Review economics
superradcompany/microsandbox
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.1× the reviews submitted of the rest.
≥6%
Attributed
a floor
7
Attributed PRs
93
Other PRs
100
Read
Attributed — the latest 5
#1181 fix(network): propagate guest TCP half-close to proxy tasks
1 reviews · 15.8d to merge
#1245 feat(cli): add msb completion command for shell completion scripts
8 reviews · 2.5d to merge
#1175 docs(sdk/python): document labels, ephemeral, and on_secret_violation create kwargs; fix ViolationPolicy parsing
5 reviews · 15.6d to merge
#1187 feat: add Windows support to the Go SDK (FFI loader + release build)
0 reviews · 16h to merge
#1152 fix(python): restore Python 3.10 compatibility for typed enums
1 reviews · 11.6d to merge
The rest — the latest 5
#1250 feat(sdk): expose active backend context
10 reviews · 5.6d to merge
#1212 fix(agentd): centralize child process reaping
8 reviews · 10.0d to merge
#1272 feat(sdk): support cloud default volume files
2 reviews · 27h to merge
#1266 feat(runtime): coordinate writeback admission
0 reviews · 33h to merge
#1261 feat(rootfs): add flat OCI root disks
7 reviews · 44h to merge
How this was measured
6% 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; 4 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 855 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Claude Code.
“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 superradcompany/microsandbox 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 superradcompany/microsandbox — 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