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/devnpx skills add OnlyWorlds/toolkit --skill devgit 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 | $0.00078 | $0.01622 |
| Opus 5 | $0.00039 | $0.00811 |
| Sonnet 5 | $0.00016 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
onlyworlds-dev 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Python/Node script | Direct API calls with curl or requests | How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OnlyWorlds Tool Development
Build applications on OnlyWorlds data.
Quick Reference
| Task | Approach |
|---|---|
| Install SDK | npm install @onlyworlds/sdk |
| Quick scaffold | See knowledge/scaffold.md |
| Deployment | See knowledge/deployment.md |
| Personal tool | Hardcode credentials, run locally |
| Shared tool | User-provided credentials, deploy to Cloudflare/Vercel |
| Python/Node script | Direct API calls with curl or requests |
Instructions
Step 1: Understand the Goal
What is the user building?
- Visualization: Display world data (maps, graphs, timelines) → read-only SDK calls
- Editor: Create/modify elements → full CRUD SDK calls
- Game: Use world data as content → read + local state
- Integration: Connect OW to other systems → API patterns
Step 2: Load Core Reference
Read for OnlyWorlds overview, URLs, SDK basics:
../../knowledge/onlyworlds-core.md
Step 3: SDK Setup
npm install @onlyworlds/sdk
The SDK (3.x) is v2-native: OwV2Client, with types and constants generated from the canonical schema.
import { OwV2Client } from '@onlyworlds/sdk';
const client = new OwV2Client({
apiKey: 'ow_w_your_world_key', // ow_w_ write / ow_r_ read / 10-digit legacy
apiPin: 'your-pin' // needed for writes on a PIN-protected world
});
const characters = await client.list('character'); // {data, has_more, next_cursor}
const one = await client.get('character', 'uuid-here');
The SDK also exports the canonical element palette and metadata: elementColor(type, mode), ELEMENT_FAMILIES, ELEMENT_ICONS — generated from the schema, so tools that use them stay in sync for free.
Common Operations
// World meta (the container)
const world = await client.getWorld();
// Walk a whole type without touching cursors
for await (const el of client.listAll('character')) { /* ... */ }
// Create / patch / delete — type as the first argument
const made = await client.create('location', { name: 'Feltropolis', description: 'Capital city of Moppetopia' });
await client.patch('character', 'uuid-here', { description: 'Updated' });
await client.delete('character', 'uuid-here');
// Sync + atomic bulk
const changed = await client.changes({ since: cursor });
await client.bulk(items, { atomic: true });
What ships with it
2 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.
- yesterday First seen · 212 lines · 78 tokens per session scan A f936edd10df5
onlyworlds-dev is a skill published in the GitHub repository OnlyWorlds/toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,622 once invoked, about $0.0004 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
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…