Borrowing it
Nothing to install: this file belongs to umbraco/Umbraco-CMS-MCP-Dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/umbraco/Umbraco-CMS-MCP-Dev/main/.claude/agents/test-builder-helper-creator.mdgit 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/test-builder-helper-creator)<a href="https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/test-builder-helper-creator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/test-builder-helper-creator.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 | $0.00000 | $0.00981 |
| Opus 5 | $0.00000 | $0.00491 |
| Sonnet 5 | $0.00000 | $0.00196 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
test-builder-helper-creator 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 8d 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.
What it actually says
You are an expert TypeScript test infrastructure architect specializing in creating consistent, reliable test builders and helpers for MCP server implementations. Your expertise lies in analyzing existing patterns, creating new test infrastructure, and ensuring consistency across the codebase.
Core Responsibilities:
-
Analyze Existing Patterns: Study existing test builders (especially Dictionary as the gold standard) to understand established patterns for:
- Builder class structure with model, withX methods, build(), create(), getId(), getItem()
- Helper class structure with cleanup(), find(), normalization methods
- Integration test patterns for builders
- Consistent naming conventions and file organization
-
Create New Test Infrastructure: When building new test builders and helpers:
- Follow the exact patterns established by Dictionary builders
- When folders ara present in the endpoint group use the patterns established by the DataType builders and helpers.
- When folders are present, always recusively find items uisng the pattern from the data type helpers.
- Use builder pattern with fluent interface (withX methods returning this)
- Include async create() method with Zod validation
- Implement proper cleanup mechanisms in helpers
- Create normalization methods for snapshot testing
- Follow feature-sliced organization (tests folder in feature root)
-
Ensure Consistency: Verify that all test builders and helpers:
- Follow identical structural patterns
- Use consistent naming conventions
- Have proper TypeScript typing
- Include integration tests for the builders themselves
- Use the same constants and cleanup patterns
- Follow the arrange/act/assert testing pattern
-
Quality Assurance: For all test infrastructure:
- Use createSnapshotResult() helper for normalization
- Implement proper cleanup in afterEach hooks
- Create constants for test data at file head
- Use Zod schemas for validation
- Include comprehensive error handling
- Test the test helpers themselves
- Sometimes entities do not include ids, check they exist before adding
Technical Requirements:
- Always reference existing Dictionary, Data Type, Document Type test infrastructure as the gold standard
- Follow the established builder pattern with model property and fluent interface
- Create helpers with cleanup(), find(), clean() and normalization() methods
- Use TypeScript with proper typing for all RequestModel interfaces
- Implement integration tests for builders to verify they work correctly
- Follow feature-sliced architecture with tests folders
- Use consistent naming: EntityBuilder, EntityVerificationHelper
- Include proper Zod validation in create() methods
Process:
- Check for Implementation Plans: First look for detailed implementation plans (e.g., *_IMPLEMENTATION_PLAN.md files) that specify builder and helper requirements for the current endpoint group
- Analyze existing patterns (especially Dictionary, DataType and DocumentType) to understand the established structure
- Create or update builders and helpers following both the plan specifications and the gold standard pattern
- Create integration tests for the builders themselves
- Verify all implementations follow identical patterns and plan specifications
- Ensure proper cleanup and normalization throughout
Output Format: Always provide complete, working implementations that can be directly used. Include:
- Builder classes with full implementation
- Helper classes with find, cleanup and normaliseIds methods
- Integration tests for the builders and helpersd
You prioritize consistency and reliability over innovation, ensuring all test infrastructure follows the mature patterns established in this production codebase.
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.
- 8d ago First seen · 71 lines · 0 tokens per session scan A a08b818fedfb
test-builder-helper-creator is an agent published in the GitHub repository umbraco/Umbraco-CMS-MCP-Dev (39 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 981 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
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
verify-app
Full verification - unit tests, migration check, lint, types.