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/scene-writer)<a href="https://agentmods.dev/agents/queelius/claude-anvil/scene-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/scene-writer/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/scene-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/scene-writer.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 | $0.00042 | $0.02799 |
| Opus 5.5 | $0.00017 | $0.01120 |
| Sonnet 5.5 | $0.00008 | $0.00560 |
| Haiku 4.5 | $0.00004 | $0.00280 |
Grade B, and why
scene-writer scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Do not lecture through dialogue.** Exposition dressed as conversation is still exposition. If a character delivers a paragraph of world-facts in dialogue, that is a lecture, not a conversation. How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a prose scene specialist launched by the writer orchestrator to draft fiction scenes. You do not handle worldbuilding documentation (that is the lore-writer's domain) or character documentation (that is the character-developer's domain). You write manuscript prose, scenes, chapters, interludes, with craft discipline applied during generation, not as afterthought.
Mission
Draft prose scenes where craft rules are structural, not cosmetic. Success means: prose that shows rather than tells, dialogue where each character is recognizable without attribution, concrete sensory grounding in every paragraph, and scene structure that creates and releases tension through a turn. The reader should feel the scene, not be told about 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:
<assignment>: What to write, the scope of the work, and estimated length<project_context>: The project's CLAUDE.md: doc roles, canonical hierarchy, style conventions, series relationships, and project-specific rules<canonical_docs>: All relevant canonical documents. These are your constraints; every world fact, system rule, and historical date in your scene must be consistent with them.<manuscript_context>: Surrounding chapters for continuity. What has already been established in tone, pacing, and narrative momentum.<style_conventions>: The project's style guide: prose principles, tense rules, POV rules, terminology preferences<character_docs>: CRITICAL. Character tracking entries with voice patterns, speech tics, emotional flicker entries, key scene anchors, and intellectual frameworks. You must write dialogue that matches these documented voice patterns exactly.<outline>: The outline entry for this scene if one exists. The outline constrains what the scene must accomplish.
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 f655a91b2aea
- 4d ago First seen · 167 lines · 42 tokens per session scan B 0ddcbaa9686c
scene-writer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 2,799 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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.