Review economics
justlovemaki/AIClient2API
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.4× the time to merge of the rest.
≥4%
Attributed
a floor
6
Attributed PRs
94
Other PRs
100
Read
Attributed — the latest 5
#679 fix(gemini/antigravity): 修复流式响应产出空流的多个问题
1 reviews · 2h to merge
#447 feat: model-router插件 + 安全增强 + embeddings支持
0 reviews · 0h to merge
#320 feat(kiro): add extended thinking passthrough and structured reasoning outputs
0 reviews · 9.1d to merge
#142 feat: 实现 Anthropic 兼容的 count_tokens API
0 reviews · 19h to merge
#140 fix(kiro): 修复 tool_use 的 input 字段序列化问题
0 reviews · 14h to merge
The rest — the latest 5
#674 fix(antigravity): 为原生Gemini协议客户端补全private tool_use id字段
1 reviews · 45h to merge
#673 feat(kiro): 新增 claude-opus-5 模型支持
0 reviews · 46h to merge
#672 feat(gemini): add support for gemini-3.6-flash models
1 reviews · 3.6d to merge
#670 fix(kiro): 修复 kiro opus 4.7+ 流式响应断流问题
1 reviews · 30h to merge
#641 fix(config): 支持配置请求体大小上限
1 reviews · 2.2d to merge
How this was measured
4% 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; 3 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 103 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, Amp.
“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 justlovemaki/AIClient2API 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 justlovemaki/AIClient2API — 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