zguard-ai-integrations: Instructions file for Claude Code

CLAUDE.md

zguard-ai-integrations CLAUDE.md is an instructions file for Claude Code from zscaler/zguard-ai-integrations. It costs 2,276 tokens per session, scanned A, original, MIT.

A set of project instructions for working on Zscaler's AI Guard integrations, including the repository's purpose, layout, and integration patterns.

In plain words
What is it for?
Understanding and modifying integrations between Zscaler AI Guard and supported services.
Why use it?
It gives an agent the project-specific context needed to make changes that fit the codebase.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is zscaler/zguard-ai-integrations's own configuration. It tells Claude Code how to work on zguard-ai-integrations itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zguard-ai-integrations configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zscaler/zguard-ai-integrations. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zscaler/zguard-ai-integrations/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zscaler/zguard-ai-integrations

Made for: Claude Code.

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 zguard-ai-integrations CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zscaler/zguard-ai-integrations/claude-md/github.svg)](https://agentmods.dev/instructions/zscaler/zguard-ai-integrations/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zscaler/zguard-ai-integrations/claude-md"><img src="https://agentmods.dev/badge/instructions/zscaler/zguard-ai-integrations/claude-md/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 zguard-ai-integrations CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zscaler/zguard-ai-integrations/claude-md"><img src="https://agentmods.dev/badge/instructions/zscaler/zguard-ai-integrations/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,276 This file is loaded in full into every session.
When invoked 2,276 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02276 $0.02276
Opus 5 $0.01138 $0.01138
Sonnet 5 $0.00455 $0.00455
Haiku 4.5 $0.00228 $0.00228

Measured 4d ago against content hash 0e9b8fc4d876, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zguard-ai-integrations CLAUDE.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Exception: AWS.** Those components run inside Lambda and agent runtimes where adding a dependency is a deployment-package cost the user pays, so they call the API with `urllib` and stay stdlib-only. Keep them depende
CLAUDE.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zscaler AI Guard Integrations

Integration repository for connecting Zscaler AI Guard with third-party AI gateways, LLM platforms, and automation tools. Each integration scans prompts and LLM responses via the AI Guard DAS API (resolve-and-execute-policy) to enforce DLP, content safety, PII detection, secrets scanning, and compliance policies.

Repository Purpose

Working code, configuration examples, and documentation for deploying Zscaler AI Guard across the AI ecosystem. Where possible, integrations use zscaler-sdk-python (LegacyZGuardClientHelper) for direct SDK-based API calls rather than raw HTTP.

Structure

├── Anthropic/          # Claude Code hooks (pre/post scan) + Claude Code skill (on-demand /aiguard scanner)
├── OpenAI/             # Codex CLI hooks (user input, bash command/response, MCP request/response, stop)
├── Microsoft/          # Azure API Management policy integration
├── Cursor/             # Cursor IDE hooks (beforeSubmitPrompt, beforeMCPExecution, postToolUse, afterAgentResponse)
├── Cline/              # Cline VS Code hooks (UserPromptSubmit, PreToolUse, PostToolUse, TaskComplete)
├── Windsurf/           # Windsurf Cascade hooks (pre/post prompt, command, MCP, cascade response)
├── AWS/                # Bedrock AgentCore wrapper, Lambda decorator, boto3 SDK hooks, Strands Agents (stdlib only)
├── Google/             # Apigee X (inline proxy + reusable SharedFlow) and Cloud Run provisioning pipelines
├── Kong/               # Kong Gateway — Lua custom plugin & Konnect request callout
├── LiteLLM/            # LiteLLM proxy — Python custom callback (zscaler-sdk-python)
├── NemoGuardrails/     # NVIDIA NeMo Guardrails — custom action + library plugin (zscaler-sdk-python)
├── Portkey/            # Portkey AI Gateway — client-side SDK scanning (zscaler-sdk-python)
├── TrueFoundry/        # TrueFoundry — custom guardrail server via FastAPI (zscaler-sdk-python)
├── github-actions/     # GitHub Actions CI/CD — policy validation pipeline (zscaler-sdk-python)
├── Jenkins/            # Jenkins Declarative Pipeline — policy validation (zscaler-sdk-python)
├── n8n/                # n8n workflow automation — custom TypeScript node

Read the full file on GitHub · 162 lines

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. 4d ago Changed · +9 lines · +387 tokens per session 0e9b8fc4d876
  2. 9d ago First seen · 153 lines · 1,889 tokens per session scan A e5b63df5b76b

Subscribe to this mod's changes

zguard-ai-integrations CLAUDE.md is an instructions file published in the GitHub repository zscaler/zguard-ai-integrations (5 stars, last pushed 7d ago), licensed MIT. It adds 2,276 tokens to every session, about $0.0114 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.