livewire-flux-mcp: Skill for Claude Code

.claude/skills/test-mcp-tools/SKILL.md

test-mcp-tools is a skill for Claude Code from leMaur/livewire-flux-mcp. It costs 16 tokens per session (536 once invoked), scanned A, original, MIT.

A testing workflow for MCP server tools, which are functions an AI agent can call through a standard interface. It uses Node.js's built-in test runner to check tool behavior and responses.

In plain words
What is it for?
Use it to test Flux documentation, component, layout, and icon tools through standard input and output, including repeated calls, invalid URLs, and network failures.
Why use it?
It helps reveal incorrect response formats, parsing errors, broken error handling, and caching problems before release.

Skill for Claude Code

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

This is leMaur/livewire-flux-mcp's own configuration. It tells Claude Code how to work on livewire-flux-mcp 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 livewire-flux-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to leMaur/livewire-flux-mcp. 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/leMaur/livewire-flux-mcp/main/.claude/skills/test-mcp-tools/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/leMaur/livewire-flux-mcp

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-mcp-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/lemaur/livewire-flux-mcp/test-mcp-tools/github.svg)](https://agentmods.dev/skills/lemaur/livewire-flux-mcp/test-mcp-tools)
Your own site
<a href="https://agentmods.dev/skills/lemaur/livewire-flux-mcp/test-mcp-tools"><img src="https://agentmods.dev/badge/skills/lemaur/livewire-flux-mcp/test-mcp-tools/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 test-mcp-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/lemaur/livewire-flux-mcp/test-mcp-tools"><img src="https://agentmods.dev/badge/skills/lemaur/livewire-flux-mcp/test-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 536 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00016 $0.00536
Opus 5 $0.00008 $0.00268
Sonnet 5 $0.00003 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 11d ago against content hash fd720d5812f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

test-mcp-tools 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 11d 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/skills/test-mcp-tools/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test MCP tools for the Livewire Flux MCP server.

Workflow

  1. Read index.js to understand tool schemas and implementation
  2. Create or update test file in test/ directory
  3. Test each tool:
    • fetch_flux_docs (with/without component, layout, search)
    • list_flux_components
    • list_flux_layouts
    • list_flux_component_icons (with/without variant, search)
  4. Validate:
    • Response schema matches tool definition
    • Cache behavior (repeated calls should be faster)
    • Error handling (invalid URLs, network failures)
    • Content parsing accuracy
  5. Run tests with npm test
  6. Show results and coverage summary

Test Framework

Use Node.js built-in test runner (no external dependencies needed):

import { test, describe } from 'node:test';
import assert from 'node:assert';

Test Categories

Unit Tests (test/unit/)

  • cache.test.js - SimpleCache class (TTL, expiration, key generation)
  • tools.test.js - Tool schema validation and parameter handling

Integration Tests (test/integration/)

  • server.test.js - Full server with stdio transport
  • fetch.test.js - Real HTTP requests (with mocking)

Cache Testing

Test the SimpleCache class:

  • TTL expiration: Verify entries expire after 24 hours
  • Key generation: Ensure unique keys for different params
  • Data persistence: Get/set operations work correctly
  • Cache hits: Repeated calls return cached data

Example Test Structure

describe('fetch_flux_docs tool', () => {
  test('fetches component documentation', async () => {
    // Arrange: mock fetch
    // Act: call tool
    // Assert: validate response
  });

  test('caches responses', async () => {
    // First call: slow (network)
    // Second call: fast (cache hit)
  });

  test('handles errors gracefully', async () => {
    // Mock network failure
    // Verify error message format
  });
});

Success Criteria

  • All 4 tools have test coverage
  • Cache behavior is verified
  • Error cases are tested
  • Tests run with npm test
  • No external test dependencies (use Node.js built-in)

Read the full file on GitHub · 82 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. 11d ago First seen · 82 lines · 16 tokens per session scan A fd720d5812f3

Subscribe to this mod's changes

test-mcp-tools is a skill published in the GitHub repository leMaur/livewire-flux-mcp (9 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 536 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 2026-08-31.