world-model-ideation

world-model-ideation is a skill for Claude Code from happyhappy-jun/writing-driven-autoresearch. It costs 85 tokens per session (1,206 once invoked), scanned A, original, Apache-2.0.

A research-planning guide for testing ideas about world models—systems that learn how the world changes and how actions affect it.

In plain words
What is it for?
Use it to rank world-model research directions, define measurable predictions and interventions, choose baselines, and prepare a compact experiment brief.
Why use it?
It turns a vague demo idea into a research question that can be tested and compared fairly. It also helps reject ideas that cannot support meaningful action-based tests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ralphthon-icml plugin — 8 skills shipped together

Good fit Use it to rank world-model research directions, define measurable predictions and interventions, choose baselines, and prepare a compact experiment brief.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation
Install

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.

Any agent
npx skills add happyhappy-jun/writing-driven-autoresearch --skill world-model-ideation
Clone the repo
git clone --depth 1 https://github.com/happyhappy-jun/writing-driven-autoresearch

Made for: Claude Code.

Or install ralphthon-icml, the plugin that ships this one along with the rest of its 8 skills.

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.

agentmods badge for world-model-ideation

README.md
[![agentmods](https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation/github.svg)](https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation)
Your own site
<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation/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.

agentmods 80×15 button for world-model-ideation

Your own site · 80×15
<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/world-model-ideation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,206 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01206
Opus 5 $0.00043 $0.00603
Sonnet 5 $0.00017 $0.00241
Haiku 4.5 $0.00009 $0.00121

Measured 11d ago against content hash 9ad67443a5a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

world-model-ideation 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 11d 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.

ralphthon-icml/skills/world-model-ideation/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

World Model Ideation

Overview

Turn a demo concept into a research question, fair comparison, and smallest useful experiment before designing a polished interface. This skill selects and frames the work; auto-research owns evidence management, execution, and submission artifacts.

Read the evaluation patterns and claim guardrails before ranking candidates. Copy the research-spec template into the participant workspace as the handoff to auto-research.

Preflight

Identify the environment, observations, actions or interventions, future target, available data and time, intended Track, and external claims requiring public verification.

If action is unavailable, unobserved, or cannot plausibly change the target, do not call the work action-conditioned or counterfactual. Reframe it as forecasting or representation learning, or reject it as a world-model candidate.

Workflow

Candidate Gate

Generate three research questions, not product slogans. Score each from 0–2 for world-model necessity, intervention identifiability, falsifiability, fair-baseline feasibility, and deadline fit using the reference rubric. Reject a candidate with no observable state/action/target path, no disconfirming outcome, or no fair baseline.

Select the highest-scoring viable candidate and state why the others lost. Do not use a visual simulation, generic predictor, or prompt-only demo as proof of a world model.

Research Handoff

Choose one research pattern from the reference: action-conditioned state prediction, planning with a learned model, representation for downstream control, or counterfactual intervention modeling. Complete research-spec.md with:

  1. state, observation, action/intervention, target horizon, and why the question needs a world model;
  2. falsifiable hypothesis, named baseline, primary evaluation metric, success threshold, and claim limit;
  3. smallest end-to-end comparison, split or sampling rule, and one appropriate smoke test;
  4. likely failure modes and the intended General Track 1, Training Track 1, or Track 2 route.

Read the full file on GitHub · 85 lines

Files

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.

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.

  1. 11d ago First seen · 85 lines · 85 tokens per session scan A 9ad67443a5a1

Subscribe to this mod's changes

world-model-ideation is a skill published in the GitHub repository happyhappy-jun/writing-driven-autoresearch (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,206 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens