health

A command for checking the health of a Claude orchestration system, which coordinates agents, tools, hooks, and related components. It can show summaries, detailed results, JSON output, metrics, or available checks.

In plain words
What is it for?
Use it to check the whole system or a specific component, inspect metrics, list checks, get machine-readable results, or apply supported fixes.
Why use it?
It helps identify problems in the system and can attempt to fix issues marked as automatically fixable.

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/thelobbi/claude/health
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,174 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 $0.00011 $0.01174
Opus 5 $0.00005 $0.00587
Sonnet 5 $0.00002 $0.00235
Haiku 4.5 $0.00001 $0.00117

Measured today against content hash 16453e54ec71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

health 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 today.

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/health.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Health Check Command

Run comprehensive health checks on the Claude orchestration system to identify and fix issues.

Usage

/health [options]

Options

  • --verbose - Show detailed health information including all check details
  • --fix - Automatically attempt to fix auto-fixable issues
  • --component [name] - Check only a specific component (registry, mcp-servers, hooks, agents, database)
  • --json - Output results in JSON format
  • --list - List all available health checks
  • --metrics - Show health metrics and statistics

Examples

Quick Health Check

/health

Shows overall system health status with summary.

Detailed Health Check

/health --verbose

Shows full health report with all component details and issues.

Auto-Fix Issues

/health --fix

Runs health checks and attempts to automatically fix any auto-fixable issues.

Check Specific Component

/health --component registry
/health --component mcp-servers
/health --component hooks

JSON Output

/health --json

Outputs health status in JSON format for programmatic use.

List Available Checks

/health --list

Lists all registered health checks with their descriptions.

View Metrics

/health --metrics

Shows health check metrics and statistics.

Health Check Components

  1. Registry - Validates registry index files and references
  2. MCP Servers - Checks MCP server availability and configuration
  3. Hooks - Validates hook script executability
  4. Agents - Checks agent file existence and frontmatter
  5. Database - Tests database connectivity (if applicable)

Status Indicators

  • HEALTHY - Component is functioning normally
  • ⚠️ DEGRADED - Component has warnings but is functional
  • UNHEALTHY - Component has critical issues
  • UNKNOWN - Component status cannot be determined

Issue Severity

  • 🔴 CRITICAL - Requires immediate attention
  • 🟡 WARNING - Should be addressed soon
  • 🔵 INFO - Informational, no action required

Read the full file on GitHub · 188 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. today First seen · 188 lines · 11 tokens per session scan A 16453e54ec71

Subscribe to this mod's changes

health is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 1,174 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.