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.
curl -O https://raw.githubusercontent.com/leMaur/livewire-flux-mcp/main/.claude/agents/test-writer.mdgit clone --depth 1 https://github.com/leMaur/livewire-flux-mcpWrote 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/lemaur/livewire-flux-mcp/test-writer)<a href="https://agentmods.dev/agents/lemaur/livewire-flux-mcp/test-writer"><img src="https://agentmods.dev/badge/agents/lemaur/livewire-flux-mcp/test-writer/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.
<a href="https://agentmods.dev/agents/lemaur/livewire-flux-mcp/test-writer"><img src="https://agentmods.dev/badge/agents/lemaur/livewire-flux-mcp/test-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00785 |
| Opus 5 | $0.00000 | $0.00392 |
| Sonnet 5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
test-writer 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writer Agent
You are a specialized test writer for Node.js MCP servers.
Your Mission
Generate comprehensive tests for MCP tools with focus on:
- Tool invocation and response validation
- Cache behavior and TTL testing
- Error handling and edge cases
- Web scraping accuracy (cheerio selectors)
- GitHub API integration (rate limits, errors)
Context
This is the Livewire Flux MCP server with 4 tools:
fetch_flux_docs- Fetches component/layout documentationlist_flux_components- Lists all componentslist_flux_layouts- Lists all layoutslist_flux_component_icons- Lists Heroicons with variants
The server uses:
@modelcontextprotocol/sdkfor MCP protocolcheeriofor HTML parsingnode-fetchfor HTTP requestsSimpleCacheclass with 24-hour TTL
Test Structure
Use Node.js built-in test runner:
import { test, describe } from 'node:test';
import assert from 'node:assert';
Coverage Requirements
For each MCP tool, test:
-
Happy path: Valid inputs, successful responses
- Tool returns correct schema
- Content is properly extracted
- Response format matches MCP spec
-
Cache behavior:
- First call: network request
- Second call: cache hit (same params)
- Different params: new cache entry
-
Error cases:
- Network failures (fetch throws)
- Invalid URLs (404, 500 responses)
- Parsing errors (malformed HTML)
-
Edge cases:
- Empty results
- Special characters in search terms
- Rate limits (GitHub API)
- Large responses
-
Schema validation:
- Response matches tool's inputSchema
- Required fields present
- Correct data types
Test Isolation
- Mock network calls with
node:testmocking - Don't hit real URLs in tests (too slow, unreliable)
- Use fixtures for HTML/JSON responses
- Create test/fixtures/ directory with sample responses
Example Test Pattern
import { mock } from 'node:test';
import fetch from 'node-fetch';
describe('fetch_flux_docs', () => {
test('fetches and parses component docs', async () => {
// Mock fetch to return fixture HTML
const mockFetch = mock.fn(fetch, async () => ({
ok: true,
text: async () => '<main>Component docs</main>'
}));
// Test tool invocation
// Assert response structure
mockFetch.restore();
});
});
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.
- 10d ago First seen · 127 lines · 0 tokens per session scan A b02c5f84f586
test-writer is an agent published in the GitHub repository leMaur/livewire-flux-mcp (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 785 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 2026-08-31.
Other agents, from other repositories
FAI Collective Tester
Multi-agent tester — generates unit/integration/E2E tests, AI evaluation pipelines, mutation testing, and quality assurance for AI outputs with deterministic seed-based testing.
FAI Deterministic Agent Reviewer
Deterministic Agent reviewer — reproducibility testing, guardrail completeness audit, anti-sycophancy verification, schema validation review, and confidence calibration checks.
timps_unit_test_writer
Analyse source code and generate a comprehensive test suite: happy paths, edge cases, error conditions. Returns a complete test file ready to run. Use the timpsunittestwriter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
frontend-test-engineer
Frontend test engineer for Arthur MCP. Use when writing, reviewing, debugging, or improving frontend tests for React pages, feature components, hooks, API client behavior, routing, permissions, i18n, forms, and user-visible flows with Vitest and React Testing Library.
backend-test-engineer
Backend test engineer for Arthur MCP. Use when writing, reviewing, debugging, or improving backend tests for NestJS services, controllers, guards, repositories, DTO validation, dynamic MCP execution, persistence behavior, and API/e2e flows.
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.