go-tests-reviewer

go-tests-reviewer is an agent for coding agents from vladolaru/claude-code-plugins. It costs 31 tokens per session (1,064 once invoked), scanned B, original, MIT.

A reviewer for Go tests, including table-driven tests, HTTP tests, benchmarks, and interface-based mocks. Go is a programming language, and tests are code that check whether software behaves correctly.

In plain words
What is it for?
Use it to review Go test files, test helpers, HTTP handlers, benchmarks, mocks, fuzz tests, and race-detection setup.
Why use it?
It catches weaknesses and non-idiomatic patterns in Go test code before the tests give misleading confidence.

Agent

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 agents/vladolaru/claude-code-plugins/go-tests-reviewer
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins

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 go-tests-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/go-tests-reviewer.svg)](https://agentmods.dev/agents/vladolaru/claude-code-plugins/go-tests-reviewer)
Your own site
<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/go-tests-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/go-tests-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00031 $0.01064
Opus 5 $0.00015 $0.00532
Sonnet 5 $0.00006 $0.00213
Haiku 4.5 $0.00003 $0.00106

Measured 4d ago against content hash b5278f30556d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

go-tests-reviewer scanned grade B with 1 finding 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 4d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Read the output carefully. It contains your review rules (including the shared tests protocol), review scope, and output instructions. If STATUS is NO_DOMAIN_FILES, report "No Go test files to review" → APPROVE → exit. I
plugins/pirategoat-tools/agents/go-tests-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY SETUP — Run Bootstrap Before Reviewing

Do NOT start reviewing code until this step is done:

Run the bootstrap script:

PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent go-tests-reviewer

Read the output carefully. It contains your review rules (including the shared tests protocol), review scope, and output instructions. If STATUS is NO_DOMAIN_FILES, report "No Go test files to review" → APPROVE → exit. If ERROR, follow the instructions and exit.


You are an expert Go Test Quality Reviewer specializing in the standard testing package ecosystem and common Go testing patterns.

Your expertise: Table-driven tests, subtests, test helpers with t.Helper(), httptest for HTTP testing, interface-based mocking, benchmarks, fuzz testing, race detection, t.Cleanup/t.TempDir/t.Setenv patterns, and Go-specific test anti-patterns.

This review matters. False confidence from bad tests causes production bugs that proper review would have caught.

Core Mission

Verify test quality -> Detect false confidence -> Ensure behavior coverage

Do NOT review implementation code. Do NOT review tests in other languages.

Deep Knowledge References

All reference files are at $PLUGIN_ROOT/skills/testing-patterns/references/.

Test Issue Reference File Sections to Read
Behavior vs implementation test-philosophy.md ## The Fundamental Shift + ## Four Core Principles
Flaky/brittle/slow tests test-smells.md ## The Six Major Test Smells (relevant subsection)
Mock usage decisions mocking-strategies.md ## The Mocking Decision Framework + ## Types of Test Doubles
AAA pattern/naming test-structure.md ## The AAA Pattern + ## Test Naming Conventions
Go testing patterns go-testing-patterns.md Full file (~420L, manageable)

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 31 tokens per session scan B b5278f30556d

Subscribe to this mod's changes

go-tests-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,064 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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

test-writer

Generate context-aware Go tests with meaningful assertions and branch coverage. Use when adding tests to existing code, improving coverage, or after implementing new features.

erraggy/oastools · 33 tokens

strike-test-writer

Writes Go tests only for strike-cli using stdlib testing and repo conventions. Never modifies production code. Use when adding coverage for tools, permissions, protocol, session, config, providers, auth, engine, or TUI.

jonathanung/strike · 45 tokens

hcc-frontend-go-unit-test-writer

Use this agent when you need to write unit tests for Go code. This includes pure functions, utilities, services, handlers, and business logic. Use this agent AFTER writing or modifying Go code that falls into these categories. Examples: Context: User has written a service function for data transformation. user: "I…

RedHatInsights/platform-frontend-ai-toolkit · 245 tokens

go-test-engineer

Write comprehensive tests, debug test failures, improve test coverage.

ready-to-release/eac · 16 tokens

go-test-developer

Go testing developer. Helps design and write high-quality tests: table-driven tests, test helpers, subtests, fixtures, assertion strategies, and benchmark design.

yanmxa/cc-plugins · 36 tokens

test-engineer

MUST BE USED for writing and maintaining Go unit tests, integration tests, table-driven test patterns, test fixtures, and test utilities. Use after implementation is complete or when someone says "write tests for" or "add test coverage for" or "this needs tests.".

datum-cloud/claude-code-plugins · 58 tokens