Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Teddy563/mcwrench/plugin install 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/skills/teddy563/mcwrench/server-doctor)<a href="https://agentmods.dev/skills/teddy563/mcwrench/server-doctor"><img src="https://agentmods.dev/badge/skills/teddy563/mcwrench/server-doctor.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 | $0.00172 | $0.01185 |
| Opus 5 | $0.00086 | $0.00593 |
| Sonnet 5 | $0.00034 | $0.00237 |
| Haiku 4.5 | $0.00017 | $0.00119 |
Grade A, and why
server-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Server Doctor (day-2 operations)
Keep a running server healthy. Three jobs, all local and read-only — paste a log or point at a
server folder; never run live commands or write to a panel (that is a future operator mode).
Never invent config keys or plugin behaviour; confirm specifics with learn-plugin-docs.
1. Diagnose a crash or error (/mcwrench:diagnose)
The headline. Read a crash-reports/crash-*.txt, logs/latest.log, or pasted text and return a
ranked root cause.
node "${CLAUDE_PLUGIN_ROOT}/skills/server-doctor/scripts/parse-log.mjs" <file-or-server-root>
# or pipe: cat latest.log | node .../parse-log.mjs
# add --json for machine output
It names the likely culprit namespace (the first non-engine stack frame), and matches signatures
in references/log-signatures.md: UnsupportedClassVersionError (Java too old — class file version 69
= Java 25), OutOfMemoryError, Watchdog / single-tick overload, ticking entity/world crashes, port
already in use, EULA not accepted, plugin load failures (Unsupported API version / missing
dependency), NoClassDefFoundError/NoSuchMethodError. Each finding has a fix recipe; route a named
plugin to learn-plugin-docs and lag findings to performance-tuning. Cross-reference the
server-profile (Java/software/plugins) to disambiguate (e.g. UnsupportedClassVersionError on a
26.1 jar = Java < 25).
2. Health scorecard (/mcwrench:health)
A one-shot graded report for a server folder. Run the existing read-only scanners and roll them up:
node "${CLAUDE_PLUGIN_ROOT}/skills/audit-config/scripts/scan-server-tree.mjs" <root> # software, version, plugins, footguns
node "${CLAUDE_PLUGIN_ROOT}/skills/audit-config/scripts/check-conflicts.mjs" <root> # plugin conflicts + missing deps
node "${CLAUDE_PLUGIN_ROOT}/skills/server-doctor/scripts/check-plugin-versions.mjs" <root> # outdated / no-build-for-this-MC
node "${CLAUDE_PLUGIN_ROOT}/skills/server-doctor/scripts/parse-log.mjs" <root> # today's crash/log, if any
Grade four areas — security, performance, durability, currency — list the top fixes prioritised
critical to low, and hand deep tuning to performance-tuning and config lint to audit-config. Use
the server-profile so you do not re-ask known facts.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 74 lines · 172 tokens per session scan A 7ae425f50f73
server-doctor is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed yesterday), licensed MIT. It adds 172 tokens to every session and 1,185 once invoked, about $0.0009 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.
Other skills, from other repositories
performance-optimization
Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each…
code-review
Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback…
gamedev-perf-profile
Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.
jahro-logging
Reviews and improves Debug.Log usage in Unity C# projects following structured logging principles: context tags, severity contracts, boundary-based placement, and criticality tiers. Detects common antipatterns (naked Debug.Log, logging in Update, stringly-typed errors), adds missing logs at system/state/error/external…
jahro-migration
Analyzes existing debug systems (IMGUI menus, custom loggers, cheat frameworks, performance HUDs) and generates incremental migration plans to Jahro equivalents. Use when the user wants to replace a custom debug UI, migrate from an existing console or cheat system, switch to Jahro, or has OnGUI debug code they want to…
jahro-troubleshooting
Diagnoses common Jahro issues using decision trees: commands not appearing, watcher not updating, console not opening, snapshots failing, launch button missing. Use when the user reports something not working, missing, broken, or unexpected with Jahro, or when generated Jahro code doesn't behave as expected.