investigate-url

investigate-url is a command for Claude Code from zscaler/zscaler-mcp-server. It costs 20 tokens per session (447 once invoked), scanned A, original, MIT.

A command for finding where a URL or URL category is used in Zscaler Internet Access policy rules. Zscaler Internet Access is a cloud service that controls and inspects web traffic.

In plain words
What is it for?
Use it to look up a URL category and list matching URL filtering, SSL inspection, data-loss prevention, and cloud-firewall rules, including their actions and scope.
Why use it?
It shows which security rules are affected by a URL category and what each rule does. This makes policy changes and their impact easier to review.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the zscaler plugin — 42 skills, 20 commands, 1 MCP server shipped together

Good fit Use it to look up a URL category and list matching URL filtering, SSL inspection, data-loss prevention, and cloud-firewall rules, including their actions and scope.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/zscaler/zscaler-mcp-server/investigate-url
Install

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.

Clone the repo
git clone --depth 1 https://github.com/zscaler/zscaler-mcp-server

Made for: Claude Code.

Or install zscaler, the plugin that ships this one along with the rest of its 42 skills, 20 commands, 1 MCP server.

Wrote 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.

agentmods badge for investigate-url

README.md
[![agentmods](https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/investigate-url/github.svg)](https://agentmods.dev/commands/zscaler/zscaler-mcp-server/investigate-url)
Your own site
<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/investigate-url"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/investigate-url/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.

agentmods 80×15 button for investigate-url

Your own site · 80×15
<a href="https://agentmods.dev/commands/zscaler/zscaler-mcp-server/investigate-url"><img src="https://agentmods.dev/badge/commands/zscaler/zscaler-mcp-server/investigate-url.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 447 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00447
Opus 5 $0.00010 $0.00224
Sonnet 5 $0.00004 $0.00089
Haiku 4.5 $0.00002 $0.00045

Measured 12d ago against content hash 64dd548dafa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

investigate-url 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.

commands/investigate-url.md · 88 lines

What it actually says

Investigate URL Category

Investigate: $ARGUMENTS

Step 1: Classify the URL

If a URL was provided (not a category name):

zia_url_lookup(urls=["<url>"])
```text

Note the category name and ID.

## Step 2: Search Across All Policy Types

Check every policy type for references to this category:

**URL Filtering:**

```text
zia_list_url_filtering_rules()
```text

**SSL Inspection:**

```text
zia_list_ssl_inspection_rules()
```text

**DLP Web Rules:**

```text
zia_list_dlp_web_rules()
```text

**Cloud Firewall:**

```text
zia_list_cloud_firewall_rules()
```text

## Step 3: Map Policy Impact

For each rule that references the category, document:

- Rule name and order
- Action (ALLOW, BLOCK, CAUTION, INSPECT, DO_NOT_INSPECT, etc.)
- Scope (which users/groups/departments)
- Whether the rule is enabled

## Step 4: Present Report

```text
URL Category Policy Impact Report
===================================

URL: <url>
Category: <category_name>

Referenced in X rules across Y policy types:

URL FILTERING (Z rules):
  1. "<rule>" (order N): BLOCK for All Users
  2. "<rule>" (order N): ALLOW for <group> (override)

SSL INSPECTION (Z rules):
  1. "<rule>" (order N): DO_NOT_INSPECT for All Users

DLP (Z rules):
  (none)

CLOUD FIREWALL (Z rules):
  1. "<rule>" (order N): ALLOW ports 80,443

Net effect for a typical user:
  URL Filtering: BLOCKED
  SSL Inspection: NOT INSPECTED
  DLP: Not applicable (bypassed by SSL)
```text
Changes

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.

  1. 12d ago First seen · 88 lines · 20 tokens per session scan A 64dd548dafa9

Subscribe to this mod's changes

investigate-url is a command published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 447 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.