konnexx-dev-mcp: Command for Claude Code

.cursor/commands/test-fix.md

test-fix is a command for Claude Code, Cursor from Konnexx-Software-Developers/konnexx-dev-mcp. It costs 0 tokens per session (1,099 once invoked), scanned A, original, MIT.

A development command that runs Vitest, a JavaScript and TypeScript testing tool, after code changes and fixes the failures it finds.

In plain words
What is it for?
Use it after implementing features in the package to run tests, investigate failures, and apply fixes.
Why use it?
It avoids accidentally starting a watch mode that keeps running and gives a repeatable test-and-fix routine.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

This is Konnexx-Software-Developers/konnexx-dev-mcp's own configuration. It tells Claude Code and Cursor how to work on konnexx-dev-mcp 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 konnexx-dev-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Konnexx-Software-Developers/konnexx-dev-mcp. 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/Konnexx-Software-Developers/konnexx-dev-mcp/main/.cursor/commands/test-fix.md
Clone the repo
git clone --depth 1 https://github.com/Konnexx-Software-Developers/konnexx-dev-mcp

Made for: Claude Code, Cursor.

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-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/konnexx-software-developers/konnexx-dev-mcp/test-fix/github.svg)](https://agentmods.dev/commands/konnexx-software-developers/konnexx-dev-mcp/test-fix)
Your own site
<a href="https://agentmods.dev/commands/konnexx-software-developers/konnexx-dev-mcp/test-fix"><img src="https://agentmods.dev/badge/commands/konnexx-software-developers/konnexx-dev-mcp/test-fix/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for test-fix

Your own site · 80×15
<a href="https://agentmods.dev/commands/konnexx-software-developers/konnexx-dev-mcp/test-fix"><img src="https://agentmods.dev/badge/commands/konnexx-software-developers/konnexx-dev-mcp/test-fix.svg" alt="Reviewed on agentmods" width="80" 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 1,099 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 $0.00000 $0.01099
Opus 5 $0.00000 $0.00549
Sonnet 5 $0.00000 $0.00220
Haiku 4.5 $0.00000 $0.00110

Measured 8d ago against content hash 3089d7a392e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-fix 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 8d 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.

.cursor/commands/test-fix.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Fix (Default - Vitest)

Use this command for: Standard development machines

Test Framework: Vitest

Command: npm run test:run (always use this - npm test runs in watch mode and will hang)

You are a test automation assistant for the konnexx-dev-mcp package. Use this command after implementing a feature to run tests, identify failures, and fix them automatically.

Important: Git Command Usage

ALWAYS use git --no-pager prefix for all git commands to prevent pagination that blocks AI execution:

  • git --no-pager diff (not git diff)
  • git --no-pager diff --name-only (not git diff --name-only)
  • git --no-pager status (not git status)

Step 0: MCP-Enhanced Setup (Optional)

Before running tests, use MCPs for better context:

Use Filesystem MCP to Find Test Files

  • Search for test files related to changed code using Filesystem MCP
  • Look for patterns: src/**/*.test.ts
  • This helps identify which tests might be affected

Use Context7 MCP for Testing Patterns (When Fixing)

  • Query Vitest/TypeScript testing best practices when fixing tests
  • Examples: "How do I mock modules in Vitest?", "TypeScript test assertion examples"
  • "Vitest mocking best practices"

Step 1: Run Tests

Execute in terminal:

npm run test:run

What to expect:

  • Tests run using Vitest
  • Output shows passing/failing tests
  • Any failures will be displayed with error messages

If tests pass:

  • ✅ Display: "All tests passing!"
  • ✅ Return success summary
  • ✅ Skip to Step 4 (Summary)

If tests fail:

  • Continue to Step 2

Step 2: Analyze Failures

Review the test output to identify:

  • Which tests failed? (test file names and test names)
  • What are the error messages? (TypeScript errors, assertion failures, etc.)
  • What files are involved? (source files and test files)

Categorize failures:

  • TypeScript compilation errors: Syntax errors, type errors
  • Test assertion failures: Expected vs actual mismatches
  • Import/module errors: Missing imports, wrong paths
  • Logic errors: Incorrect implementation

Read the full file on GitHub · 150 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. 8d ago First seen · 150 lines · 0 tokens per session scan A 3089d7a392e4

Subscribe to this mod's changes

test-fix is a command published in the GitHub repository Konnexx-Software-Developers/konnexx-dev-mcp (0 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,099 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 2026-08-31.