss/conductor 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 conductor-oss/conductor — 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