Review economics
modelcontextprotocol/registry
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.4× the reviews submitted of the rest.
≥53%
Attributed
a floor
46
Attributed PRs
54
Other PRs
100
Read
Attributed — the latest 5
#1482 build(deps): consolidate open dependabot updates
1 reviews · 0h to merge
#1481 fix(deps): bump golang.org/x/text to v0.39.0 (GO-2026-5970)
1 reviews · 0h to merge
#1443 deploy: update prod to v1.8.0
0 reviews · 0h to merge
#1441 test(api): remove placeholder CORS test superseded by #1436
0 reviews · 0h to merge
#1440 fix(ci): re-validate author association via REST in close-invalid-publish-prs
0 reviews · 0h to merge
The rest — the latest 5
#1480 build(deps): bump google.golang.org/grpc from 1.81.1 to 1.82.1 in /deploy
1 reviews · 0h to merge
#1448 build(deps): bump github.com/pulumi/pulumi/sdk/v3 from 3.251.0 to 3.253.0 in /deploy
1 reviews · 11.4d to merge
#1447 build(deps): bump cloud.google.com/go/kms from 1.31.0 to 1.32.0
1 reviews · 11.4d to merge
#1207 feat: add cargo (crates.io) as a package registry type
1 reviews · 38.5d to merge
#1411 fix(validators): distinguish a missing package from a missing version on PyPI/NPM
1 reviews · 11.6d to merge
How this was measured
53% 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 599 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, Cursor agent.
“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 modelcontextprotocol/registry 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 modelcontextprotocol/registry — 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