Review economics
Fission-AI/OpenSpec
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.3× the review rounds of the rest.
≥46%
Attributed
a floor
47
Attributed PRs
53
Other PRs
100
Read
Attributed — the latest 5
#1517 feat(copilot): make cloud coding-agent files opt-in
1 round · 5 reviews · 1h to merge
#1516 feat(tools): add Atlassian Rovo Dev CLI as a first-class tool
1 round · 4 reviews · 1h to merge
#1515 refactor(templates): share one apply instruction body across skill and command
2 reviews · 1h to merge
#1514 fix(templates): restore intentional apply skill/command separation
1 round · 3 reviews · 1h to merge
#1484 feat(archive): let a change retire a capability it empties
9 rounds · 24 reviews · 6.1d to merge
The rest — the latest 5
#1491 docs(stores): add multi-repo implementation flow
1 round · 4 reviews · 3.4d to merge
#1513 fix(telemetry): honor telemetry.enabled in global config
4 reviews · 7h to merge
#1153 fix(templates): deduplicate apply skill and command instructions
2 rounds · 6 reviews · 64.2d to merge
#1511 fix(codex): install skills in canonical agents directory
1 round · 20 reviews · 3h to merge
#1214 feat: add MiniMax Code skills support
1 round · 8 reviews · 50.6d to merge
How this was measured
46% 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; 16 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 533 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