mcp-coroot: Command for Claude Code

.claude/commands/test-coroot-natural.md

test-coroot-natural is a command for Claude Code from jamesbrink/mcp-coroot. It costs 0 tokens per session (909 once invoked), scanned A, original, MIT.

A command for testing a Coroot monitoring integration through ordinary language. Coroot is a tool for observing applications, infrastructure, logs, deployments, and request traces.

In plain words
What is it for?
Use it to run a full natural-language integration check, including creating a uniquely named test project, inspecting applications and infrastructure, and reviewing recent errors, traces, and deployments.
Why use it?
It provides a repeatable way to check connectivity, permissions, project health, monitoring data, and tracing without manually planning each request.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is jamesbrink/mcp-coroot's own configuration. It tells Claude Code how to work on mcp-coroot 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 mcp-coroot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jamesbrink/mcp-coroot. 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/jamesbrink/mcp-coroot/main/.claude/commands/test-coroot-natural.md
Clone the repo
git clone --depth 1 https://github.com/jamesbrink/mcp-coroot

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-coroot-natural

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/jamesbrink/mcp-coroot/test-coroot-natural"><img src="https://agentmods.dev/badge/commands/jamesbrink/mcp-coroot/test-coroot-natural.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 909 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 $0.00909
Opus 5 $0.00000 $0.00454
Sonnet 5 $0.00000 $0.00182
Haiku 4.5 $0.00000 $0.00091

Measured 9d ago against content hash d16db0b857eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

test-coroot-natural 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 9d 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/test-coroot-natural.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Coroot Integration

Perform a comprehensive test of the Coroot integration using natural language to verify all functionality works correctly.

Test Sequence

  1. Connection Test

    • Check if the Coroot server is healthy and responding
  2. Authentication Check

    • Show me who I'm logged in as and what permissions I have
  3. Explore Projects

    • List all the projects I have access to
    • Show me details about the first project
    • Check the health status of that project
  4. Create Test Environment

    • Create a new test project with a unique name including today's date and time
    • Verify the project was created successfully
  5. Application Monitoring

    • Show me an overview of all applications in an existing project
    • If there are any applications running, show me detailed metrics for one
  6. Infrastructure Inspection

    • Display the infrastructure nodes and their resource usage
    • Show me the distributed tracing overview
    • List recent deployments and their impact
  7. Logs and Traces (if applications exist)

    • Search for any error logs from the last hour
    • Show me some recent traces to understand request flow
  8. Integration Review

    • List all the integrations that are configured
    • Set up a test webhook integration to demonstrate configuration
  9. Configuration Management

    • Show me what inspection types are available for monitoring
    • Display the current application categorization rules
    • Create a new test application category with some patterns
    • Update the test category to add more patterns
    • Remove the test category we just created
    • Check if there are any custom application definitions
    • If applications exist, show me the SLO configuration for one
    • Test updating an inspection threshold (using the same value to avoid changes)
  10. Advanced Troubleshooting

    • If any applications have issues, analyze the root cause
    • Show me CPU and memory profiling data for a busy application
    • Review the risk configuration for critical applications

Read the full file on GitHub · 114 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. 9d ago First seen · 114 lines · 0 tokens per session scan A d16db0b857eb

Subscribe to this mod's changes

test-coroot-natural is a command published in the GitHub repository jamesbrink/mcp-coroot (16 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 909 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 2026-08-30.