Review economics
Egonex-AI/Understand-Anything
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 3.7× the commits after first review of the rest.
≥44%
Attributed
a floor
39
Attributed PRs
61
Other PRs
100
Read
Attributed — the latest 5
#577 fix(dashboard): guard res.ok on the knowledge-graph fetch (fixes misleading "Missing or invalid project metadata")
0 reviews · 6.4d to merge
#490 perf+robustness: eight verified hot-path fixes for large graphs (tour-gen O(n²)→O(n), single-parse, louvain crash, …)
0 reviews · 20.1d to merge
#524 fix(skills): force explicit UTF-8 on locale-default Python file reads
0 reviews · 6.3d to merge
#537 feat(core): add Swift tree-sitter support
0 reviews · 2h to merge
#538 fix: repair Windows skill test failures
0 reviews · 2h to merge
The rest — the latest 5
#609 fix(hooks): emit PostToolUse additional context
0 reviews · 47h to merge
#600 feat(core): broaden .understandignore starter — Swift XCTest/Quick patterns
2 reviews · 8.7d to merge
#606 fix(docs): fix italic formatting in Korean README skill invocation guide
0 reviews · 45h to merge
#598 fix(hooks): read PostToolUse payload from stdin instead of $TOOL_INPUT env var
0 reviews · 4.8d to merge
#597 feat(core): broaden .understandignore starter — Ruby RSpec/Minitest patterns
0 reviews · 21h to merge
How this was measured
44% 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; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 121 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 Egonex-AI/Understand-Anything 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 Egonex-AI/Understand-Anything — 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