Tooluck logoTooluck
SKILL.md

live-watch

Agent skill fromhoangsonww/Claude-Code-Agent-Monitor

Polls the Agent Monitor /api/stats endpoint several times over a short window and reports the live deltas in active_sessions, active_agents, events_today, and ws_connections so you can see activity moving in real time. Use when watching the dashboard for live changes rather than a one-time snapshot.

How to install live-watch

install live-watch
# install the Claude-Code-Agent-Monitor pack with the skills CLI
npx skills add hoangsonww/Claude-Code-Agent-Monitor

# or add only this skill to Claude Code: copy the folder

plugins/ccam-dashboard/skills/live-watch/

# into

~/.claude/skills/live-watch/ (all projects)

.claude/skills/live-watch/ (one project)

plugins/ccam-dashboard/skills/live-watch/SKILL.md

MITFull file
1# Live Watch
2
3Watch the dashboard's live counters change over a short window by polling
4`/api/stats` a few times and reporting the deltas.
5
6## Input
7
8The user provides: **$ARGUMENTS**
9
10Interpreted as the watch shape: number of polls and/or interval (e.g. `5x3s` =
115 samples 3 seconds apart). Defaults when empty: **5 samples, ~3 seconds apart**
12(a ~15-second window). A bare number means that many samples at the default
13interval; a bare duration means the default sample count at that interval.
14
15## Data Sources
16
17| Endpoint | Returns |
18|----------|---------|
19| `GET /api/stats` (polled) | `{ total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, ws_connections, agents_by_status, sessions_by_status }` |
20
21## Method
22
23Poll `GET /api/stats` once per interval for the configured number of samples,
24recording the timestamp and the four watched counters each time. Pace the polls
25with a short wait between requests; keep the total window short (seconds, not
26minutes) so it stays interactive.
27
28If the very first poll fails to connect, the dashboard is down — stop and tell
29the user to start it with `npm start` (or `npm run dev`) from the repo root,
30then retry.
31
32## Report Sections
33
34### 1. Watch Window
35State the sample count, interval, and total elapsed window.
36
37### 2. Sample Timeline
38A Markdown table — one row per poll — with columns:
39`#`, `time`, `active_sessions`, `active_agents`, `events_today`, `ws_connections`.
40
41### 3. Deltas
42…

Excerpt shown under the repository's MIT license.

More skills in Claude-Code-Agent-Monitor

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates