Review economics
HKUDS/OpenHarness
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.6× the commits after first review of the rest.
≥20%
Attributed
a floor
18
Attributed PRs
82
Other PRs
100
Read
Attributed — the latest 5
#279 feat(hooks): add priority ordering for lifecycle hooksdering for lifecycle hooks
0 reviews · 0h to merge
#270 fix(feishu): add domain config to support Lark international (larksuite.com)
0 reviews · 3.0d to merge
#260 feat(tui): preview diffs before edit and write approval
1 reviews · 3.3d to merge
#219 fix: catch re.error in _python_grep_files to prevent crash on invalid regex
0 reviews · 34h to merge
#205 fix(tools): prevent subprocess stderr pipe deadlocks in glob, grep, bash, and session_runner
1 reviews · 12h to merge
The rest — the latest 5
#285 [codex] support persisted web resolution modes
0 reviews · 15h to merge
#287 fix(ohmo): send final image paths as media
0 reviews · 13h to merge
#288 fix(ohmo): tee gateway run logs to file
0 reviews · 0h to merge
#281 [security] fix(ohmo): gate gateway-scoped /provider and /model commands
0 reviews · 7.2d to merge
#276 [security] fix(ohmo): keep session restore local-only remotely
0 reviews · 2.1d to merge
How this was measured
20% 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; 8 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 109 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Claude Code, 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 HKUDS/OpenHarness 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 HKUDS/OpenHarness — 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