Review economics
addyosmani/agent-skills
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.9× the reviews submitted of the rest.
≥10%
Attributed
a floor
17
Attributed PRs
83
Other PRs
100
Read
Attributed — the latest 5
#418 docs: add skill-gap issue form for reporting guidance mismatches
0 reviews · 2.6d to merge
#420 fix(hooks): quote opt-in hook paths in setup docs
1 reviews · 2.0d to merge
#401 docs(skill-anatomy): explain the shared references/ design
2 reviews · 3.8d to merge
#405 fix(validator): reject fenced-block headings and negated triggers
1 reviews · 33h to merge
#323 feat(scripts): enforce naming + description-trigger rules in skill validator
1 reviews · 3.6d to merge
The rest — the latest 5
#442 docs: explain per-skill reference limitation (#361)
1 reviews · 2.4d to merge
#443 test(ci): add command validator regression coverage
1 reviews · 2.4d to merge
#425 docs(skills): extend ecosystem-neutral commands catalog-wide (#404 Phase 2)
2 reviews · 3.7d to merge
#403 docs(performance): add Step 4 (verify with keep-or-revert)
0 reviews · 11.1d to merge
#236 docs: add optional references, examples, and resources directories to skill anatomy
2 reviews · 43.5d to merge
How this was measured
10% 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; 4 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 116 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, 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 addyosmani/agent-skills 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 addyosmani/agent-skills — 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