Review economics
luongnv89/claude-howto
Read from the 64 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.5× the time to merge of the rest.
≥9%
Attributed
a floor
12
Attributed PRs
52
Other PRs
64
Read
Attributed — the latest 5
#109 fix(quiz): correct Q4 extended thinking toggle wording
0 reviews · 16h to merge
#76 fix(lesson-quiz): shuffle answer options and add per-round feedback
0 reviews · 17.8d to merge
#83 fix(extended-thinking): correct fictional /think command to valid ultrathink keyword
0 reviews · 14.2d to merge
#81 docs(skills): improve skill loading process diagram clarity
0 reviews · 8.9d to merge
#84 docs(plugins): clarify marketplace update vs plugin update and add auto-update documentation
0 reviews · 7.9d to merge
The rest — the latest 5
#155 docs: accuracy pass against Claude Code v2.1.220
0 reviews · 6h to merge
#77 Fixed a configuration error in the hooks Chinese guide
0 reviews · 98.6d to merge
#149 Add Vexilo field guide to Additional Resources
0 reviews · 21.1d to merge
#154 docs: sync to Claude Code v2.1.212
0 reviews · 12h to merge
#151 docs: sync to Claude Code v2.1.206
0 reviews · 7h to merge
How this was measured
9% 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.
Detected: 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 luongnv89/claude-howto 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 luongnv89/claude-howto — 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