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.
git clone --depth 1 https://github.com/forsonny/The-Crucible-Writing-System-For-ClaudeWrote 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/forsonny/the-crucible-writing-system-for-claude/crucible-write)<a href="https://agentmods.dev/commands/forsonny/the-crucible-writing-system-for-claude/crucible-write"><img src="https://agentmods.dev/badge/commands/forsonny/the-crucible-writing-system-for-claude/crucible-write/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/forsonny/the-crucible-writing-system-for-claude/crucible-write"><img src="https://agentmods.dev/badge/commands/forsonny/the-crucible-writing-system-for-claude/crucible-write.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 | $0.00023 | $0.00650 |
| Opus 5 | $0.00012 | $0.00325 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
crucible-write 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.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/crucible-write
Write prose drafts scene-by-scene from your Crucible outlines.
Execution Instructions
IMPORTANT: When this command is invoked, you MUST:
- Invoke the
crucible-suite:crucible-writerskill using the Skill tool - The skill will guide you through the complete writing workflow
- Verify outline is complete before writing
- Follow the skill's scene-by-scene protocol
- Track chapter completion and trigger bi-chapter reviews per the skill instructions
- When triggering reviews, use the Task tool with the 5 review agent subagent_types
Usage
/crucible-suite:crucible-write 1- Start writing chapter 1/crucible-suite:crucible-write 5- Jump to chapter 5/crucible-suite:crucible-write continue- Resume from last position
What This Does
- Activates the crucible-writer skill (you must follow its instructions)
- Loads your chapter outline and style profile
- Writes scene-by-scene, matching your voice
- Verifies each scene against the outline
- Updates the story bible after each chapter
- Triggers bi-chapter reviews every 2 chapters
Bi-Chapter Reviews
Every 2 chapters, the system automatically triggers a comprehensive review using 5 specialized agents:
| Agent | Focus |
|---|---|
| voice-checker | Style/voice consistency |
| continuity-checker | Plot/character continuity |
| outline-checker | Outline fidelity |
| timeline-checker | Chronological consistency |
| prose-checker | Craft-level feedback |
Reviews help catch issues before they compound.
Prerequisites
Requires:
- Completed chapter outlines from
/crucible-suite:crucible-outline - Style sample (2,000+ words of your writing) OR style preferences
- Crucible Summary Card (for quick reference)
Word Count Targets
Default targets per scene type:
- Action scenes: 1,500-2,500 words
- Dialogue scenes: 1,000-2,000 words
- Reflection scenes: 800-1,500 words
- Transitional scenes: 500-1,000 words
Anti-Hallucination
The writer follows strict rules:
- Never invents plot points not in the outline
- Never creates characters not in the Constellation Bible
- Flags any [INVENTED] minor details for your review
- Asks you if anything seems missing rather than guessing
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.
- 12d ago First seen · 80 lines · 0 tokens per session scan A ab9f03cdf1bc
crucible-write is a command published in the GitHub repository forsonny/The-Crucible-Writing-System-For-Claude (60 stars, last pushed 8mo ago), licensed MIT. It adds 23 tokens to every session and 650 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.