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.
npx agentmods add skills/teddy563/mcwrench/pterodactyl-opsnpx skills add Teddy563/mcwrench --skill pterodactyl-opsgit 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/skills/teddy563/mcwrench/pterodactyl-ops)<a href="https://agentmods.dev/skills/teddy563/mcwrench/pterodactyl-ops"><img src="https://agentmods.dev/badge/skills/teddy563/mcwrench/pterodactyl-ops.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 | $0.00171 | $0.01074 |
| Opus 5 | $0.00086 | $0.00537 |
| Sonnet 5 | $0.00034 | $0.00215 |
| Haiku 4.5 | $0.00017 | $0.00107 |
Grade A, and why
pterodactyl-ops 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pterodactyl / Pelican Ops
Run and configure Minecraft servers on Pterodactyl Panel and Pelican Panel (a fork by the
former Pterodactyl team, mid-2024; still beta as of 2026-06, relicensed AGPLv3). Pelican
imports Pterodactyl eggs unmodified and keeps the API backward-compatible, so this skill
applies to both — note the few differences in references/panel-footguns.md.
Architecture (one-screen model)
- Panel (web UI) + Wings (daemon, one per node). Each server is an isolated Docker
container; files live at
/home/container(host bind-mount under/var/lib/pterodactyl/volumes/<uuid>). - The STARTUP command substitutes egg variables (
{{SERVER_JARFILE}},{{SERVER_MEMORY}}, …) from environment variables at boot. Console/stats stream to the panel. - Allocations: the primary allocation is the game port. Anything else (RCON, query, Geyser, Dynmap) needs a secondary allocation added in the Network tab.
Tasks
- RCON →
references/rcon-setup.md. Key point: add a secondary allocation first, then setenable-rcon=true/rcon.port=<that port>/ a strongrcon.passwordinserver.properties. Confirm with the user before enabling RCON, and never expose the port publicly. - Memory / OOM → if the container dies with "Cannot allocate memory" or the cgroup OOM-kills
it: the JVM heap +
-XX:+AlwaysPreTouchis claiming the full container limit at boot. SetXmxbelow the panel's allocated memory (leave ~1–1.5 GB / 10–15% headroom for JVM native memory) and/or dropAlwaysPreTouch. The panel{{SERVER_MEMORY}}value is the container limit, not a safe heap size. (Seeperformance-tuningfor the full flag discussion.) - Backups →
references/backup-strategies.md. Panel/Wings backups archive the live filesystem and are NOT atomic — quiesce writes (/save-offthen/save-all flushvia console or the/commandAPI) before taking one, or stop the server. - Editing config → edit while stopped (a running server can overwrite files on shutdown), then start. Use SFTP for large/bulk file transfers the web file manager handles poorly.
- Automation → the client API (below) for scripted file edits, commands, and power actions.
What ships with it
3 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.
- 5d ago First seen · 70 lines · 171 tokens per session scan A 4b6c38846eb8
pterodactyl-ops is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 5d ago), licensed MIT. It adds 171 tokens to every session and 1,074 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
apple-container
Build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS using Apple's open-source container CLI, no Docker daemon required.
manage-mounts
Configure which host directories agent containers can access. View, add, or remove mount allowlist entries. Triggers on "mounts", "mount allowlist", "agent access to directories", "container mounts".
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
game-ui-ux
Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected…
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…
ai-behavior-trees-utility-ai
Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system (response curves — linear, exponential, sigmoid, quadratic — considerations, and action evaluators), plus hybrid BT-drives-Utility agents. Use when implementing a…