Swarm Metrics

SkillMonitoring & ops

Aggregate and interpret swarm metrics for status and report surfaces

Use Swarm Metrics in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Swarm Metrics and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Swarm Metrics skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Swarm MetricsStart free

What this skill tells your AI

The instructions your AI receives, as published by effortlessmetrics/perl-lsp in .claude/skills/swarm-metrics/SKILL.md and read by Ahel’s review.

Use this skill when you need to inspect .ops-perl-lsp/swarm-metrics.jsonl, summarize recent swarm activity, or write status/report commentary that is backed by the metrics file.

Canonical Analyzer

Prefer the repo-native analyzer:

cargo xtask swarm-summary .ops-perl-lsp --since 24h --limit 10
cargo xtask swarm-summary .ops-perl-lsp --since 7d --limit 20
cargo xtask swarm-summary .ops-perl-lsp --since 24h --limit 10 --format json

Reporting Patterns

  • Use --since 24h for /swarm-status style check-ins.
  • Use --since 7d for /swarm-report and weekly rollups.
  • Use --format json when another tool needs machine-readable summary data.
  • Call out the top event types, agent types, sessions, and worktree hotspots.
  • Prefer the analyzer output over raw tail/jq snippets so the same grouping rules are used everywhere.

Notes

  • The metrics file is append-only and may contain mixed event shapes.
  • Missing fields should be treated as (none) rather than dropped.
  • If the analyzer reports zero matching entries, mention the window and the file path so the operator can distinguish "no data" from "wrong directory".

Signals

GitHub stars
26
Forks
7
Last commit
Sep 2026
Advanced
Item type
skill
Key
swarm-metrics
Source
github.com/effortlessmetrics/perl-lsp