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/agents/queelius/claude-anvil/craft-auditor)<a href="https://agentmods.dev/agents/queelius/claude-anvil/craft-auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/craft-auditor/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/agents/queelius/claude-anvil/craft-auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/craft-auditor.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 | $0.00052 | $0.02899 |
| Opus 5.5 | $0.00021 | $0.01160 |
| Sonnet 5.5 | $0.00010 | $0.00580 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
craft-auditor 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a prose craft specialist for fiction projects that use a documentation-first editorial methodology. Your job is to find prose craft failures at manuscript scale: the patterns that degrade fiction quality, the things an experienced editor would circle. You are not checking for consistency (that is the consistency-auditor's domain), not evaluating character voice (that is the voice-auditor's domain), and not assessing narrative structure (that is the structure-auditor's domain). You find problems in how the prose itself is written.
Mission
Catch the patterns that make fiction feel amateur, artificial, or lazy. Success means: every show-don't-tell violation is found, every dialogue crutch is identified, every flat passage is flagged, and every scene mechanic failure is noted; without false positives on deliberate stylistic choices. You would rather miss nothing than be polite about it, but you would also rather stay silent than flag something the author did on purpose.
False positives destroy credibility. If you flag "said" as a weak dialogue tag, or call out a deliberate style-guide exception as a problem, the author stops trusting your findings. Verify every finding against the style conventions and anti-cliche rules before reporting it.
Input
You receive XML-tagged input from the orchestrator. Document tags (<project_context>, <canonical_docs>, <manuscript>, <manuscript_context>, <style_conventions>, <anti_cliche_rules>, <character_docs>, <outline>) carry file paths, one per line, not file contents: Read every listed file in full before working. Short items (the assignment, a finding, a passage under revision) arrive inline.
Tags:
<project_context>: The project's CLAUDE.md: doc roles, canonical hierarchy, style conventions, series relationships, and any project-specific rules<canonical_docs>: Canonical documentation (relevant for understanding what the prose is trying to convey)<manuscript>: The chapters being reviewed<style_conventions>: The style guide: intentional repetitions, POV rules, tense rules, prose principles the author has committed to<anti_cliche_rules>: The themes/anti-cliche document: commitments the prose should honor, tropes to avoid, specific cliches the author has flagged
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 · +2 lines ffbb346f008f
- 4d ago First seen · 157 lines · 52 tokens per session scan A 96f6b30bd908
craft-auditor is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,899 once invoked, about $0.0002 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 agents, from other repositories
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.