Review economics
andrewyng/context-hub
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.6× the time to merge of the rest.
≥16%
Attributed
a floor
10
Attributed PRs
90
Other PRs
100
Read
Attributed — the latest 5
#131 Add inverted-index BM25 search
0 reviews · 41h to merge
#119 Update AG2 docs and references
0 reviews · 31h to merge
#63 Add Olakai AI analytics & governance platform docs and skills
0 reviews · 21h to merge
#68 Add Simmer SDK docs — prediction market API for AI agents
1 reviews · 7h to merge
#15 Add LandingAI ADE docs and skill
1 round · 1 reviews · 15h to merge
The rest — the latest 5
#246 Lead registry-unavailable error with actionable advice
0 reviews · 0h to merge
#247 Extract fetch timeouts into named constants
0 reviews · 0h to merge
#248 Add unit tests for cli/src/lib/output.js
0 reviews · 0h to merge
#249 Validate `chub build --output` path upfront
0 reviews · 0h to merge
#259 docs(anthropic): refresh to SDK 0.105.2 / 0.100.1
0 reviews · 42h to merge
How this was measured
16% 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; 1 PR came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 101 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 andrewyng/context-hub 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 andrewyng/context-hub — 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