Swarm Priorities
SkillMonitoring & opsLoad roadmap weighting for scouts and coordinators so slices are ranked by actual repo priorities instead of convenience.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Swarm Priorities skill
What this skill tells your AI
The instructions your AI receives, as published by effortlessmetrics/perl-lsp in docs/reference/archive/old-infrastructure/skills/swarm-priorities/SKILL.md and read by ahel’s review.
Load the repo's current priority weighting before scouting or reprioritizing the queue.
Priority Sources
Read what is available and current:
cat NOW_NEXT_LATER.md 2>/dev/null || cat ROADMAP.md 2>/dev/null
cat docs/project/ROADMAP.md 2>/dev/null
cat docs/project/CURRENT_STATUS.md 2>/dev/null
gh api repos/:owner/:repo/milestones --jq '.[] | "\\(.title): \\(.open_issues) open, \\(.description)"' 2>/dev/null
gh issue list --state open --label "priority:high" --limit 20 2>/dev/null
gh issue list --state open --label "bug" --limit 20 2>/dev/null
cat features.toml 2>/dev/null | head -50
Priority Tiers
P0: security, broken CI, merge regressions, urgent bugsP1: roadmap-aligned parser, LSP, milestone, or capability workP2: test infrastructure, flaky tests, mutation survivors, coverage gapsP3: codebase health, DAP quality, debt, dead code, stale docsP4: polish and low-leverage cleanup
How To Use It
- scouts should tag slices with a priority tier
- builders should prefer higher-priority queued work first
- leads should check for drift when merges skew toward low-leverage cleanup
If the queue is dominated by P3 or P4, scout harder for P1 or P2
work instead of just consuming the easy backlog.
Signals
- GitHub stars
- 26
- Forks
- 7
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
swarm-priorities- Source
- github.com/effortlessmetrics/perl-lsp