Review economics
Fission-AI/OpenSpec
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.9× the review rounds of the rest.
≥56%
Attributed
a floor
57
Attributed PRs
43
Other PRs
100
Read
Attributed — the latest 5
#1490 fix(specs): warn before archiving deletes a note next to a requirement
3 rounds · 9 reviews · 11h to merge
#1483 fix(archive): tell the caller which flag to pass when archive can't ask its questions
1 round · 6 reviews · 9h to merge
#1486 fix(tasks): count indented sub-tasks so a change with unfinished work isn't reported complete
3 rounds · 9 reviews · 6h to merge
#1482 fix(validate): report scenarios a MODIFIED requirement would drop
4 reviews · 8h to merge
#1476 fix(telemetry): send the usage event directly instead of via posthog-node
1 round · 3 reviews · 1h to merge
The rest — the latest 5
#1079 Docs: add deno install instructions
1 round · 6 reviews · 80.9d to merge
#1303 feat(init): add shared agents skills target
5 reviews · 25.8d to merge
#1487 docs: catalog intent-driven community schema
2 reviews · 2h to merge
#1380 chore(release): version packages
1 round · 2 reviews · 11.4d to merge
#1167 feat(adapters): follow the Windsurf rename to Devin Desktop
5 rounds · 14 reviews · 54.5d to merge
How this was measured
56% 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; 7 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 508 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 Fission-AI/OpenSpec 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 Fission-AI/OpenSpec — 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