agentleFS
Sign inStart free
david-vrbadavid-vrba/claude-power-skills/skills/monitor-claude/SKILL.md

monitor-claude

Skill4 starsChanged 5 months agoMITView on GitHub

Run a read-only Claude Code process health check — shows active sessions, cmd/node counts, anomalies, and copy-pasteable kill commands.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a read-only health check of all Claude Code sessions on this Windows machine and present the results.

    line 7
  2. Very specific:

    If anomalies or WARN states are present, briefly explain what each means and what the suggested kill commands will do.

    line 30
  3. Very specific:

    If the user asks to kill a specific session, remind them to run the taskkill command in elevated PowerShell or CMD (not Git Bash — the /T …

    line 31
  4. Distinctive:

    If the user asks to kill all sessions, remind them this will terminate all Claude Code windows, including the current one.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Run a read-only health check of all Claude Code sessions on this Windows machine and present the results. The check never kills anything — it only reports and suggests commands.

Run it

Execute the bundled PowerShell script (it lives next to this SKILL.md):

powershell.exe -NoProfile -NonInteractive -File "<this-skill-directory>/monitor-claude.ps1"

Replace <this-skill-directory> with the absolute path to the folder containing this skill (e.g. ~/.claude/skills/monitor-claude).

What it reports

  • System totals — count of claude.exe, cmd.exe, and node.exe, each marked OK or WARN against a threshold, with the expected count for the number of active sessions.
  • Session breakdown — one row per claude.exe session: PID, age, its child cmd/node counts, and status.
  • Anomalies — orphaned sessions (parent process gone), sessions spawning far more node processes than expected, and stale orphaned cmd.exe left running for hours.
  • Snapshot history — last few recorded session starts, if a snapshot log exists (optional; degrades gracefully when absent).
  • Suggested actions — ready-to-paste taskkill commands for any flagged session.

Thresholds live at the top of the script ($WARN_CLAUDE, $WARN_NODE, $WARN_CMD, $WARN_AGE_H, $EXPECTED_PER_SESSION) — tune them to your machine.

After showing the output

Present the script output to the user as-is (it is already formatted). Then:

  • If anomalies or WARN states are present, briefly explain what each means and what the suggested kill commands will do.
  • If the user asks to kill a specific session, remind them to run the taskkill command in elevated PowerShell or CMD (not Git Bash — the /T /F flags get path-mangled there).
  • If the user asks to kill all sessions, remind them this will terminate all Claude Code windows, including the current one.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free