Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/pbx-health-check)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/pbx-health-check"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/pbx-health-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/pbx-health-check"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/pbx-health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.00474 |
| Opus 5 | $0.00005 | $0.00237 |
| Sonnet 5 | $0.00002 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
pbx-health-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
PBX Health Check
A quick read-only sweep of PBX liveness: current server time, service status, and a recent-window scan of the structured event log for a failure pattern.
Prerequisites
- A 3CX PBX connected (directly or through Conduit's BYO connector) with a
valid, authenticated MCP session — see the
api-patternsskill
Steps
-
Confirm connectivity
Get the current PBX server time. A successful response confirms the session is live and authenticated before spending calls on anything else.
-
Check service status
List PBX services and their state. Note any service not in a healthy running state.
-
Scan the recent event log
Search/list the structured PBX event log for a recent window (start with the last few hours). Look for a pattern of related failures rather than treating a single isolated entry as significant — PBX event logs are noisy by nature.
-
Synthesize
Report:
- Whether the PBX responded and server time looks correct (not wildly skewed from expected)
- Any service not in a healthy state, named explicitly
- Any recurring event-log pattern in the recent window, with timestamps
Do not report "PBX is healthy" as a single yes/no if any service is degraded or the event log shows a repeating pattern — state each finding explicitly so the reader can judge severity themselves.
Examples
/pbx-health-check
Error Handling
- Server time call fails or times out: The MCP session itself may have
expired — re-authenticate per the
api-patternsskill before assuming the PBX itself is down. - Event log search returns nothing: Confirm the queried time window is correct before reporting "no events" — an empty result for an unexpectedly narrow or misaligned window looks identical to a genuinely quiet PBX.
Related Commands
/queue-status— staffing-specific check, narrower than this general health sweep
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 70 lines · 11 tokens per session scan A 72ef129b1596
pbx-health-check is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 9d ago), licensed Apache-2.0. It adds 11 tokens to every session and 474 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
resolve-codeql
Analyze and resolve CodeQL alerts systematically.
site-audit
Crawl a website and audit for broken links, spelling errors, console errors, and visual issues.
check
Run static analysis on the Java project — detects configured tools (Checkstyle, SpotBugs, PMD) and reports findings.
analyze-issue
A command that runs a systematic problem investigation and searches for the root cause through a five-agent analysis process.
quick-analyze
A command for quickly analysing a problem when you already have a clear error message.
checklist
Generate a custom checklist for the current feature based on user requirements.