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.
npx agentmods add commands/zscaler/zscaler-mcp-server/audit-softwaregit 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/audit-software)<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/audit-software"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/audit-software.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00619 |
| Opus 5 | $0.00010 | $0.00309 |
| Sonnet 5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
audit-software 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Software Inventory
Audit software: $ARGUMENTS
Step 1: Parse Input
Extract:
- Software name (optional -- list all if not provided)
- Filter: location, department, or user (optional)
Step 2: List Software Inventory
zdx_list_software()
```text
If a specific software was requested, filter the results.
## Step 3: Drill Into Specific Software
For targeted investigation:
```text
zdx_get_software_details(software_key="<software_name_and_version>")
```text
Check version distribution across devices.
## Step 4: Check Device Details
For devices with outdated or concerning software:
```text
zdx_list_devices(search="<filter>")
zdx_get_device(device_id="<id>")
```text
## Step 5: Present Report
**ALWAYS present data in HTML tables** in the chat response using `<table>`, `<thead>`, `<tbody>`, `<tr>`, `<th>`, `<td>` tags with inline styling. Use color-coded rows: green (current), yellow (one version behind), red (EOL/vulnerable).
Include:
1. **Software inventory table** (software name, version(s), device count, status, risk level)
2. **Compliance summary table** (up to date count/%, one version behind count/%, EOL count/%)
3. **Detailed analysis** explaining the compliance posture, version distribution patterns, and geographic concentration of outdated software
4. **Security assessment** for each EOL/vulnerable entry with risk explanation
5. **Next steps / resolution** prioritized by risk:
- Critical (EOL): immediate upgrade plan, MDM push, maintenance windows
- High (known CVEs): cross-reference with CVE data, prioritize sensitive departments
- Medium (one version behind): schedule automated updates
- Low (current): verify auto-update policies
## Step 6: Generate Downloadable Artifacts — MANDATORY
**You MUST create BOTH files. Do NOT skip the HTML page.**
1. **Word document** (`software_inventory_audit_<date>.docx`): Executive summary, full inventory table, security findings, prioritized recommendations.
2. **Interactive HTML page** (`software_inventory_audit_<date>.html`): Use the complete HTML template from the `zdx-audit-software-inventory` skill. The file must be fully functional with working search bar, sortable columns, filter dropdowns, color-coded rows, summary dashboard, and CSV export button. All CSS and JavaScript inline — no external dependencies. Populate the `<tbody>` with one `<tr>` per software entry from the collected data.
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.
- 5d ago First seen · 71 lines · 19 tokens per session scan A 2077d4a74d96
audit-software is a command published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 12d ago), licensed MIT. It adds 19 tokens to every session and 619 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
epic-decompose
Break epic into concrete, actionable tasks.
issue-sync
Push local updates as GitHub issue comments for transparent audit trail.
create
This command creates the initial project context documentation in .claude/context/ by analyzing the current project state and establishing comprehensive baseline documentation.
epic-start
Launch parallel agents to work on epic tasks in a shared branch.
prd-parse
Convert PRD to technical implementation epic.
prime
This command loads essential context for a new agent session by reading the project context documentation and understanding the codebase structure.