Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add queelius/claude-anvil/plugin install worldsmithWrote 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/commands/queelius/claude-anvil/init-world)<a href="https://agentmods.dev/commands/queelius/claude-anvil/init-world"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/init-world/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/commands/queelius/claude-anvil/init-world"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/init-world.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 | $0.00009 | $0.01357 |
| Opus 5.5 | $0.00004 | $0.00543 |
| Sonnet 5.5 | $0.00002 | $0.00271 |
| Haiku 4.5 | $0.00001 | $0.00136 |
Grade A, and why
init-world 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.
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.
/worldsmith:init-world
Assess the project state and set up (or verify) a worldbuilding documentation ecosystem. Adapt behavior to what already exists. Do not impose structure on a project that already has one.
If $ARGUMENTS is provided, use it as the project name or description rather than asking.
Mode Detection
Read the current directory. Determine which mode applies:
- CLAUDE.md exists and describes a doc structure (has a document roles table or references worldbuilding docs): go to Verify Mode.
- Docs exist but CLAUDE.md is absent or unaware of them (a
docs/orlore/directory with markdown files, but CLAUDE.md either missing or lacking doc role awareness): go to Adopt Mode. - Nothing exists (no docs directory, no worldbuilding markdown files): go to Scaffold Mode.
Verify Mode
The project is already set up. Do not overwrite or "improve" anything unless asked.
- If
.worldsmith/does not exist, create it (mkdir -p .worldsmith). This activates worldsmith hooks for this project. - Read the project's CLAUDE.md. Parse the document roles table.
- For each role listed, confirm the referenced file exists and is non-empty.
- Check for missing roles: are there standard roles (timeline, lore, systems, characters, style, outline, themes, backlog, feedback) that the project might benefit from but doesn't have?
- Check for exploratory sections that might be ready for promotion.
- Report findings: confirmed files, missing files, incomplete sections, suggested additions.
- If CLAUDE.md references related projects (series/shared universe), confirm those paths are accessible.
Adopt Mode
Existing docs need a CLAUDE.md to make them work with the worldsmith methodology.
- Read every markdown file in the docs (or lore) directory. Read any existing CLAUDE.md.
- For each file, determine which worldsmith role it serves: timeline authority, lore/history, systems/mechanics, character tracking, style conventions, outline/diagnostic hub, editorial backlog, themes/anti-cliche, feedback. A single file may serve multiple roles.
- Present the mapping to the user. Ask for corrections.
- Look for manuscript files (chapters/, manuscript/, or similar). Note what exists.
- If multiple manuscript-like directories exist (e.g., both
chapters/andstories/), ask whether this is a multi-work project. If yes, generate.worldsmith/project.yamlwith the detected works. - Draft CLAUDE.md content following the structure described in
${CLAUDE_PLUGIN_ROOT}/skills/worldsmith-methodology/references/doc-structure-guide.md(see the "CLAUDE.md for Worldbuilding Projects" section): project overview, document roles table, consistency rules, world structure summary, character conventions, propagation awareness notes. - Present the draft. Ask the user before writing or modifying anything. Create
.worldsmith/(mkdir -p .worldsmith) when the user approves. - If the user has an existing CLAUDE.md, merge the worldsmith doc-awareness content into it rather than replacing it.
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 cd38c751c4a7
- 4d ago First seen · 85 lines · 9 tokens per session scan A 20239a547a77
init-world is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,357 once invoked, about $0.0000 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 2026-10-19.
Other commands, from other repositories
ia-verify
Run pre-PR verification chain: build, types, lint, tests, security scan, diff review.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
sm-swab
Run slop-mop's iterative development loop for this repository.
release
Generate changelog, bump version, and create git tag.
issue-tree
Decompose a business problem into a MECE issue tree.