Review economics
openai/codex-plugin-cc
Read from the 28 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.7× the reviews submitted of the rest.
≥67%
Attributed
a floor
17
Attributed PRs
11
Other PRs
28
Read
Attributed — the latest 5
#447 Remove shell expansion for git commands
1 reviews · 1h to merge
#374 feat: add /codex:transfer for Claude Code session handoff
2 reviews · 8.7d to merge
#398 Update plugin version to 1.0.5
0 reviews · 0h to merge
#235 fix: route /codex:rescue through the Agent tool to stop Skill recursion (#234)
4 reviews · 46h to merge
#244 Update plugin version to 1.0.4
0 reviews · 0h to merge
The rest — the latest 5
#99 fix: correct invalid 'xhigh' reasoning effort in README
1 reviews · 7.1d to merge
#35 codex: honor --cwd when reporting session runtime
3 reviews · 8.7d to merge
#126 fix: gracefully handle unsupported thread/name/set on older Codex CLI
2 reviews · 5.0d to merge
#84 codex: scope default cancel selection to the current Claude session
1 reviews · 6.8d to merge
#83 codex: scope implicit resume-last selection to the current Claude session
1 reviews · 6.8d to merge
How this was measured
67% 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; 1 PR came off an agent branch with no commit attribution, so the real share runs higher.
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 openai/codex-plugin-cc 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-plugin-cc — 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