Review economics
thedotmack/claude-mem
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.2× the reviews submitted of the rest.
≥51%
Attributed
a floor
51
Attributed PRs
49
Other PRs
100
Read
Attributed — the latest 5
#3468 feat(observations): add "sensitive" type with Telegram notification
1 reviews · 37h to merge
#3391 fix(packaging): stop shipping maintainer directives in CLAUDE.md via marketplace clone (#3381)
2 reviews · 0h to merge
#3390 fix(worker): repair orphaned FK parents before migration rebuilds; adoption after db init (#3378)
3 reviews · 0h to merge
#3389 fix(concepts): normalize concept tags at write time + v49 backfill (#3379)
1 reviews · 0h to merge
#3387 fix(shutdown): tolerate ERR_SERVER_NOT_RUNNING so full teardown completes (#3380)
1 reviews · 0h to merge
The rest — the latest 5
#3487 feat: add custom mode creator skill
1 reviews · 1h to merge
#3462 fix(chroma): prevent concurrent write storms
1 reviews · 1h to merge
#3223 fix: continue Codex transcripts after archival
4 reviews · 10.0d to merge
#3066 fix(codex): install local plugin cache during setup
2 reviews · 26.8d to merge
#2942 fix(observer): disable observer transcript persistence for tool-use queries
3 reviews · 37.5d to merge
How this was measured
51% 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; reads 100 of 502 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 thedotmack/claude-mem 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 thedotmack/claude-mem — 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