Review economics
davila7/claude-code-templates
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.4× the reviews submitted of the rest.
≥63%
Attributed
a floor
55
Attributed PRs
45
Other PRs
100
Read
Attributed — the latest 5
#781 improve: fix droid agent to use Claude Code conventions instead of GitHub Copilot
2 reviews · 1h to merge
#779 improve: enhance llm-architect agent with 2026 tooling and techniques
4 reviews · 1h to merge
#773 Add avoid-ai-writing skill (productivity)
4 reviews · 13h to merge
#775 improve: enhance ai-engineer
3 reviews · 1h to merge
#772 improve: enhance ai-ethics-advisor agent (fix frontmatter, add current standards)
2 reviews · 1h to merge
The rest — the latest 5
#771 Update retired model ids in settings components and docs
2 reviews · 42h to merge
#756 Add doc-chaser-lite skill (productivity)
3 reviews · 6.6d to merge
#751 Remove flatten-mcp MCP (project retired)
1 reviews · 14h to merge
#739 feat(components): DoorDash CLI suite — 5 skills, 4 hooks, 5 commands
1 reviews · 0h to merge
#738 feat(dashboard): hide Loops from navigation menu
0 reviews · 0h to merge
How this was measured
63% 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 317 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex.
“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 davila7/claude-code-templates 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 davila7/claude-code-templates — 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