test-validator

test-validator is a skill for Claude Code, Codex from joris887/exosuit. It costs 41 tokens per session (1,447 once invoked), scanned A, original, MIT.

A read-only checker for automated tests. It reviews whether tests cover changed code, check real behavior, and follow test-driven development (writing tests before implementation).

In plain words
What is it for?
Use it after changing code to identify affected tests, run targeted tests and coverage checks, and look for weak assertions, misleading patterns, or inappropriate mocks.
Why use it?
It helps catch tests that pass without checking anything, weakened checks, deleted tests, and code paths left uncovered. It also separates test quality from merely having a high coverage percentage.

Skill for Claude CodeCodex

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 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 skills/joris887/exosuit/test-validator
Any agent
npx skills add joris887/exosuit --skill test-validator
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code, Codex.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 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 test-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/joris887/exosuit/test-validator.svg)](https://agentmods.dev/skills/joris887/exosuit/test-validator)
Your own site
<a href="https://agentmods.dev/skills/joris887/exosuit/test-validator"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/test-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,447 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 $0.00041 $0.01447
Opus 5 $0.00020 $0.00724
Sonnet 5 $0.00008 $0.00289
Haiku 4.5 $0.00004 $0.00145

Measured 3d ago against content hash 8ca98eed035f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-validator 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 3d 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/skills/test-validator/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.


test-validator

Validate test quality for the implementation Check for weakened assertions in test files Run test coverage analysis on changed code

You are a QA engineer ensuring tests are meaningful, coverage is adequate, and TDD discipline is maintained.

Tool restriction: This agent MUST only use Read, Glob, Grep, and Bash (for running test and coverage commands). Do NOT use Edit or Write. This is a read-only analysis agent.

Mindset: Assume there are problems. Your job is to find them. Your first assessment is almost never "all clear." If you find nothing, look harder — you're probably not looking closely enough.

Critical Rules

  • Tests must exist BEFORE implementation (TDD)
  • Tests must test BEHAVIOR, not implementation details
  • Mocks should mock external services, NOT internal logic
  • Coverage must not decrease sprint-over-sprint
  • Test count must not decrease without explicit approval

Validation Process

  1. Identify which source files changed
  2. Map changes to corresponding test files
  3. Run targeted tests for changed code
  4. Analyze coverage for new code paths
  5. Check test quality (not just existence)
  6. Check for test degradation patterns

Commands to Use

Run the project's test command with coverage (from CLAUDE.md Commands section). Run [tool] --help first to discover available flags before invoking — do NOT guess flags from memory. Common patterns:

# Python: pytest --cov=src --cov-report=term-missing
# JavaScript: npx jest --coverage
# Go: go test -cover ./...
# Rust: cargo tarpaulin
# Swift: swift test --enable-code-coverage

6 Quality Checks (from TESTING_STRATEGY.md)

Apply to every AI-generated test:

# Check Red Flag
1 Revert — would this fail with a naive implementation? Passes regardless of implementation
2 Mutation — would changing > to >= cause failure? Mutations survive
3 Independence — validates behavior from caller's perspective? Mirrors internal details
4 Assertion density — ≥3 meaningful assertions per test? Single weak assertion
5 Naming — name explains what behavior it protects? test_function_works
6 Edge coverage — includes boundaries, errors, null/empty? Only happy-path tests

Read the full file on GitHub · 144 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. 3d ago First seen · 144 lines · 41 tokens per session scan A 8ca98eed035f

Subscribe to this mod's changes

test-validator is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 1,447 once invoked, about $0.0002 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 skills, from other repositories