Review economics
headroomlabs-ai/headroom
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.6× the reviews submitted of the rest.
≥10%
Attributed
a floor
13
Attributed PRs
87
Other PRs
100
Read
Attributed — the latest 5
#2736 fix(kompress): let orgs run Kompress on their own inference stack
0 reviews · 1h to merge
#2728 fix(telemetry): anonymous compression stats — no prompts, no data
0 reviews · 7h to merge
#2725 fix(proxy/cost): mark estimated-basis budget records and add an enforcement policy (#2713)
0 reviews · 7h to merge
#2711 fix(proxy/debug): reconcile Kompress warmup state in /debug/warmup
0 reviews · 28h to merge
#2718 feat(compress): accept config.frozen_message_count on /v1/compress
0 reviews · 0h to merge
The rest — the latest 5
#2762 fix(providers): stop a shorter model family shadowing a longer one
0 reviews · 1h to merge
#2761 fix(providers): give every model exactly one tokenizer
0 reviews · 1h to merge
#2759 fix(router): compare token quantities in one unit
0 reviews · 1h to merge
#2757 fix(cost): send litellm the total prompt so --budget stops seeing $0
1 reviews · 1h to merge
#2760 fix(providers): stop pricing modern content blocks at zero
0 reviews · 0h 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; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 1249 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, Cursor 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 headroomlabs-ai/headroom 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 headroomlabs-ai/headroom — 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