Borrowing it
Nothing to install: this file belongs to Teddy563/mcwrench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Teddy563/mcwrench/main/.gemini/commands/mcwrench/health.tomlgit clone --depth 1 https://github.com/Teddy563/mcwrenchWrote 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.
[](https://agentmods.dev/commands/teddy563/mcwrench/health)<a href="https://agentmods.dev/commands/teddy563/mcwrench/health"><img src="https://agentmods.dev/badge/commands/teddy563/mcwrench/health.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00184 |
| Opus 5 | $0.00000 | $0.00092 |
| Sonnet 5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
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 yesterday.
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.
What it actually says
description = "Grade a Minecraft server folder: config, conflicts, plugin currency, and today's log." prompt = """Act as mcwrench's server-doctor. Produce a health scorecard for: {{args}} (default: the current directory). Run the read-only scanners and roll them into one graded report: node skills/audit-config/scripts/scan-server-tree.mjs node skills/audit-config/scripts/check-conflicts.mjs node skills/server-doctor/scripts/check-plugin-versions.mjs node skills/server-doctor/scripts/parse-log.mjs
Grade security, performance, durability, and currency; list the top fixes prioritised critical to low. Read the server-profile so you do not re-ask known facts. Hand deep tuning to performance-tuning and config lint to audit-config. Read-only; never run live commands."""
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.
- yesterday Changed · -6 lines 921933c12ddf
- 6d ago First seen · 18 lines · 0 tokens per session scan A ca26626b61d7
health is a command published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 184 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 2026-08-31.
Other commands, from other repositories
refactor-clean
Remove dead code, duplicates, and tech debt with safe automated cleanup.
web-scene-audit
Audit web game scenes, screen flow, state transitions, and teardown patterns.
review-perf
Review the current branch for rendering performance, memoization, data fetching, and bundle impact in a React/Next.js codebase. Supports whole-branch review or scoped review by path, feature, or base branch.
build-fix
Incrementally fix build and type errors with minimal, safe changes.
fix
A pair of coding commands for fixing problems: one aims for a quick repair, while the other guides a step-by-step investigation.
unity-doctor
Diagnostic health check — verifies MCP connectivity, .claude/ integrity, Unity project structure, and hook registration.