Review economics
mengxi-ream/read-frog
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.0× the reviews submitted of the rest.
≥46%
Attributed
a floor
30
Attributed PRs
70
Other PRs
100
Read
Attributed — the latest 5
#2042 fix(translation-hub): swap languages while the source is auto-detected
0 reviews · 0h to merge
#2041 fix(options): keep the sidebar and search reachable in a narrow window
1 reviews · 2h to merge
#2040 fix(translate): keep X Chat message timestamps out of translations
0 reviews · 0h to merge
#2039 feat: translation language settings
0 reviews · 0h to merge
#2014 fix(translate): translate SillyTavern <code> narration via site-rule tag-set overrides (#1951)
1 round · 5 reviews · 2.2d to merge
The rest — the latest 5
#2037 fix(translate): translate Ubiquiti Community release posts and comments
1 reviews · 0h to merge
#2036 feat(translation): add precision rewrite as an optional built-in prompt
1 reviews · 1h to merge
#2035 docs: update retired Claude model ids in add-provider command
0 reviews · 5h to merge
#2032 fix(config): disable AI smart context by default
0 reviews · 0h to merge
#2025 chore(release): version packages
0 reviews · 17h to merge
How this was measured
46% 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; 30 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 1068 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, Cursor 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 mengxi-ream/read-frog 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 mengxi-ream/read-frog — 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