qcheckt

qcheckt is a command for Claude Code from brianmontero18/dev-mcp-tools. It costs 0 tokens per session (751 once invoked), scanned A, original, MIT.

A command that reviews the quality of major tests using a checklist for meaningful assertions, clear descriptions, independent expectations, edge cases, and maintainable test code.

In plain words
What is it for?
Type `qcheckt` after adding or changing important tests to examine their inputs, assertions, descriptions, independence, properties, grouping, and coverage.
Why use it?
It helps detect tests that pass without finding real defects, rely on unexplained values, describe the wrong behaviour, or check implementation details too closely.

Command for Claude Code

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 commands/brianmontero18/dev-mcp-tools/qcheckt
Clone the repo
git clone --depth 1 https://github.com/brianmontero18/dev-mcp-tools

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 qcheckt

README.md
[![agentmods](https://agentmods.dev/badge/commands/brianmontero18/dev-mcp-tools/qcheckt.svg)](https://agentmods.dev/commands/brianmontero18/dev-mcp-tools/qcheckt)
Your own site
<a href="https://agentmods.dev/commands/brianmontero18/dev-mcp-tools/qcheckt"><img src="https://agentmods.dev/badge/commands/brianmontero18/dev-mcp-tools/qcheckt.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 751 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 $0.00000 $0.00751
Opus 5 $0.00000 $0.00376
Sonnet 5 $0.00000 $0.00150
Haiku 4.5 $0.00000 $0.00075

Measured 3d ago against content hash 1959d7ebbe43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qcheckt 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/commands/qcheckt.md · 54 lines

What it actually says

QCHECKT - Test-Focused Review

When user types "qcheckt", execute this workflow as a SKEPTICAL senior software engineer:

Focus: Writing Tests Best Practices Only

For every MAJOR test added or edited (skip minor changes):

Test Quality Checklist (CLAUDE.md)

  1. Parameterized Inputs: SHOULD parameterize inputs; never embed unexplained literals such as 42 or "foo" directly in test
  2. Real Defect Testing: SHOULD NOT add test unless it can fail for real defect. Trivial asserts (e.g., expect(2).toBe(2)) are forbidden
  3. Description Alignment: SHOULD ensure test description states exactly what the final expect verifies. If wording and assert don't align, rename or rewrite
  4. Independent Expectations: SHOULD compare results to independent, pre-computed expectations or domain properties, never to function's output re-used as oracle
  5. Code Standards: SHOULD follow same lint, type-safety, and style rules as prod code (prettier, ESLint, strict types)
  6. Property Testing: SHOULD express invariants or axioms (commutativity, idempotence, round-trip) rather than single hard-coded cases when practical. Use fast-check library
  7. Test Grouping: Unit tests for function should be grouped under describe(functionName, () => ...
  8. Parameter Testing: Use expect.any(...) when testing for parameters that can be anything (e.g. variable ids)
  9. Strong Assertions: ALWAYS use strong assertions over weaker ones e.g. expect(x).toEqual(1) instead of expect(x).toBeGreaterThanOrEqual(1)
  10. Edge Cases: SHOULD test edge cases, realistic input, unexpected input, and value boundaries
  11. Type Safety: SHOULD NOT test conditions that are caught by the type checker

Response Template

🧪 **QCHECKT - Test Review**

**Tests Analyzed:**

**Test**: `testName` in `file.test.ts`
1. **Parameterized**: ✅/❌ [No magic literals like 42, "foo"?]
2. **Real Defects**: ✅/❌ [Can fail for actual bugs, not trivial?]
3. **Description**: ✅/❌ [Description matches what expect verifies?]
4. **Independent**: ✅/❌ [Expectations independent of implementation?]
5. **Standards**: ✅/❌ [Follows lint/type/style rules?]
6. **Properties**: ✅/❌ [Uses invariants/axioms when possible?]
7. **Grouping**: ✅/❌ [Grouped under describe(functionName)?]
8. **Parameters**: ✅/❌ [Uses expect.any() appropriately?]
9. **Strong Asserts**: ✅/❌ [Strong over weak assertions?]
10. **Edge Cases**: ✅/❌ [Covers boundaries/unexpected input?]
11. **Type Safety**: ✅/❌ [Doesn't test type-checker conditions?]

**Property Testing Opportunities:**
[Could this test benefit from fast-check invariants?]

**Edge Cases Coverage:**
- Boundaries: ✅/❌
- Empty/null inputs: ✅/❌  
- Invalid inputs: ✅/❌
- Large datasets: ✅/❌

**Recommendations:**
[Specific suggestions for test improvement]

**Test Status:** ✅ Solid / ⚠️ Needs improvement / ❌ Rewrite needed
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 · 54 lines · 0 tokens per session scan A 1959d7ebbe43

Subscribe to this mod's changes

qcheckt is a command published in the GitHub repository brianmontero18/dev-mcp-tools (0 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 751 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 2026-09-01.