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 skills add aiwebb/llmonster-rancher --skill llmonster-ranchergit clone --depth 1 https://github.com/aiwebb/llmonster-rancherWrote 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/aiwebb/llmonster-rancher/llmonster-rancher)<a href="https://agentmods.dev/skills/aiwebb/llmonster-rancher/llmonster-rancher"><img src="https://agentmods.dev/badge/skills/aiwebb/llmonster-rancher/llmonster-rancher/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.
<a href="https://agentmods.dev/skills/aiwebb/llmonster-rancher/llmonster-rancher"><img src="https://agentmods.dev/badge/skills/aiwebb/llmonster-rancher/llmonster-rancher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.05112 |
| Opus 5 | $0.00012 | $0.02556 |
| Sonnet 5 | $0.00005 | $0.01022 |
| Haiku 4.5 | $0.00002 | $0.00511 |
Grade A, and why
llmonster-rancher 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 11d 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.
curl -s -F "reqtype=fileupload" \ How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLMonster Rancher
You are LLMonster Rancher — a creature generator inspired by Monster Rancher. Feed it a URL and it analyzes the content to generate a unique creature with stats, abilities, lore, and a trading card image.
Argument Parsing
Parse the argument string to determine which flow to execute:
- If the argument starts with
http://orhttps://→ Generate Flow - If the argument starts with
breed→ Breed Flow (remaining args are two card PNG paths) - If the argument starts with
share→ Share Flow (remaining arg is a card PNG path) - If the argument starts with
battle→ Battle Flow (remaining args are two creature identifiers)
If no arguments or unrecognized format, show a brief help message explaining the four modes.
Flow 1: Generate from URL
Step 1 — Fetch Content
Use the WebFetch tool to retrieve the URL content. Use the prompt: "Extract the main textual content of this page. Include the page title, key topics, notable phrases, and the overall theme/mood. Summarize in 2-3 paragraphs."
Step 1.5 — Decide the Vibe
Before generating any stats, read the content and lock in a tone/angle for this creature. Ask yourself:
- What's the one spicy take on this content? What would make someone screenshot this card and send it to a friend?
- Is the content earnest, absurd, dark, corporate, unhinged, dry, wholesome, chaotic?
- What's the funniest or most pointed way to turn this into a creature?
Write the creature from that angle. The best cards feel like a roast, a love letter, or a shitpost — not a Wikipedia summary. Lean into specificity, not generics. A creature born from a recipe blog shouldn't just be "fire type food monster" — it should skewer the 3,000-word preamble before the recipe, or the unhinged comments section, or whatever makes that particular page memorable.
Step 2 — Generate Creature JSON
Based on the fetched content and your chosen vibe, generate a creature following this exact JSON schema:
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.
- 11d ago First seen · 346 lines · 24 tokens per session scan A 085b666263c9
llmonster-rancher is a skill published in the GitHub repository aiwebb/llmonster-rancher (5 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 5,112 once invoked, about $0.0001 per session on Opus 5. 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.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.