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/linknpx skills add OnlyWorlds/toolkit --skill linkgit 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 | $0.00085 | $0.01434 |
| Opus 5 | $0.00043 | $0.00717 |
| Sonnet 5 | $0.00017 | $0.00287 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
onlyworlds-link 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.
curl -s -X PATCH "https://www.onlyworlds.com/api/v2/{type}/{uuid}" \ How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OnlyWorlds Link
Find and create missing connections between world elements.
Quick Reference
| User Says | Action |
|---|---|
| "Connect my elements" | Full link audit + suggestions |
| "Find orphans" | Identify unlinked elements |
| "Add relations between characters" | Targeted Relation creation |
| "Link my institutions to locations" | Targeted field linking |
| "Audit my world's connections" | Report link density by type |
Instructions
Step 1: Pick the Source
- World folder (no account needed): the user has an Atlas world folder or any OW-shaped folder on disk. Read world.json + every .json under elements//, keyed on internal id (see knowledge/world-folder.md). Applying suggested links = editing the files in place (preserve every field you didn't change, including atlas_/x_ extensions).
- API: check
.ow/config.jsonfirst; if not found, ask user for API-Key and API-Pin.
The analysis (Steps 3+) is identical for both sources.
Step 2: Fetch World Data (API source)
Fetch all narrative element types in parallel:
character, creature, species, family, collective, institution,
location, zone, object, construct, title, ability, trait,
language, law, event, narrative, phenomenon, relation
Skip: map, pin, marker (spatial, not narrative links).
CRITICAL: v2 endpoints (/api/v2/{type}), singular type names, www.onlyworlds.com, exact API-Key/API-Pin headers. v2 lists paginate — follow next_cursor until has_more is false. Link fields come back as flat UUID arrays.
Step 3: Analyze the Web
Build a connection map from existing link fields across all elements:
For each element, check:
- Which link fields are populated? (e.g., Character.location, Character.species, Character.institutions)
- Which link fields are empty but could be filled based on description content?
- Does the element appear in other elements' link fields?
Produce three lists:
Orphans — elements with zero incoming or outgoing links:
| Element | Type | Links Out | Links In | Issue |
|---------|------|-----------|----------|-------|
| The Stale Roll | Object | 0 | 0 | Completely disconnected |
| Deep Drip | Location | 0 | 1 | Only referenced by one Event |
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 · 130 lines · 85 tokens per session scan A bf0c0a3627ef
onlyworlds-link is a skill published in the GitHub repository OnlyWorlds/toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,434 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…