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/investigate-alerts)<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/investigate-alerts"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/investigate-alerts/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/investigate-alerts"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/investigate-alerts.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 | $0.00023 | $0.00760 |
| Opus 5 | $0.00012 | $0.00380 |
| Sonnet 5 | $0.00005 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
investigate-alerts 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate ZDX Alerts
Investigate alerts: $ARGUMENTS
Step 1: Parse Input
Extract:
- Time window in hours (default: 24)
- Severity filter (default: all)
Step 2: List Active Alerts
zdx_list_alerts(since=<hours>)
```text
## Step 3: For Each Alert, Investigate
For each active or recent alert:
```text
zdx_get_alert(alert_id="<id>")
```text
Note: alert type, severity, affected application, start time, end time (if resolved).
## Step 4: Check Affected Devices
```text
zdx_list_alert_affected_devices(alert_id="<id>")
```text
Determine scope: one user, one office, one ISP, or organization-wide.
## Step 5: Correlate with Application Metrics
For the affected application:
```text
zdx_get_application_score_trend(app_id="<app_id>", since=<hours>)
zdx_get_application_metric(app_id="<app_id>", metric_name="dns_time", since=<hours>)
```text
Check if metrics degraded around the alert start time.
## Step 6: Present Report
**ALWAYS present data in HTML tables** using `<table>`, `<thead>`, `<tbody>`, `<tr>`, `<th>`, `<td>` tags with inline styling. Use color-coded rows: red (high priority), yellow (medium), green (low/resolved).
Include:
1. **Active alerts summary table** (priority, alert name, application, duration, affected devices, locations, bottleneck metric)
2. **Metric correlation table** per alert (PFT, DNS, availability, root cause indicator)
3. **Detailed analysis** explaining alert severity, scope (isolated vs widespread), and correlation between alerts
4. **Historical pattern analysis** -- is this recurring? What time patterns exist?
5. **Next steps / resolution** per alert:
- High priority: immediate actions (check service health, ISP paths, engage vendor)
- Medium priority: investigate specific bottleneck (DNS, network path)
- Low priority: monitor, check for transient causes (deployments, maintenance)
- Proactive: start a deep trace (`zdx_start_deeptrace`) for recurring alerts to capture detailed network path evidence, then analyze with `zdx_get_deeptrace_webprobe_metrics`, `zdx_get_deeptrace_cloudpath`, and `zdx_get_deeptrace_events`
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 · 79 lines · 23 tokens per session scan A f7396c1fbf2c
investigate-alerts is a command published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 760 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.
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.
checklist
Generate a custom checklist for the current feature based on user requirements.