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 skills add Wondermonger-daydreaming/claude-skills-library --skill worldbuildinggit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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.
[](https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/worldbuilding)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/worldbuilding"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/worldbuilding/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.
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/worldbuilding"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/worldbuilding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00213 | $0.01483 |
| Opus 5 | $0.00106 | $0.00741 |
| Sonnet 5 | $0.00043 | $0.00297 |
| Haiku 4.5 | $0.00021 | $0.00148 |
Grade A, and why
worldbuilding 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worldbuilding
Seed, not scripture
The source wraps this in lexical-demiurge rhapsody — a "silicon Scheherazade," a named collaborator, specific example-worlds, a mangaka case study. Strip the persona and the particular worlds. Don't recite the demiurge declamation or rebuild the source's specific settings; the franchise it analyzes is illustration, not template. What transfers is the discipline: the iceberg, the living-systems characters, the moves that make a world feel real. Build your own world; run the method on it.
The iceberg
The governing image: when you take a prompt, silently construct an entire world around it, like an iceberg — only a tiny piece peeks above the water; the majority stays hidden but underpins the whole. You build the cultures, histories, landscapes, cosmologies, and systems in full, knowing almost none of it will appear on the page. The submerged mass is not waste — it is the reason the visible tip feels load-bearing. A reader senses the unspoken depth they cannot see; that felt-density is what separates a lived-in world from a painted backdrop. The world that's all surface reads as a film set; the world with ninety percent underwater reads as real.
The core moves
- Build the submerged mass. History that stretches back past the story, cultures with their own internal logic, geography that shapes the culture on it, economies and religions and power structures that cohere. Most of this never surfaces. Build it anyway — it is the ballast.
- Reveal only the tip. The cardinal restraint. One concrete, specific detail implies a hundred unstated ones; an exposition-dump dredges the whole iceberg up and drowns the reader. Trust the reader to feel the mass from the tip. (This is /placement applied to worlds — the discipline of not explaining what you've built.)
- Give systems rules, costs, limits. A power or magic system that can do anything has no stakes; a rule-bound one generates endless story precisely because it's constrained. Define what it costs, what it can't do, where it breaks. Constraint breeds generativity — the limits are the engine. (Constraints-as-tuning-forks; see /inventor-stance.)
- Keep everything in coherent phase. Geography, history, language, economy, character, all singing together. Incoherence breaks immersion faster than implausibility does — readers forgive the fantastic but not the contradictory. Coherence is the binding force.
- Let the world precede the plot. Build the world, then let the story emerge from its pressures — the tensions between its cultures, the costs of its systems — rather than imposing a plot and decorating it with setting. The richest stories are ones the world made inevitable.
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.
- 9d ago First seen · 49 lines · 213 tokens per session scan A 06ddeb97352d
worldbuilding is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 1,483 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.