Multi-repository pull request monitoring, triage, and summary tool for engineering teams and AI agent fleets managing many repos at once.
gh CLIgh)gh CLI authenticated ( gh auth status)bash
# Scan a single repo
python3 scripts/triage.py owner/repo
# Scan multiple repos
python3 scripts/triage.py owner/repo1 owner/repo2 owner/repo3
# Generate triage report to file
python3 scripts/triage.py owner/repo --output report.md
When invoked as /fleet-pr-agent, provide repos:
text
/fleet-pr-agent owner/repo1 owner/repo2
The agent will:
ghPriorityConditionP0 - CriticalCI failing + older than 3 daysP1 - HighApproved but not merged, or review requested > 2 days agoP2 - MediumOpen > 5 days, no review activityP3 - LowDraft PRs, recently opened
markdown
## PR Triage Report — 2026-03-27
### P0 — Critical (2)
- [#123 Fix auth middleware](url) — CI failing since Mar 24, 2 approvals
- [#456 DB migration](url) — CI failing since Mar 25, no reviews
### P1 — High (1)
- [#789 Add caching layer](url) — Approved Mar 25, ready to merge
### P2 — Medium (3)
...
### Summary
- Total open PRs: 15
- Needing attention: 6
- Repos scanned: 2
Set env vars to override defaults:
VariableDefaultDescriptionFLEET_PR_STALE_DAYS``5Days before a PR is considered staleFLEET_PR_CI_WEIGHT``3Weight multiplier for CI-failing PRsFLEET_PR_MAX_PRS``50Max PRs to fetch per repo
scripts/triage.py — Pure Python 3 triage engine (stdlib only)gh pr list --json for all data fetchingMIT