Mastra System Check — Security skill for Claude Code
Claude Code skill that validates Mastra AI agent projects with 66 checks across configuration, agents, workflows, memory, tools, prompts, and security.
How to install Mastra System Check
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open goldk3y/mastra-system-check and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Mastra System Check does
Claude Code skill that validates Mastra AI agent projects with 66 checks across configuration, agents, workflows, memory, tools, prompts, and security.
Alternatives in Security
- Imcodes — The IM for agents 960 ★
- Unifly Audit — Security audit of UniFi configuration 248 ★
- Goal Prompt Builder — Build audit-friendly /goal prompts for OpenAI Codex 225 ★
README
Mastra System Check
A comprehensive Claude Code skill for validating Mastra AI agent projects. This skill performs **66 checks** across **10 categories** to identify configuration issues, missing best practices, and potential problems before they cause runtime errors.
Installation
Option 1: npx (Recommended)
npx mastra-system-check
Option 2: One-line install
curl -fsSL https://raw.githubusercontent.com/goldk3y/mastra-system-check/main/install.sh | bash
Option 3: Git clone
git clone https://github.com/goldk3y/mastra-system-check.git ~/.claude/skills/mastra-system-check
Option 4: Manual
Download and copy this directory to:
~/.claude/skills/mastra-system-check/
Verification
The skill will automatically activate when working with Mastra projects. You can verify installation by asking Claude Code to perform a system check on your Mastra project.
What It Checks
Priority Levels
| Badge | Level | Description | Action |
|---|---|---|---|
| 🔴 | CRITICAL | System won't function | Fix immediately |
| 🟠 | HIGH | Major functionality issues | Fix before deployment |
| 🟡 | MEDIUM | Quality and maintainability | Fix when possible |
| 🟢 | LOW | Performance and cost | Nice to have |
Check Categories
| # | Category | Rules | Priority | Key Checks |
|---|---|---|---|---|
| 1 | Configuration & Setup | 6 | 🔴 CRITICAL | Storage, env vars, TypeScript, entry points |
| 2 | Agent Configuration | 6 | 🟠 HIGH | Model format, instructions, tools, memory |
| 3 | Workflow Configuration | 6 | 🟠 HIGH | .commit(), schemas, steps, error handling |
| 4 | Context & Data Flow | 8 | 🟠 HIGH | Type safety, middleware, propagation |
| 5 | Prompt Engineering | 10 | 🟠 HIGH | Structure, token efficiency, examples |
| 6 | Memory Configuration | 6 | 🟡 MEDIUM | Stor |
Related Skills
Crewforth
Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and shi
Cchub
Desktop hub for managing Claude Code MCP servers, health checks, configuration profiles, skills, plugins, hook
MCP Test
Run MCP protocol compliance tests — 39 tests across protocol, tools, resources, prompts, edge cases, and secur
LLM Memory Audit Prompts
Audit Your LLM Memory: Prompt Recipes for Business Users
Aeo Audit
Comprehensive Agentic Engine Optimization audit for websites and documentation. Checks llms.txt, robots.txt, t
Prompt Audit
Audit of Claude Code's default system prompt behavioral instructions. Each instruction is classified by how cl
Related Agents
Context Optimizer
Meta utility agent for token and context optimization. Spawn when needing to compress agent prompts, optimize
Ga4 Conversions
GA4 key events (conversions) configuration auditor. Validates which events are marked as key events, checks co
ProvenanceAuditor
Provenance and deployment integrity auditor -- validates SLSA sidecars, manifests, and drift across providers.