Review economics
openai/codex
Read from the 100 most recently merged pull requests ·
Not enough merged pull requests on both sides yet to compare how they land in review.
≥96%
Attributed
a floor
96
Attributed PRs
4
Other PRs
100
Read
Attributed — the latest 5
#37144 Preserve discovery paths for symlinked skills
0 reviews · 0h to merge
#37134 Report prompt image resizing to the model
0 reviews · 0h to merge
#37132 Enforce managed authentication requirements locally
0 reviews · 0h to merge
#37129 Make Windows path URI comparisons ASCII-case-insensitive
0 reviews · 0h to merge
#37128 Centralize tool approval handling in `Session`
0 reviews · 0h to merge
The rest — the latest 4
#36983 Preserve ChatGPT auth for trusted staging MCP servers
0 reviews · 0h to merge
#36979 Add Fence auditing to the blob size workflow
0 reviews · 0h to merge
#36945 Grant the blob size policy job read access to contents
0 reviews · 0h to merge
#36924 Reject implicitly discovered bare Git repositories
0 reviews · 0h to merge
How this was measured
96% 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; reads 100 of 9049 merged PRs — the rest have not been analyzed yet.
Detected: 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 openai/codex 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 openai/codex — 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