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-experience)<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/troubleshoot-experience"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/troubleshoot-experience/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-experience"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/troubleshoot-experience.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 | $0.01319 |
| Opus 5 | $0.00013 | $0.00660 |
| Sonnet 5 | $0.00005 | $0.00264 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
troubleshoot-experience 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot User Experience (ZDX)
Investigate experience for: $ARGUMENTS
Step 1: Parse Input
Extract:
- Username or email
- Application name (optional -- investigate all if not provided)
- Time window in hours (default: 2, max: 168)
Step 2: Find the User's Device
zdx_list_devices(search="<username>")
```text
Note the `device_id`. If multiple devices, ask which one.
## Step 3: Get Device Details
```text
zdx_get_device(device_id="<device_id>")
```text
Check OS, ZCC version, location, department.
## Step 4: Check Application Scores
```text
zdx_list_applications()
zdx_get_application(app_id="<app_id>", since=<hours>)
zdx_get_application_score_trend(app_id="<app_id>", since=<hours>)
```text
Score interpretation:
- **66-100**: Good experience
- **34-65**: Degraded -- investigate further
- **0-33**: Poor -- significant issue
## Step 5: Drill Into Metrics
For degraded/poor scores:
```text
zdx_get_application_metric(app_id="<app_id>", metric_name="dns_time", since=<hours>)
zdx_get_application_metric(app_id="<app_id>", metric_name="availability", since=<hours>)
```text
Check: DNS time, TCP connect, SSL handshake, server response, page fetch time.
## Step 6: Check Alerts
```text
zdx_list_alerts(since=<hours>)
```text
If alerts exist for this user or application, investigate affected devices:
```text
zdx_list_alert_affected_devices(alert_id="<id>")
```text
## Step 7: Deep Trace Analysis
Check for existing deep trace sessions:
```text
zdx_list_device_deep_traces(device_id="<device_id>")
```text
If a deep trace exists, analyze its diagnostics data:
```text
zdx_get_device_deep_trace(device_id="<device_id>", trace_id="<trace_id>")
zdx_list_deeptrace_top_processes(device_id="<device_id>", trace_id="<trace_id>")
zdx_get_deeptrace_webprobe_metrics(device_id="<device_id>", trace_id="<trace_id>")
zdx_get_deeptrace_cloudpath(device_id="<device_id>", trace_id="<trace_id>")
zdx_get_deeptrace_cloudpath_metrics(device_id="<device_id>", trace_id="<trace_id>")
zdx_get_deeptrace_health_metrics(device_id="<device_id>", trace_id="<trace_id>")
zdx_get_deeptrace_events(device_id="<device_id>", trace_id="<trace_id>")
```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 · 132 lines · 25 tokens per session scan A 01e5d3cfe95c
troubleshoot-experience is a command published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 1,319 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
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
ingest-dev
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.
primer
Start with reading the CLAUDE.md file if it exists to get an understanding of the project.
infinite
INFINITE AGENTIC LOOP COMMAND.
next
You just finished a slash command or a batch of work. The user monitors via Farmer on their phone and cannot see CLI text output.