agentleFS
Sign inStart free
k1p1l0k1p1l0/claude-telegram-supercharged/skills/monitor/SKILL.md

monitor

Skill144 starsChanged 8 months agoApache-2.0View on GitHub

Monitor the Telegram daemon — check if it's alive, view recent logs, find the remote control URL, and diagnose MCP server issues. Use when the user asks "is the daemon running", "check the bot", "show daemon logs", "monitor telegram", or "what's happening with the bot".

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use spec, debug and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 3 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run these checks and present a clean summary:

    line 23
  2. Distinctive:

    If no processes found, report "Daemon is NOT running."

    line 38
  3. Distinctive:

    No args — full status check (default)

    line 104

“Common” is measured: kept by at least 6 in 10 of the 26 edited versions of this file we could read. “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

/telegram:monitor — Telegram Daemon Monitor

Shows the health and status of the Telegram daemon at a glance.

What to check

Run these checks and present a clean summary:

1. Process status

ps aux | grep -E "telegram-supervisor|channels.*telegram|expect.*daemon|caffeinate.*supervisor|bun server.ts" | grep -v grep

Report:

  • Supervisor (bun telegram-supervisor.ts) — PID, uptime
  • Expect wrapper — PID
  • Claude bot (claude --channels ...) — PID, TTY, CPU/memory
  • MCP server (bun server.ts) — PID (if missing, the Telegram plugin didn't start)
  • Caffeinate — running or not

If no processes found, report "Daemon is NOT running."

2. Launchd status

launchctl list | grep claude-telegram

Report loaded/not loaded.

3. Recent supervisor logs

tail -10 ~/.claude/channels/telegram/data/supervisor-stderr.log

Show the last few log entries — look for crashes, restarts, orphan cleanup, or errors.

4. MCP server health

cat ~/.claude/channels/telegram/data/supervisor-stdout.log | strings | grep -i "MCP server" | tail -5

Report any "MCP server needs a..." or "MCP servers fail" messages.

5. Remote control URL

cat ~/.claude/channels/telegram/data/supervisor-stdout.log | strings | grep "session_" | tail -1

Extract and show the https://claude.ai/code/session_XXX URL so the user can watch the daemon live in the browser.

6. Lock file

cat ~/.claude/channels/telegram/data/telegram.lock 2>/dev/null

Show the PID in the lock file and whether that process is still alive.

Output format

Present as a clean status dashboard:

## Telegram Daemon Status

| Component        | Status  | PID   | Details          |
|------------------|---------|-------|------------------|
| Supervisor       | ✅ alive | 12345 | uptime: 2h       |
| Claude bot       | ✅ alive | 12346 | CPU: 0.5%, 300MB |
| MCP server       | ✅ alive | 12347 |                  |
| Caffeinate       | ✅ alive | 12348 |                  |
| Launchd          | ✅ loaded|       |                  |

**Remote control:** https://claude.ai/code/session_XXX
**Lock file:** PID 12346 (alive)

### Recent logs
[last 5 log entries]

Arguments

  • No args — full status check (default)
  • logs — show last 30 lines of supervisor stderr
  • stdout — show last 30 lines of stdout (Claude's output)
  • restart — show the restart command for the user to run
  • url — just show the remote control URL

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