test_helper

test_helper is a command for Claude Code from caidish/instrMCP. It costs 9 tokens per session (1,138 once invoked), scanned A, original, MIT.

An interactive helper for testing the tools and data resources exposed by the InstrMCP server.

In plain words
What is it for?
It helps test core server functions, notebook operations, measurement tools, database tools, and resource templates by category.
Why use it?
It gives a structured way to check whether the server’s tools work and shows their results for review.

Command for Claude Code

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.

agentmods
npx agentmods add commands/caidish/instrmcp/test_helper
Clone the repo
git clone --depth 1 https://github.com/caidish/instrMCP

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 test_helper

README.md
[![agentmods](https://agentmods.dev/badge/commands/caidish/instrmcp/test_helper.svg)](https://agentmods.dev/commands/caidish/instrmcp/test_helper)
Your own site
<a href="https://agentmods.dev/commands/caidish/instrmcp/test_helper"><img src="https://agentmods.dev/badge/commands/caidish/instrmcp/test_helper.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00009 $0.01138
Opus 5 $0.00005 $0.00569
Sonnet 5 $0.00002 $0.00228
Haiku 4.5 $0.00001 $0.00114

Measured 5d ago against content hash 173305b341f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test_helper 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.

.claude/commands/test_helper.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Interactive Test Helper

You are helping the user interactively test the InstrMCP server. You are presumably already connected to a user-launched instrmcp session, and in unsafe mode.

Context

  • Server metadata: @instrmcp/config/metadata_baseline.yaml
  • The user is running the MCP server in unsafe mode with consent dialogs
  • Test notebook: "TestNotebook.ipynb" is open in JupyterLab
  • You need to interact with instrmcp, and print the tool result to screen for the user to be able to verify it.

Test Categories

The user can specify a category to test: $ARGUMENTS

Available categories:

  • all - Test everything systematically
  • core - Test mcp_list_resources, mcp_get_resource
  • notebook - Test notebook_* tools (safe and unsafe)
  • qcodes - Test qcodes_* tools
  • measureit - Test measureit_* tools
  • database - Test database_* tools
  • resources - Test all resource templates

If no category specified, test all.

Testing Workflow

For each tool/resource category, follow this workflow:

1. Description Review

First, read the tool description from metadata_baseline.yaml and ask:

Use AskUserQuestion to ask:
"For [tool_name]: Is this description clear and accurate?"
Options:
- "Yes, clear and accurate"
- "Needs improvement" (ask for details)
- "Skip this tool"

2. Tool Execution Test

If the description is approved, attempt to call the tool with sensible defaults:

  • For read-only tools: Execute directly and report results
  • For unsafe tools: Warn the user that consent dialog will appear, then execute
  • For tools requiring specific state (e.g., running sweep): Ask user to set up the state first
  • For testing some of the tools, you may need to ask the user to run some code, or you use MCP to run code.

3. Result Verification

After execution, ask the user to verify:

Use AskUserQuestion to ask:
"Did [tool_name] behave as expected?"
Options:
- "Yes, working correctly"
- "Bug found" (document the issue)
- "Unexpected behavior" (document details)

Read the full file on GitHub · 140 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. 5d ago First seen · 140 lines · 9 tokens per session scan A 173305b341f8

Subscribe to this mod's changes

test_helper is a command published in the GitHub repository caidish/instrMCP (35 stars, last pushed 24d ago), licensed MIT. It adds 9 tokens to every session and 1,138 once invoked, about $0.0000 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.