A procedure for adding a playable world, called a realm, to the OpenAgents website. It covers cloning the repository, writing a small compiled module, checking it locally in a browser, and opening a pull request.

Use it to create or remix a Verse game or world, choose its URL and module names, build it for WebAssembly, and prepare the site change for review.

It gives a repeatable path through the repository's specific files, build tools, naming rules, and local checks. This avoids changing unrelated parts of the site while adding a realm.

verse-realm — Skill for Claude Code and Codex by OpenAgentsInc

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/OpenAgentsInc/openagents

agentmods

npx agentmods add skills/openagentsinc/openagents/verse

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/openagentsinc/openagents/verse/github.svg)](https://agentmods.dev/skills/openagentsinc/openagents/verse)

Your own site

<a href="https://agentmods.dev/skills/openagentsinc/openagents/verse"><img src="https://agentmods.dev/badge/skills/openagentsinc/openagents/verse/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/openagentsinc/openagents/verse"><img src="https://agentmods.dev/badge/skills/openagentsinc/openagents/verse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,037 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.00062	$0.03037
Opus 5.5	$0.00025	$0.01215
Sonnet 5.5	$0.00012	$0.00607
Haiku 4.5	$0.00006	$0.00304

Measured 3d ago against content hash 2d84f79c20ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verse-realm 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 3d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (benchmarks/loop.py, benchmarks/run.py, benchmarks/tails.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

verse/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Make a Verse realm

A realm is a page at https://openagents.com/realms/<slug> that runs one Coax module, compiled to WebAssembly and drawn with WebGPU. You add four things and one table row; a generator writes the page. Nothing else in the site changes. The full contract is docs/verse/realm-host.md; this file is the short path.

1. Get the code

git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git
cd openagents

One level of history is all you need. Tools (macOS: Homebrew; Linux: your package manager): a C11/C++20 compiler (clang), llvm and lld with wasi-libc (for wasm32), bun, python3, and Chrome or Chromium for a headless look.

Build the Coax compiler once (a few minutes; it lands in coax/bin/coax):

coax/build.sh

2. Pick a slug and a module name

slug: lowercase words with dashes, e.g. lantern-maze (the URL and the save slot).
module: one short lowercase word, e.g. lanternmaze (the file names).
Read apps/openagents-web/realms.json and pick a slug, module, world id and orbit nobody uses.

3. Write the module (three files in `apps/openagents-web/`)

Start from the template: verse/realm-template/ is a whole small realm (Star Catcher, about 500 lines of Coax with five #test checks that play it, no assets) that a fresh agent made from this skill. Copy its files to apps/openagents-web/<module>.coax and <module>-face.c, and its gpu/starcatch.coax, .module and .bindings to apps/openagents-web/gpu/<module>.coax, .module and .bindings; rename starcatch/Starcatch to your module throughout (in the .module too), then make your own game in it. verse/realm-template/row.json is its realms.json row and index.md its page text. For bigger ideas, read Hold the Stair (stair.coax, a tower defense with buttons and phone taps) or Orbit League (orbitleague.coax, an arcade game with two thumbs); their faces also send analytics (analytics-face.h, track_drain), which your realm can leave out.

Read the full file on GitHub · 208 lines

Files

What ships with it

60 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.

Changes

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.

3d ago Changed · +5 lines 2d84f79c20ca
4d ago Changed 9dae3a8ce775
5d ago First seen · 203 lines · 62 tokens per session scan A 7fbc36722f17

Subscribe to this mod's changes

verse-realm is a skill published in the GitHub repository OpenAgentsInc/openagents (460 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 3,037 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-01.

Game development

verse-realm next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verse-realmOpenAgentsInc/openagents	Skill	460	today	Apache-2.0	A	62	Claude Code, Codex
playtest-reportDonchitos/Claude-Code-Game-Studios	Skill	36k	18d ago	MIT	A	20	Claude Code
godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills	Skill	6.9k	9d ago	Apache-2.0	A	95	Claude Code
scenario-unreal-gameplayscenario-labs/skills	Skill	3.2k	yesterday	MIT	A	121	Claude Code
motionOpenDCAI/GameFactory-3A	Skill	1.0k	8d ago	Apache-2.0	A	0	Claude Code, Codex
unity-addressablesBesty0728/Unity-Skills	Skill	1.9k	yesterday	MIT	A	25	Claude Code, Codex
unity-manual-componentBesty0728/Unity-Skills	Skill	1.9k	yesterday	MIT	A	36	Claude Code, Codex