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/app-health)<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/app-health"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/app-health/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/app-health"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/app-health.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 | $0.00016 | $0.00674 |
| Opus 5 | $0.00008 | $0.00337 |
| Sonnet 5 | $0.00003 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
app-health 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 12d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Application Health
Analyze health for: $ARGUMENTS
Step 1: Parse Input
Extract:
- Application name (optional -- analyze all monitored apps if not provided)
- Time window in hours (default: 2)
Step 2: List Monitored Applications
zdx_list_applications()
```text
## Step 3: Get Scores for Each Application
For each application (or the specified one):
```text
zdx_get_application(app_id="<app_id>", since=<hours>)
zdx_get_application_score_trend(app_id="<app_id>", since=<hours>)
```text
## Step 4: Investigate Degraded Applications
For any application with score < 66:
```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
Identify the metric causing degradation.
## Step 5: Check Most Impacted Users
```text
zdx_list_devices(app_id="<app_id>")
```text
## 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: green (score 66-100), yellow (score 34-65), red (score 0-33).
Include:
1. **Application health overview table** (app name, score, status, PFT, DNS, availability, impacted users, bottleneck)
2. **Detailed analysis** for each degraded/poor application explaining what the bottleneck metric indicates
3. **Root cause** per degraded app (DNS resolver, server-side, CDN, ISP, etc.)
4. **Next steps / resolution** prioritized by user impact count:
- Critical apps: immediate investigation, check service health, engage vendor
- Degraded apps: monitor trend, investigate bottleneck metric, check ISP paths
- Healthy apps: no action, note any borderline (66-70) for proactive monitoring
## Step 7: Generate Downloadable Artifacts — MANDATORY
**You MUST create BOTH files. Do NOT skip the HTML page.**
1. **Word document** (`application_health_report_<date>.docx`): Executive summary, application health table, per-app deep dive for degraded apps, root cause analysis, user impact breakdown, prioritized remediation actions.
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.
- 12d ago First seen · 74 lines · 16 tokens per session scan A 225f9e987c67
app-health is a command published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 674 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.