airis-mcp-gateway: Command for Claude Code

.claude/commands/test.md

test is a command for Claude Code from agiletec-inc/airis-mcp-gateway. It costs 15 tokens per session (543 once invoked), scanned A, original, MIT.

A test procedure for checking an AIRIS MCP Gateway, including its health, pre-warmed servers, tools, and optional data persistence. MCP Gateway is a service that connects an agent to multiple tools and servers.

In plain words
What is it for?
Use it for gateway health checks, server pre-warming checks, time and memory tests, confidence and repository-index tests, suggestion tests, and optional persistence testing.
Why use it?
It provides an ordered way to verify that the gateway is running and that representative tools respond correctly. This can reveal failures in health checks, server startup, tool access, or persistence.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is agiletec-inc/airis-mcp-gateway's own configuration. It tells Claude Code how to work on airis-mcp-gateway 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 airis-mcp-gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agiletec-inc/airis-mcp-gateway. 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/agiletec-inc/airis-mcp-gateway/main/.claude/commands/test.md
Clone the repo
git clone --depth 1 https://github.com/agiletec-inc/airis-mcp-gateway

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 test

README.md
[![agentmods](https://agentmods.dev/badge/commands/agiletec-inc/airis-mcp-gateway/test/github.svg)](https://agentmods.dev/commands/agiletec-inc/airis-mcp-gateway/test)
Your own site
<a href="https://agentmods.dev/commands/agiletec-inc/airis-mcp-gateway/test"><img src="https://agentmods.dev/badge/commands/agiletec-inc/airis-mcp-gateway/test/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

Your own site · 80×15
<a href="https://agentmods.dev/commands/agiletec-inc/airis-mcp-gateway/test"><img src="https://agentmods.dev/badge/commands/agiletec-inc/airis-mcp-gateway/test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00015 $0.00543
Opus 5 $0.00008 $0.00271
Sonnet 5 $0.00003 $0.00109
Haiku 4.5 $0.00002 $0.00054

Measured 10d ago against content hash 2d8826546277, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

test scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(task*), Bash(docker*), Bash(curl*), mcp__airis-mcp-gateway__*
.claude/commands/test.md · 58 lines

What it actually says

AIRIS MCP Gateway End-to-End Test

Run a comprehensive end-to-end test of the AIRIS MCP Gateway.

Pre-flight Checks

Container status: !task docker:ps 2>/dev/null || docker compose ps 2>/dev/null || echo "Stack not running"

Test Sequence

Execute these tests in order:

1. Gateway Health

  • Call mcp__airis-mcp-gateway__gateway_health to verify the gateway is healthy
  • Confirm status is "healthy" and at least some servers are "ready"

2. HOT Server Pre-warming

  • Check pre-warm status: task test:prewarm
  • Verify HOT servers (airis-mcp-gateway-control, airis-commands) pre-warmed

3. Tool Functionality

Test tools from different servers:

  • Time server: Call mcp__airis-mcp-gateway__get_current_time with timezone "UTC"
  • Memory server: Call mcp__airis-mcp-gateway__read_graph to read knowledge graph
  • Confidence: Call mcp__airis-mcp-gateway__airis-confidence with task "test"
  • Repo Index: Call mcp__airis-mcp-gateway__airis-repo-index with repo_path "." and mode "quick"
  • Suggest: Call mcp__airis-mcp-gateway__airis-suggest with intent "search the web"

4. Data Persistence (optional)

If $ARGUMENTS contains "persistence":

  • Create a test entity with mcp__airis-mcp-gateway__create_entities
  • Restart container: task docker:restart
  • Wait 10 seconds for pre-warm
  • Verify entity still exists with mcp__airis-mcp-gateway__read_graph
  • Clean up test entity with mcp__airis-mcp-gateway__delete_entities

Output

Provide a summary table:

Test Status Details
Gateway Health
Pre-warming
Time Tool
Memory Tool
Confidence
Repo Index
Suggest
Persistence (if tested)

Report any failures with actionable troubleshooting steps.

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. 10d ago First seen · 58 lines · 15 tokens per session scan A 2d8826546277

Subscribe to this mod's changes

test is a command published in the GitHub repository agiletec-inc/airis-mcp-gateway (172 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 543 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.