README

README is a command for Claude Code from jamesbrink/mcp-coroot. It costs 0 tokens per session (319 once invoked), scanned A, original, MIT.

Project documentation for custom slash commands that test a Coroot MCP server. It explains two commands: one that names the tools explicitly and one that uses natural-language requests.

In plain words
What is it for?
Use it to run or understand the Coroot test commands, check prerequisites, and review their safety boundaries and expected test sequence.
Why use it?
It tells developers what the commands test, what they may create, and which Coroot credentials and server setup are required.

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/jamesbrink/mcp-coroot/readme
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 README

README.md
[![agentmods](https://agentmods.dev/badge/commands/jamesbrink/mcp-coroot/readme.svg)](https://agentmods.dev/commands/jamesbrink/mcp-coroot/readme)
Your own site
<a href="https://agentmods.dev/commands/jamesbrink/mcp-coroot/readme"><img src="https://agentmods.dev/badge/commands/jamesbrink/mcp-coroot/readme.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 319 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 $0.00319
Opus 5 $0.00000 $0.00160
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 5d ago against content hash 9652bf072212, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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 5d 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/README.md · 45 lines

What it actually says

Claude Code Slash Commands for Coroot MCP

This directory contains custom slash commands for testing the Coroot MCP server integration.

Available Commands

/test-coroot-tools

A comprehensive test suite that explicitly calls each MCP tool to verify functionality. This command:

  • Tests all 61 Coroot MCP tools in a logical sequence
  • Creates test resources with unique names to avoid conflicts
  • Provides detailed feedback on each tool's success/failure
  • Never modifies or deletes existing resources (except for test resources it creates)

/test-coroot-natural

The same comprehensive test but using natural language instead of tool names. This command:

  • Performs the same tests as above but with conversational requests
  • Useful for testing the LLM's ability to map natural language to appropriate tools
  • Creates the same test resources safely
  • Provides user-friendly feedback

Usage

In Claude Code, simply type:

/test-coroot-tools

or

/test-coroot-natural

Prerequisites

Ensure your Coroot MCP server is configured and running:

  1. The .env file contains valid Coroot credentials
  2. The MCP server is accessible to Claude Code
  3. Your Coroot instance is running and accessible

Safety

Both commands are designed to be non-destructive:

  • They only create new resources with unique timestamps
  • They never delete or modify existing projects or configurations
  • They handle errors gracefully and continue testing
  • Test resources are clearly named (e.g., mcp-test-20250126-143022)
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. 5d ago First seen · 45 lines · 0 tokens per session scan A 9652bf072212

Subscribe to this mod's changes

README is a command published in the GitHub repository jamesbrink/mcp-coroot (16 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 319 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.