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/schemanpx skills add OnlyWorlds/toolkit --skill schemagit 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 | $0.00066 | $0.01241 |
| Opus 5 | $0.00033 | $0.00620 |
| Sonnet 5 | $0.00013 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
onlyworlds-schema 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OnlyWorlds Schema Reference
Quick Reference
| Question | Answer |
|---|---|
| "What fields does X have?" | Read ../../knowledge/schema-reference.md, find the element section, and present the fields directly to the user |
| "Does X.field exist?" | Grep schema-reference.md — no match = doesn't exist |
| "Object vs Construct?" | Specific instance vs type/concept. Can you touch it? Object. |
| "Character vs Creature?" | Narrative agency → Character. Biological focus → Creature. |
| "Event vs Narrative?" | What happened (factual) → Event. How it's told → Narrative. |
| "Trait vs Ability?" | Inherent quality → Trait. Learnable/usable power → Ability. |
| "Institution vs Collective?" | Formal hierarchy → Institution. Named group of people → Collective. |
| "Location vs Zone?" | Physical place → Location. Abstract territory/boundary → Zone. |
| "How to link X to Y?" | Check schema-reference.md for which element has the link field |
Field Lookup
For complete field reference, read:
../../knowledge/schema-reference.md
Every field for all 22 element types, organized by element.
When the user asks "what fields does X have?", read the file and present the fields directly in your response. Do not just tell the user to read the file — extract and show them the answer.
Base Fields (All Elements)
Every element has:
name(text, required)description(text)supertype(text)subtype(text)
Link Field Patterns
- Single link: field name, links to one element
- Multi link: field name, links to array of elements
- API writes: bare field names holding UUIDs on the modern v2 dialect (
location,species); the legacy v1 dialect suffixes writes with_id/_ids— see the api skill
Number Ranges
- Personality scores: 0-100 (Character: charisma, courage, etc.)
- Trait modifiers: -100 to 100
- Relation intensity: 0-100
Type Disambiguation
Object vs Construct
Object: Specific physical instance. You can point at it.
- The Vorpal Blade, USS Fuzzball, The Crown of Feltropolis
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 · 135 lines · 66 tokens per session scan A 5b07ab1ae77b
onlyworlds-schema is a skill published in the GitHub repository OnlyWorlds/toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,241 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…