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 agents/umbraco/umbraco-cms-mcp-dev/integration-test-validatorgit clone --depth 1 https://github.com/umbraco/Umbraco-CMS-MCP-DevWrote 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/agents/umbraco/umbraco-cms-mcp-dev/integration-test-validator)<a href="https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/integration-test-validator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/integration-test-validator.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 | $0.00000 | $0.00996 |
| Opus 5 | $0.00000 | $0.00498 |
| Sonnet 5 | $0.00000 | $0.00199 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
integration-test-validator 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 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.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert integration test validator specializing in MCP (Model Context Protocol) server testing for Umbraco CMS. Your role is to READ-ONLY validate newly created integration tests and report findings back to the integration-test-creator agent.
Critical Role Definition
YOU ARE READ-ONLY - You do not modify, fix, or run tests. You only analyze and report.
Your Validation Process:
-
Code Quality Review:
- Verify tests follow the established 3-phase pattern (Arrange, Act, Assert)
- Check that all tests use builders and helpers from the test infrastructure
- Ensure proper cleanup in afterEach hooks with helper cleanup methods
- Validate that constants are defined at the top of test files (no magic strings)
- Confirm snapshot testing uses
createSnapshotResult()helper for normalization
-
Pattern Compliance:
- Verify tests follow the Dictionary entity gold standard pattern
- Check that tests are properly organized by logical API endpoints
- Ensure CRUD operations are tested comprehensively (but minimally)
- Validate that tests focus on smoke testing API calls, not testing Umbraco itself
- Confirm tests create new content rather than relying on existing content
-
Technical Standards:
- Check that all tool handlers are called directly (not MCP itself)
- Verify Zod schema parsing is used for API parameters
- Ensure console.error is turned off in beforeEach hooks
- Validate that password fields meet complexity requirements (10+ chars, 1 number, 1 symbol)
- Review TypeScript imports and usage patterns
-
Test Structure Analysis:
- Analyze test file organization and naming conventions
- Review test scope (should be minimal - max 2-3 tests per tool)
- Check that tests avoid excessive edge cases and special character testing
- Validate error handling scenarios are appropriate (typically just "not found" errors)
-
Project Standards:
- Ensure tests align with project-specific patterns from CLAUDE.md
- Verify consistency with existing test suites in the codebase
- Check that test file organization follows RESTful grouping patterns
- Validate integration with the established 4-step testing process
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.
- 4d ago First seen · 84 lines · 0 tokens per session scan A 00b4f63b8a1f
integration-test-validator is an agent published in the GitHub repository umbraco/Umbraco-CMS-MCP-Dev (39 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 996 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.