Review economics
abhigyanpatwari/GitNexus
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.1× the reviews submitted of the rest.
≥43%
Attributed
a floor
32
Attributed PRs
68
Other PRs
100
Read
Attributed — the latest 5
#2810 fix: type an inference-typed class field so it can act as a call receiver (#2807)
3 reviews · 28h to merge
#2806 perf(mcp): cut the analyze-only language-provider closure out of MCP server startup (#2802)
1 reviews · 9h to merge
#2808 fix(analyze): replace the hand-incremented schema version with a derived DDL fingerprint (#2798)
0 reviews · 2h to merge
#2795 fix(embeddings): retry unparseable 200 responses and survive partial embedding failures (#2790)
10 reviews · 11h to merge
#2796 fix(mcp): make impact/context reproducible — deterministic ordering on every capped query (#2787)
1 reviews · 6h to merge
The rest — the latest 5
#2827 chore(deps)(deps): bump @hono/node-server from 1.19.14 to 2.1.0 in /gitnexus
0 reviews · 1h to merge
#2825 chore(deps): bump aiohttp from 3.14.1 to 3.14.3 in /eval in the uv group across 1 directory
0 reviews · 1h to merge
#2821 chore(deps)(deps): bump fast-uri from 3.1.4 to 3.1.5 in /gitnexus
0 reviews · 2h to merge
#2815 chore(deps)(deps): bump @modelcontextprotocol/sdk from 1.29.0 to 1.30.0 in /gitnexus
0 reviews · 12h to merge
#2823 chore(deps)(deps): bump the npm_and_yarn group across 1 directory with 2 updates
0 reviews · 1h to merge
How this was measured
43% 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; 5 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 1182 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Cursor agent, OpenAI Codex, GitHub Copilot coding 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 abhigyanpatwari/GitNexus 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 abhigyanpatwari/GitNexus — 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