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/change)<a href="https://agentmods.dev/commands/queelius/claude-anvil/change"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/change/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/change"><img src="https://agentmods.dev/badge/commands/queelius/claude-anvil/change.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 | $0.00018 | $0.00853 |
| Opus 5.5 | $0.00007 | $0.00341 |
| Sonnet 5.5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
change 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/worldsmith:change
Apply a change to the worldbuilding project. Determine the appropriate mode from the user's request and the project context. This is not a rigid step-by-step script: understand the rules, then reason about the specific change.
Setup
Read the project's CLAUDE.md first. Parse the document roles table to know which files serve which roles. Understand the canonical hierarchy and any project-specific rules.
Mode Determination
Determine the mode from the user's request:
- Canonical change: The user is fixing, revising, or updating established facts. Correcting a date, updating a character arc after writing a chapter, revising a system rule, reconciling a contradiction.
- Exploratory idea: The user is developing something new that isn't established yet. Drafting mythology, sketching a future plot thread, experimenting with a system extension, noting an idea for later.
- Promotion: The user wants to make an exploratory idea canonical. Moving provisional content to established status.
If the mode is unclear from $ARGUMENTS, ask.
Canonical Change
- Identify the canonical source for the fact being changed. Use the canonical hierarchy: canonical tables > timeline authority > system specs > character entries > outline > manuscript.
- Update the authoritative source doc first.
- Think about what else is affected. Consult the project's CLAUDE.md for the doc structure and propagation notes. Consider: does this change affect character ages, event references, system plausibility, scene logistics, cross-references, or thematic commitments?
- Update affected docs. Update manuscript passages where the old fact appears.
- If project-level facts changed (world structure, canonical tables, character conventions, anti-cliche rules, series relationships), update CLAUDE.md.
- If
.worldsmith/project.yamlexists with multiple works, grep EACH work's manuscript directory for references to the changed fact. A character name change in shared lore affects every work that character appears in.
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 296e1f90c200
- 4d ago First seen · 58 lines · 18 tokens per session scan A dcdaf4de2dac
change is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 853 once invoked, about $0.0001 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.