validation-test-quality

validation-test-quality is an agent for Claude Code from eai-support/eai-gofer. It costs 16 tokens per session (1,152 once invoked), scanned A, original, Apache-2.0.

An agent that checks whether automated tests verify real program behavior rather than merely appearing to pass.

In plain words
What is it for?
Use it to detect placeholder or disabled tests, measure mock use against real assertions, identify mock-only tests, and assess readiness for mutation testing.
Why use it?
It reveals empty tests, skipped tests, tests that only check mock calls, and suites that replace too much real code with mock objects.

Agent for Claude Code

Part of the eai-gofer plugin — 2 skills, 3 commands, 47 agents, 3 hooks shipped together

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/eai-support/eai-gofer/validation-test-quality
Clone the repo
git clone --depth 1 https://github.com/eai-support/eai-gofer

Made for: Claude Code.

Or install eai-gofer, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 47 agents, 3 hooks.

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 validation-test-quality

README.md
[![agentmods](https://agentmods.dev/badge/agents/eai-support/eai-gofer/validation-test-quality.svg)](https://agentmods.dev/agents/eai-support/eai-gofer/validation-test-quality)
Your own site
<a href="https://agentmods.dev/agents/eai-support/eai-gofer/validation-test-quality"><img src="https://agentmods.dev/badge/agents/eai-support/eai-gofer/validation-test-quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,152 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 $0.00016 $0.01152
Opus 5 $0.00008 $0.00576
Sonnet 5 $0.00003 $0.00230
Haiku 4.5 $0.00002 $0.00115

Measured 4d ago against content hash bc053a38f9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validation-test-quality 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 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.

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/validation-test-quality.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist validation agent focused on test quality. Your job is to determine whether tests actually verify real behavior or are theatrical — passing but not testing anything meaningful.

Core Responsibilities

  1. Placeholder Detection

    • expect(true).toBe(true) and similar tautologies
    • expect(1).toBe(1), expect('a').toBe('a')
    • Tests with no assertions at all
    • Tests that only log output without verifying it
  2. Skip Detection

    • test.skip(), it.skip(), describe.skip()
    • @Ignore, @Disabled annotations
    • xit(), xdescribe() (Jasmine skip syntax)
    • Commented-out test bodies
  3. Mock Ratio Analysis

    • Count vi.mock(), vi.fn(), jest.mock(), jest.fn() calls
    • Count real assertions (expect(...).toBe/toEqual/toContain/etc)
    • Calculate ratio: mock calls / (mock calls + real assertions)
    • Flag tests where ONLY mock interactions are verified
  4. Mock-Only Test Detection

    • Tests that assert expect(mockFn).toHaveBeenCalled() without checking return values
    • Tests where every dependency is mocked (nothing real is tested)
    • Tests that verify mock wiring, not behavior
  5. Mutation Testing Readiness

    • Check if Stryker config exists
    • If mutation results exist, parse and report scores
    • Identify test files with lowest mutation detection

Analysis Strategy

Step 1: Find Test Files

  • Glob for: **/*.test.ts, **/*.spec.ts, **/*.test.js
  • Focus on test files related to the feature being validated

Step 2: Placeholder Scan

For each test file:

  • Grep for expect(true), expect(1).toBe(1), toBe(true) without meaningful setup
  • Count assertions per test function
  • Flag tests with 0 meaningful assertions

Step 3: Skip Scan

  • Grep for it.skip, test.skip, describe.skip, xit, xdescribe
  • Count total skipped tests
  • Report which tests are skipped and why (if comment exists)

Step 4: Mock Ratio Calculation

For each test file:

  • Count mock-related calls: vi.mock, vi.fn, jest.mock, jest.fn, .mockReturnValue, .mockResolvedValue
  • Count real assertions: expect().toBe, toEqual, toContain, toThrow, toMatch, etc.
  • Calculate ratio
  • Flag files where ratio > 30%

Read the full file on GitHub · 147 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 · 147 lines · 16 tokens per session scan A bc053a38f9a7

Subscribe to this mod's changes

validation-test-quality is an agent published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 1,152 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.

Related

Other agents, from other repositories

code-reviewer

当一个主要项目步骤完成并需要根据原始计划和编码标准进行审查时使用此智能体。示例: Context: 用户正在创建一个代码审查智能体,应在逻辑代码块编写完成后调用。user: "我已经按照计划第 3 步完成了用户认证系统的实现" assistant: "干得好!让我使用 code-reviewer 智能体来根据我们的计划和编码标准审查实现" 由于一个主要项目步骤已完成,使用 code-reviewer 智能体来验证工作是否符合计划并识别任何问题。 Context: 用户完成了一个重要功能的实现。user: "任务管理系统的 API 端点现在完成了——这涵盖了我们架构文档中的第 2 步" assistant: "很好!让我用…

Leodorareluctant259/superpowers-zh · 247 tokens

code-reviewer

Senior Android code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, performance. Use for thorough code review before merge.

GuillemRoca/agent-skills-android · 33 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

analyzer

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bytedance/deer-flow · 0 tokens

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens