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.
git clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/plugins/queelius/claude-anvil/worldsmith)<a href="https://agentmods.dev/plugins/queelius/claude-anvil/worldsmith"><img src="https://agentmods.dev/badge/plugins/queelius/claude-anvil/worldsmith/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/plugins/queelius/claude-anvil/worldsmith"><img src="https://agentmods.dev/badge/plugins/queelius/claude-anvil/worldsmith.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
worldsmith 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.
What it actually says
{
"name": "worldsmith",
"version": "0.16.0",
"description": "Documentation-first worldbuilding methodology and prose craft guardrails for fiction projects. The Silmarillion approach: docs ARE the world, story text derives from them.",
"author": {
"name": "Alexander Towell",
"email": "[email protected]",
"url": "https://metafunctor.com"
},
"repository": "https://github.com/queelius/claude-anvil",
"license": "MIT",
"keywords": [
"fiction",
"worldbuilding",
"editorial",
"writing",
"lore",
"consistency",
"prose-craft"
]
}
What it installs
The manifest is a name and a version. 2 skills, 2 commands, 7 agents travel with it, and installing the plugin installs all of them — 472 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill worldsmith-methodology A 56 tokens
- Skill prose-craft A 79 tokens
- Command init-world A 9 tokens
- Command change A 18 tokens
- Agent structure-auditor A 42 tokens
- Agent character-developer A 41 tokens
- Agent craft-auditor A 52 tokens
- Agent voice-auditor A 43 tokens
- Agent consistency-auditor A 45 tokens
- Agent lore-writer A 45 tokens
- Agent scene-writer B 42 tokens
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 Changed 8946ddc0bae0
- 3d ago First seen · 22 lines scan A 695cf319cdfc
worldsmith is a plugin published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-19.
Other plugins, from other repositories
platform-guardrails
Enforcing hooks for platform-skills, separate from the guidance plugin because hooks run for everyone who enables them: self-improve lifecycle capture (SessionStart, SessionEnd, PostToolUseFailure, PreCompact) and the ai-governance policy gate (PreToolUse/PostToolUse, active only in projects that commit a…
frontend-design
Production-grade frontend design skill that avoids AI slop — specific rules for typography, color (OKLCH), layout, motion, interaction, and UX writing.
dotnet-architect
Backend layer of the cloudstack reference architecture — scaffolds and enforces hexagonal .NET services: CQRS commands and queries, domain entities, EF Core migrations, tests, and architecture review.
conjure
Build Claude Code skills, agents, hooks, and MCP servers from plain-language descriptions. Generate, validate, and ship plugins without writing boilerplate.
zAI-Skills marketplace
Development marketplace for AI-Toolkit, consulting-toolkit, real-estate-investment, career-coach, and plugin-forge plugins.
diogenes
Senior-reviewer audit for AI-slop and LLM-generation tells in written content. The audit skill forks into the diogenes subagent (Sonnet, read-only tools plus WebFetch) and returns a verdict, attributable findings, authenticity improvements, and a human rewrite.