crucible-writer

crucible-writer is a skill for Claude Code from forsonny/The-Crucible-Writing-System-For-Claude. It costs 114 tokens per session (3,325 once invoked), scanned A, original, MIT.

A first-draft writing assistant for novels planned with the Crucible Structure. It turns chapter outlines into scenes while tracking writing style, plot details, and story continuity.

In plain words
What is it for?
It is for drafting scenes, matching an author's voice, maintaining a story bible, checking continuity, and preventing details that are not supported by the outline.
Why use it?
It reduces the risk of losing important facts or inventing events when an AI works on a long manuscript in smaller sections.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the The-Crucible-Writing-System-For-Claude plugin — 4 skills, 8 commands, 5 agents shipped together

Good fit It is for drafting scenes, matching an author's voice, maintaining a story bible, checking continuity, and preventing details that are not supported by the outline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forsonny/the-crucible-writing-system-for-claude/crucible-writer
Install

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.

Any agent
npx skills add forsonny/The-Crucible-Writing-System-For-Claude --skill crucible-writer
Clone the repo
git clone --depth 1 https://github.com/forsonny/The-Crucible-Writing-System-For-Claude

Made for: Claude Code.

Or install The-Crucible-Writing-System-For-Claude, the plugin that ships this one along with the rest of its 4 skills, 8 commands, 5 agents.

Wrote 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.

agentmods badge for crucible-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/forsonny/the-crucible-writing-system-for-claude/crucible-writer/github.svg)](https://agentmods.dev/skills/forsonny/the-crucible-writing-system-for-claude/crucible-writer)
Your own site
<a href="https://agentmods.dev/skills/forsonny/the-crucible-writing-system-for-claude/crucible-writer"><img src="https://agentmods.dev/badge/skills/forsonny/the-crucible-writing-system-for-claude/crucible-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.

agentmods 80×15 button for crucible-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/forsonny/the-crucible-writing-system-for-claude/crucible-writer"><img src="https://agentmods.dev/badge/skills/forsonny/the-crucible-writing-system-for-claude/crucible-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.03325
Opus 5 $0.00057 $0.01663
Sonnet 5 $0.00023 $0.00665
Haiku 4.5 $0.00011 $0.00332

Measured 12d ago against content hash 99ee32cd1a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

crucible-writer 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 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/compile_manuscript.py, scripts/init_draft.py, scripts/load_draft.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/crucible-writer/SKILL.md · 501 lines

How it starts

The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crucible Writer

Transform Crucible outlines into first-draft prose while maintaining style consistency, plot fidelity, and narrative quality.

Critical Principles

Context Window is Limited. Never try to hold the entire novel in context. Load only what's needed for the current scene. Save constantly.

The Outline is Law. Never invent plot points, characters, or events not in the outline. If something seems missing, ASK the author—don't improvise.

Style is Sacred. Capture the author's voice early. Maintain it relentlessly. When in doubt, match the sample.

Save Everything. After every scene, update the story bible and save the draft. Progress must survive session breaks.

Before Starting

Read these references based on the writing phase:

  • references/context-management.md — Critical: Managing limited AI context
  • references/writing-process.md — Scene-by-scene drafting approach
  • references/style-capture.md — Learning and maintaining author voice
  • references/anti-hallucination.md — Verification protocols
  • references/prose-craft.md — Genre conventions and techniques

Questioning Rules

  1. ALWAYS use AskUserQuestion tool for all user questions (provides interactive UI)
  2. Max 4 options per question (tool limit) + "Other" is automatic
  3. Max 4 questions per AskUserQuestion call
  4. Reference user's story elements by name (characters, places, etc.)
  5. Save state after every scene and chapter

CRITICAL: Use the AskUserQuestion tool, NOT plain text A/B/C options.

Required Inputs

Before writing can begin, gather:

  1. Complete Chapter Outline (required) — The crucible-outliner output
  2. Crucible Summary Card (required) — Quick reference for theme, characters
  3. Style Sample (required) — 2,000+ words of author's existing prose OR detailed style preferences
  4. Constellation Bible (as needed) — Character details
  5. World Forge (as needed) — Setting details

Workflow Overview

Phase 1: PROJECT SETUP
         ↓
Phase 2: STYLE CAPTURE
         ↓
Phase 3: CHAPTER WRITING (repeat for each chapter)
         │
         ├─→ Load Context
         ├─→ Write Scene-by-Scene  
         ├─→ Verify Against Outline
         ├─→ Update Story Bible
         └─→ Save Progress
         ↓
Phase 4: COMPILE MANUSCRIPT

Read the full file on GitHub · 501 lines

Changes

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.

  1. 12d ago First seen · 501 lines · 114 tokens per session scan A 99ee32cd1a9f

Subscribe to this mod's changes

crucible-writer is a skill published in the GitHub repository forsonny/The-Crucible-Writing-System-For-Claude (60 stars, last pushed 8mo ago), licensed MIT. It adds 114 tokens to every session and 3,325 once invoked, about $0.0006 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens