Review economics
RightNow-AI/openfang
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.4× the time to merge of the rest.
≥22%
Attributed
a floor
18
Attributed PRs
82
Other PRs
100
Read
Attributed — the latest 5
#1147 feat(channels): harden channel_id binding — adapter allowlist, strict validation, single source of truth for routing
0 reviews · 11.5d to merge
#1146 fix(kernel): lenient binding parsing — one typo no longer drops the entire bindings table
0 reviews · 11.5d to merge
#1060 fix(security): unify SSRF protection for WASM host calls
1 reviews · 13.9d to merge
#1090 Stamp last_active in streaming agent loop to prevent heartbeat false-positives
0 reviews · 9.3d to merge
#928 feat: add Novita AI as LLM provider
1 reviews · 10.5d to merge
The rest — the latest 5
#1054 feat(discord): smart auto-thread mode (true/false/smart)
1 round · 1 reviews · 28.0d to merge
#1100 channels/telegram: propagate send failures and cache terminal reaction errors
0 reviews · 7.6d to merge
#1095 fix(runtime): pass HOME/TMP/TEMP to stdio MCP servers on all platforms
0 reviews · 8.8d to merge
#1176 fix(chat): support Shift+Enter for multi-line input and proper newline display
0 reviews · 3.8d to merge
#1045 fix: system prompt and identity handling, and config form hydration
0 reviews · 30.0d to merge
How this was measured
22% 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 151 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, GitHub Copilot coding agent, 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 RightNow-AI/openfang 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 RightNow-AI/openfang — 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