Review economics
wolfpld/tracy
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 3.2× the reviews submitted of the rest.
≥8%
Attributed
a floor
4
Attributed PRs
96
Other PRs
100
Read
Attributed — the latest 4
#1411 feat(mcp): expose sections accessor in eval bindings
0 reviews · 11h to merge
#1336 TracyRocprof: fix on-demand profiling crash and missing context name
0 reviews · 53.0d to merge
#1362 Add save_trace MCP tool for snapshotting live or loaded captures
0 reviews · 2h to merge
#1330 TracyCUDA: show GPU zones for CUDA Graph-launched kernels
1 round · 9 reviews · 9.1d to merge
The rest — the latest 5
#1448 Defer CUDA GpuNewContext for on-demand connections
0 reviews · 2h to merge
#1446 Add formatted zone text/name macros to C API
0 reviews · 8h to merge
#1441 fix(mcp): cap live sessions to avoid OOM
0 reviews · 4h to merge
#1432 fix(mcp): recover from hangs and evict idle files
0 reviews · 11.2d to merge
#1439 fix #1438 null dereference in dwarf
0 reviews · 5h to merge
How this was measured
8% 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 515 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 wolfpld/tracy 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 wolfpld/tracy — 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