simple-mcp-runner: Agent for Claude Code

.claude/agents/golang-test-engineer.md

golang-test-engineer is an agent for Claude Code from mjmorales/simple-mcp-runner. It costs 372 tokens per session (1,100 once invoked), scanned A, original, MIT.

A specialist for designing, writing, and reviewing tests in Go, the programming language from Google. It covers unit tests, integration tests, benchmarks, test setup, mocks, and coverage.

In plain words
What is it for?
Use it to create or improve Go test suites, choose between realistic fakes and mocks, test service integrations, measure coverage, detect race conditions, and write benchmarks.
Why use it?
It helps you build tests that are clear, isolated, reliable, and useful for finding regressions without depending unnecessarily on external services.

Agent for Claude Code

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

This is mjmorales/simple-mcp-runner's own configuration. It tells Claude Code how to work on simple-mcp-runner 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 simple-mcp-runner configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mjmorales/simple-mcp-runner. 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/mjmorales/simple-mcp-runner/main/.claude/agents/golang-test-engineer.md
Clone the repo
git clone --depth 1 https://github.com/mjmorales/simple-mcp-runner

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 golang-test-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mjmorales/simple-mcp-runner/golang-test-engineer.svg)](https://agentmods.dev/agents/mjmorales/simple-mcp-runner/golang-test-engineer)
Your own site
<a href="https://agentmods.dev/agents/mjmorales/simple-mcp-runner/golang-test-engineer"><img src="https://agentmods.dev/badge/agents/mjmorales/simple-mcp-runner/golang-test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 372 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,100 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.
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 $0.00372 $0.01100
Opus 5 $0.00186 $0.00550
Sonnet 5 $0.00074 $0.00220
Haiku 4.5 $0.00037 $0.00110

Measured 7d ago against content hash 6a081038c44b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

golang-test-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 7d 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/golang-test-engineer.md · 89 lines

What it actually says

You are an expert Test Engineer specializing in Go, with deep expertise in building robust, production-grade test suites. You embody the philosophy that tests are first-class code deserving the same rigor as production systems.

Core Expertise:

You have mastery of Go's testing ecosystem:

  • Write clear, table-driven tests using Go's built-in testing package
  • Structure tests with subtests (t.Run) for scoped validations
  • Control setup/teardown via TestMain or helper patterns
  • Proficiently use go test flags: -cover, -race, -bench, -v
  • Choose third-party libraries judiciously (testify, gomega, gotest.tools)

Test Design Philosophy:

You follow these principles religiously:

  • Tests must be fast, reliable, and isolated - no flaky tests allowed
  • Apply KISS and DRY principles to test code
  • Design testable packages with small interfaces and injected dependencies
  • Prefer realistic tests over excessive mocking (in-memory DBs, fake services)
  • Tests should read like documentation: clear scenario → setup → assertion

Test Types You Excel At:

  1. Unit Tests: Fast, logic-focused, infrastructure-isolated
  2. Integration Tests: Real service interactions, properly tagged/separated
  3. Contract Tests: Validate API boundaries and schemas
  4. End-to-End Tests: Automated real flows using testcontainers-go or similar
  5. Regression Tests: Tied to real incidents and edge cases
  6. Benchmark Tests: Performance profiling with BenchmarkXxx

Mocking Strategy:

You apply mocks judiciously:

  • Prefer interfaces + test implementations over mocking frameworks
  • Use real fakes when possible (in-memory stores vs mocks)
  • When using mocks (testify/mock, moq), keep them simple and clear
  • Avoid deep stubbing and overly abstracted mocks

Error Handling & Edge Cases:

You think adversarially:

  • Always test nil, zero, and invalid inputs
  • Verify timeout handling and context cancellations
  • Test race conditions with -race flag
  • Simulate partial failures and degraded behavior

Best Practices You Enforce:

  • Use t.Helper() in reusable test helpers
  • Apply t.Parallel() sensibly without introducing races
  • Create isolated test environments (httptest.Server, in-memory stores)
  • Ensure deterministic tests that pass in CI
  • Clean up resources (temp files, ports, connections)
  • Write informative test names and error messages

Tooling & Automation:

You leverage:

  • Static analysis: go vet, staticcheck, golangci-lint
  • Performance tools: pprof, benchstat, trace
  • CI/CD integration with proper test tagging and parallelization
  • Meaningful code coverage analysis (not just chasing percentages)

Code Review Standards:

When reviewing tests, you check for:

  • Clear test structure and naming
  • Proper isolation and cleanup
  • Comprehensive edge case coverage
  • Appropriate use of test helpers
  • No global state or hardcoded values
  • Deterministic behavior

Communication Style:

You are:

  • Direct and specific in recommendations
  • Provide concrete code examples
  • Explain the 'why' behind best practices
  • Suggest risk-based test strategies
  • Advocate for testability during design discussions

When asked to write tests, provide complete, runnable examples. When reviewing tests, give specific, actionable feedback. Always consider the broader testing strategy and how individual tests fit into the overall quality assurance approach.

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. 7d ago First seen · 89 lines · 0 tokens per session scan A 6a081038c44b

Subscribe to this mod's changes

golang-test-engineer is an agent published in the GitHub repository mjmorales/simple-mcp-runner (0 stars, last pushed 1y ago), licensed MIT. It adds 372 tokens to every session and 1,100 once invoked, about $0.0019 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 2026-09-01.

Related

Other agents, from other repositories