Review economics
browser-use/browser-use
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥2%
Attributed
a floor
8
Attributed PRs
92
Other PRs
100
Read
Attributed — the latest 5
#5225 Fix DOMTreeSerializer leaking paint-order-occluded text to the LLM
1 reviews · 19.3d to merge
#5231 Fix Mouse.scroll() silently redirecting an explicit x=0/y=0 to viewport center
1 reviews · 18.9d to merge
#5233 Fix ChatAnthropicBedrock.ainvoke() IndexError on an empty response.content list
1 reviews · 18.6d to merge
#5175 fix(dom): clamp final chunk char_end to len(content) for trailing newline
2 reviews · 25.1d to merge
#5274 Fix clear-to-empty on React controlled inputs (native value setter)
1 reviews · 4h to merge
The rest — the latest 5
#5379 fix: include exception details in coordinate click and add missing error logs
2 reviews · 2h to merge
#5285 fix(async): avoid re-raising task callback errors
1 reviews · 10.2d to merge
#5105 fix(agent): close PIL images after GIF creation to prevent resource leak
1 reviews · 32.7d to merge
#5235 fix(mcp): surface CallToolResult.isError as a failed ActionResult
1 reviews · 18.4d to merge
#5246 fix(mcp): mark read-only MCP tools with readOnlyHint annotations
2 reviews · 16.9d to merge
How this was measured
2% 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; 7 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 1882 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 browser-use/browser-use 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 browser-use/browser-use — 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