Review economics
charmbracelet/crush
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.1× the reviews submitted of the rest.
≥4%
Attributed
a floor
6
Attributed PRs
94
Other PRs
100
Read
Attributed — the latest 5
#3469 fix(config): retry transient Windows rename failures in atomicWriteFi…
1 reviews · 5h to merge
#3328 fix(mcp): clear tools and close the session on MCP error; reap stdio process groups
1 round · 2 reviews · 31h to merge
#3338 feat(ui): clickable ✕ remove button on attachment chips
1 round · 1 reviews · 43h to merge
#3348 feat(mcp): add OAuth support for HTTP MCP servers
1 round · 3 reviews · 4.5d to merge
#3363 perf(tui): keep synchronous workspace probes off the per-message Update path
0 reviews · 26h to merge
The rest — the latest 5
#3513 fix(hyper): render error messages from back-end
0 reviews · 0h to merge
#3481 feat(mcp): don't hold callback port open permanently
1 reviews · 3.6d to merge
#3509 fix: reduce default and suggested mcp timeout
0 reviews · 16h to merge
#3495 fix(server): mcp auth in client-server mode
1 reviews · 14h to merge
#3499 docs(agents): mark crushrc as primary config format over crush.json
0 reviews · 8h to merge
How this was measured
4% 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 1382 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 charmbracelet/crush 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 charmbracelet/crush — 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