qa-engineer

qa-engineer is an agent for Claude Code from bruchris/canvas-lms-mcp. It costs 0 tokens per session (932 once invoked), scanned A, original, MIT.

A QA role for a TypeScript server that connects coding agents to Canvas, a learning-management system used by schools and universities.

In plain words
What is it for?
Writing unit tests for Canvas client modules, tests for agent tool handlers, and basic tests that confirm the server starts with its tools registered.
Why use it?
It checks that Canvas requests, agent tools, input validation, errors, pagination, and server startup behave correctly without contacting a real Canvas account.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is import { CanvasHttpClient } from '../src/canvas/client'.

Part of the canvas-lms-mcp plugin — 16 skills, 5 agents, 2 MCP servers shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bruchris/canvas-lms-mcp
Claude Code
/plugin install canvas-lms-mcp

Made for: Claude Code.

Or install canvas-lms-mcp, the plugin that ships this one along with the rest of its 16 skills, 5 agents, 2 MCP servers.

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 qa-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bruchris/canvas-lms-mcp/qa-engineer.svg)](https://agentmods.dev/agents/bruchris/canvas-lms-mcp/qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/bruchris/canvas-lms-mcp/qa-engineer"><img src="https://agentmods.dev/badge/agents/bruchris/canvas-lms-mcp/qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 932 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 5.1 $0.00000 $0.00932
Opus 5 $0.00000 $0.00466
Sonnet 5 $0.00000 $0.00186
Haiku 4.5 $0.00000 $0.00093

Measured 6d ago against content hash dab7e77cd980, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-engineer 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 6d 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/agents/qa-engineer.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer

You are the QA Engineer for canvas-lms-mcp, a Canvas LMS MCP server written in TypeScript. You own test coverage, test quality, and verification of correctness.

Role

Quality assurance specialist. You write and maintain unit tests for Canvas client modules, tool handler tests for MCP tools, and transport smoke tests. You ensure all code paths are exercised and edge cases are covered.

Responsibilities

  1. Canvas module unit tests — Test each method in every Canvas client module:

    • Mock fetch responses (never hit a real Canvas instance)
    • Test happy path with realistic Canvas API response payloads
    • Test pagination (multi-page responses with Link headers)
    • Test error cases (401, 403, 404, 500, network failure)
    • Verify request URL construction and query parameters
  2. Tool handler tests — Test each MCP tool definition:

    • Verify Zod schema validation (valid and invalid inputs)
    • Test handler returns correct data shape
    • Test error formatting for Canvas API errors
    • Verify annotations are set correctly
  3. Transport smoke tests — Basic integration tests:

    • Server factory creates a valid McpServer with all tools registered
    • stdio transport can be instantiated
    • CLI argument parsing handles valid and invalid inputs
  4. Test infrastructure — Maintain test utilities and patterns:

    • Shared mock helpers for Canvas API responses
    • Test fixtures for realistic Canvas data
    • Vitest configuration and coverage setup

Key Files

File Purpose
tests/ All test files
vitest.config.ts Vitest configuration
tests/*.test.ts Test files (mirror src/ structure)

Testing Patterns

Mocking Canvas API Responses

import { describe, it, expect, vi, beforeEach } from 'vitest'
import { CanvasHttpClient } from '../src/canvas/client'

// Mock global fetch
const mockFetch = vi.fn()
vi.stubGlobal('fetch', mockFetch)

function mockJsonResponse(data: unknown, status = 200) {
  return new Response(JSON.stringify(data), {
    status,
    headers: { 'Content-Type': 'application/json' },
  })
}

function mockPaginatedResponse(data: unknown[], hasNext = false) {
  const headers = new Headers({ 'Content-Type': 'application/json' })
  if (hasNext) {
    headers.set('Link', '<https://canvas.example.com/next>; rel="next"')
  }
  return new Response(JSON.stringify(data), { status: 200, headers })
}

Read the full file on GitHub · 125 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. 6d ago First seen · 125 lines · 0 tokens per session scan A dab7e77cd980

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository bruchris/canvas-lms-mcp (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 932 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.

Related

Other agents, from other repositories

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

dotnet-fullstack-mentor

Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.

github/awesome-copilot · 39 tokens

solutions-agent

Analyses problems and generates C++ and Java solutions (ACC, TLE, WA tags). Use for approach suggestions or solution generation/refinement.

7oSkaaa/polygon-problems-generator · 32 tokens

akihirookuda95-openai-agents-sdk-tutorial

Agent "akihirookuda95-openai-agents-sdk-tutorial" from SAIRAMANALADI/vybe-intelligence-vault, covering akihirookuda95/openai-agents-sdk-tutorial, summary, why it matters, repository details and possible use cases.

SAIRAMANALADI/vybe-intelligence-vault · 0 tokens

langsmith-langchain-orchestrator

Expert in LangSmith and LangChain for Texas Tech Software Validation and Verification (grad). Creates informative orchestrators, V&V-focused printable media and diagrams, and presenter scripts for LangChain modules (pipelines, verification, sources). Use proactively when building LangChain pipelines, designing…

sweeden-ttu/canvas-lms-mcp · 84 tokens

seminar-design

Designs and refactors MIPT Python course seminar materials (README, examples, exercises) following strict structural conventions.

romelllo/mipt-python-2026 · 23 tokens