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/onlyworlds-startnpx skills add OnlyWorlds/toolkit --skill onlyworlds-startgit 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 | $0.00095 | $0.01199 |
| Opus 5 | $0.00048 | $0.00600 |
| Sonnet 5 | $0.00019 | $0.00240 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
onlyworlds-start 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 2d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OnlyWorlds Start
Route users to the right capability. The toolkit is a general worldbuilding companion: it works on whatever the user has (notes, manuscripts, folders, nothing yet), with no account required. OnlyWorlds is the shared language underneath -- and the optional power layer (cloud world, API, app ecosystem) when they want it.
Quick Reference
| User Says | Route To |
|---|---|
| "I have notes/text/docs to structure" | project-setup (only if they already have an OnlyWorlds world) → parsing |
| "I want to organize/manage my world" | project-setup → api |
| "I'm designing a magic system / factions / complex thing" | modeling |
| "I want to build a tool/game with world data" | dev |
| "I need to sync/upload/fetch data" | api |
| "I want to understand/feel/read a world" | survey |
| "Give me a creative brief of my world" | survey |
| "What fields/types exist?" | schema |
| "The schema should have X / propose a change" | council |
| "Are there motions about X?" | council |
| "My elements aren't connected well" | link |
| "I have an Atlas world folder / world files on disk" | survey or link (both read folders directly -- no credentials) |
| "I'm building an AI agent / need world-state or memory for my AI" | Read knowledge/ai-builders.md; route to dev or the MCP connect line |
| "Find orphaned elements / enrich links" | link |
| "What is OnlyWorlds?" | Explain below, then ask what they're working on |
| "Which tool should I use / what exists?" | Read knowledge/ecosystem.md, route from its table |
| "How do Atlas / Obsidian / MCP fit together?" | Read knowledge/ecosystem.md |
| "I found a bug / want a feature in a tool" | Point to onlyworlds.com/feedback |
| "I have an idea for a world" | Discuss, then modeling or schema |
Process
1. Discover User Situation
Ask: "What brings you here?"
Listen for signals from the routing table above. Don't interrogate — one open question usually reveals the path.
Do not assume the user is a developer. Many users are writers, GMs, hobbyists. Meet them where they are.
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.
- 2d ago First seen · 89 lines · 95 tokens per session scan A e0f1a61c0ee1
onlyworlds-start is a skill published in the GitHub repository OnlyWorlds/toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,199 once invoked, about $0.0005 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
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
cap_llm_inspect_image
How to inspect a local image with inspectimage.