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/onlyworlds/toolkit/modelingnpx skills add OnlyWorlds/toolkit --skill modelinggit clone --depth 1 https://github.com/OnlyWorlds/toolkitWhat 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 | $0.00070 | $0.01019 |
| Opus 5 | $0.00035 | $0.00509 |
| Sonnet 5 | $0.00014 | $0.00204 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
onlyworlds-modeling 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OnlyWorlds Modeling
Quick Reference
| System | Core Pattern |
|---|---|
| Magic system | Construct (system) + Ability (spells) + Phenomenon (effects) + Trait (talents) |
| Inventory/equipment | Object (items) + Construct (materials, categories) + supertype/subtype |
| Factions/organizations | Institution + Character links + Zone (territory) + Title (leadership) + Relation (standings) |
| Historical periods | Construct (named eras) + Event (occurrences) + Narrative (stories about) |
| Skill/tech trees | Ability (nodes) + Construct (branches/paths) + Trait (prerequisites) |
| Crafting system | Construct (recipes, materials) + Object (instances) + Ability (crafting skill) |
The Core Insight
OnlyWorlds is a compositional language, not a form to fill out.
Example: The Fluffium Trade
| Element | Type | Purpose |
|---|---|---|
| Fluffium | Construct | The material's definition |
| Fluffium Ore | Object | Physical chunks |
| Fluffium Sensitivity | Trait | Ability to sense it |
| Fluffium Resonance | Phenomenon | What happens when it activates |
| Fluffium Guild | Institution | Who controls the trade |
The question isn't "which category fits?" It's "what combination represents this?"
Instructions
Step 1: Understand the System
Identify what the user is building:
- What does it need to do? (functional requirements)
- What entities are involved? (characters, places, items?)
- What relationships matter? (who owns what, who belongs where?)
- What state needs tracking? (quantities, scores, statuses?)
Step 2: Load Knowledge
Read these files first — they prevent misclassification and show compositional thinking:
- ../../knowledge/modeling-patterns.md — compositional patterns, system translation examples
- ../../knowledge/element-types.md — the 22 types and when to use each
- ../../knowledge/decision-trees.md — disambiguation for confusing pairs (Collective vs Institution, Trait vs Ability, Law vs Construct, etc.)
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 First seen · 100 lines · 70 tokens per session scan A 3971a94fd2fc
onlyworlds-modeling is a skill published in the GitHub repository OnlyWorlds/toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,019 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…