mcp-deadmansnitch: Command for Claude Code

.claude/commands/test-mcp-tools.md

test-mcp-tools is a command for Claude Code from jamesbrink/mcp-deadmansnitch. It costs 0 tokens per session (949 once invoked), scanned A, original, MIT.

A command for safely testing Dead Man’s Snitch, a service that alerts you when scheduled check-ins stop arriving. It runs through MCP tools and reports each test result.

In plain words
What is it for?
Use it to list, create, inspect, update, tag, check in, pause, resume, and delete a test snitch.
Why use it?
It lets you verify monitoring actions without using direct API calls or leaving the test snitch behind. Failed steps are recorded while the remaining checks continue.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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

Reuse

Borrowing it

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

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-mcp-tools

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/jamesbrink/mcp-deadmansnitch/test-mcp-tools"><img src="https://agentmods.dev/badge/commands/jamesbrink/mcp-deadmansnitch/test-mcp-tools.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 949 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 $0.00000 $0.00949
Opus 5 $0.00000 $0.00475
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 9d ago against content hash c383aad7012f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

test-mcp-tools 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 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.

Makes network callslowCapability

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

- **ONLY use the MCP tools** - Do NOT use curl, bash commands, or direct API calls
.claude/commands/test-mcp-tools.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test MCP Tools

You are going to comprehensively test the Dead Man's Snitch MCP tools in a non-destructive manner. Follow these steps exactly and report the results of each operation.

Test Plan

  1. List all snitches - Use the MCP tool to list existing snitches and display a summary
  2. Create a test snitch - Create a new snitch with specific test parameters
  3. Get snitch details - Retrieve and display the created snitch's details
  4. Update the snitch - Modify various attributes of the test snitch
  5. Add tags - Add multiple tags to the test snitch
  6. Remove a tag - Remove one of the added tags
  7. Check in - Send a check-in to the test snitch with a message
  8. Pause the snitch - Temporarily pause monitoring
  9. Unpause the snitch - Resume monitoring
  10. Delete the test snitch - Clean up by removing the test snitch

Important Instructions

  • ONLY use the MCP tools - Do NOT use curl, bash commands, or direct API calls
  • Use the unified snitch tool mcp__deadmansnitch__snitch with the action parameter
  • Report each step's outcome clearly with success/failure status
  • If any step fails, continue with the remaining tests and note the failure
  • Use unique identifiers for the test snitch to avoid conflicts

Test Execution

Step 1: List All Snitches

Use mcp__deadmansnitch__snitch with action="list" to get the current list of snitches. Display:

  • Total count of snitches
  • A brief summary of existing snitches (names and statuses)

Step 2: Create Test Snitch

Use mcp__deadmansnitch__snitch with these parameters:

  • action: "create"
  • name: "MCP Tool Test Snitch - DELETE ME"
  • interval: "hourly"
  • notes: "This is a temporary test snitch created to verify MCP tools functionality. Safe to delete."
  • alert_type: "basic"

Save the token from the response for subsequent operations.

Step 3: Get Snitch Details

Use mcp__deadmansnitch__snitch with:

  • action: "get"
  • token: (from Step 2)

Step 4: Update Snitch

Read the full file on GitHub · 120 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 · 120 lines · 0 tokens per session scan A c383aad7012f

Subscribe to this mod's changes

test-mcp-tools is a command published in the GitHub repository jamesbrink/mcp-deadmansnitch (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 949 tokens. 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 2026-08-31.