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/zscaler/zscaler-mcp-serverWrote 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/zscaler/zscaler-mcp-server/troubleshoot-user)<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/troubleshoot-user"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/troubleshoot-user/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/zscaler/zscaler-mcp-server/troubleshoot-user"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/troubleshoot-user.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 | $0.00025 | $0.00870 |
| Opus 5 | $0.00013 | $0.00435 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
troubleshoot-user 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot User Connectivity
Perform end-to-end troubleshooting for user: $ARGUMENTS
Follow this systematic workflow:
Step 1: Parse Input
Extract from the arguments:
- User identifier (name or email)
- Application or URL (if provided)
- Symptom (cannot connect, slow, intermittent, access denied)
If any required information is missing, ask the administrator.
Step 2: ZCC Client Status
zcc_list_devices(search="<user>")
```text
Check enrollment status, ZCC version, last seen time. Verify traffic is being forwarded:
```text
zcc_list_forwarding_profiles()
zcc_list_trusted_networks()
```text
## Step 3: ZDX Digital Experience
```text
zdx_list_devices(search="<user>")
zdx_get_device(device_id="<id>")
zdx_list_applications()
zdx_get_application_score_trend(app_id="<id>")
zdx_list_alerts()
```text
Evaluate: Score > 80 = good, 50-80 = degraded, < 50 = poor. Check DNS time, TCP connect time, server response time.
### Step 3a: Deep Trace Diagnostics (if score is degraded/poor)
Check for existing deep trace sessions and analyze or start a new one:
```text
zdx_list_device_deep_traces(device_id="<id>")
```text
If a trace exists, analyze the diagnostics data:
```text
zdx_get_device_deep_trace(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_webprobe_metrics(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_cloudpath(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_cloudpath_metrics(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_health_metrics(device_id="<id>", trace_id="<trace_id>")
zdx_list_deeptrace_top_processes(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_events(device_id="<id>", trace_id="<trace_id>")
```text
If no trace exists and the symptom suggests network issues, discover probe IDs and start one (requires write tools):
```text
zdx_get_web_probes(device_id="<id>", app_id="<app_id>")
zdx_list_cloudpath_probes(device_id="<id>", app_id="<app_id>")
zdx_start_deeptrace(device_id="<id>", session_name="Cross-Product-<user>-<date>", app_id=<app_id>, web_probe_id=<id>, cloudpath_probe_id=<id>, session_length_minutes=15, probe_device=True)
```text
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.
- 10d ago First seen · 110 lines · 25 tokens per session scan A 0708fbf7ad9b
troubleshoot-user is a command published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 870 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
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
run-agents-for-issues
address all found gaps and issues. start one agent per the problem.
preflight
Diagnostique l'environnement Cortex et guide la réparation (DB, extensions, modèles).
trace-claude-code
Control Opik tracing for your Claude Code sessions.
inventory
Codebase inventory skill — scans the repo for a named pattern (inline SQL, fetch calls, feature flags, debug leftovers, deprecated APIs, etc.) and emits a structured Markdown inventory cross-referenced with framework metadata (routes, handlers). Language-agnostic and pack-driven — the engine matches whatever a YAML…
diagnose
Diagnose why ig-dl isn't working — checks auth, browsers, and backend availability.