cat:monitor-subagents

Monitor running subagents and track token usage via a shell script.

101|2|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/cowwoc/cat --skill cat-monitor-subagents
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cat:monitor-subagents
Source: https://github.com/cowwoc/cat/tree/main/plugin/skills/monitor-subagents
Command: npx skills add https://github.com/cowwoc/cat --skill cat-monitor-subagents

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Track the status of active subagents, monitor their token consumption, detect context limit approaches, and identify compaction events. Enables the parent agent to make informed decisions about intervention or result collection.

Core Features & Use Cases

  • Monitor the status of all active subagents using the provided monitoring script.
  • Observe token usage and compaction events to detect context pressure and potential stalls.
  • Use during orchestration after spawning subagents or during long-running tasks to decide whether to spawn more or collect results.

Quick Start

Run the monitoring script to get current subagent status and telemetry: /workspace/cat/scripts/monitor-subagents.sh

Frequently Asked Questions about cat:monitor-subagents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track subagent token usage during orchestration?

To track subagent token usage during orchestration, run the monitoring script to output structured JSON containing subagent status, token counts, compaction events, and a summary for decision making.

What is subagent monitoring and when do I need it?

Subagent monitoring tracks active subagents, token consumption, and context limit approaches. You need it when spawning or supervising long-running subagents to decide whether to intervene, spawn more, or collect results.

How do I detect context limits and compaction events for running subagents?

You detect context limits and compaction events by executing the monitoring script, which observes telemetry and outputs structured JSON indicating context pressure and potential stalls for active subagents.

Can I use a shell script to monitor subagent status and token counts?

Yes, you can use the provided shell script at /workspace/cat/scripts/monitor-subagents.sh to monitor subagent status and token counts, outputting structured JSON for orchestration decisions.

How do I decide when to collect results or intervene with active subagents?

You decide when to collect results or intervene by reviewing the structured JSON output from the monitoring script, which provides subagent status, token counts, and compaction events to guide intervention.