agentmods.dev

crucible-review

crucible-review is a command for Claude Code from forsonny/The-Crucible-Writing-System-For-Claude. It costs 23 tokens per session (1,813 once invoked), scanned A, original, MIT.

A command for manually reviewing selected chapters with five specialised agents in the Crucible writing system.

In plain words
What is it for?
Use it to review the latest two chapters or a chosen range, after the system finds the Crucible project and gathers the required chapter and project files.
Why use it?
It lets you run a review between automatic checks or focus on a particular chapter range when you need targeted feedback.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

not rated 60repo +1 8mo ago A scan 23 tokens original MIT

Good fit Use it to review the latest two chapters or a chosen range, after the system finds the Crucible project and gathers the required chapter and project files.

Compare 6 commands from other repositories ↓
View source ↗ forsonny/The-Crucible-Writing-System-For-Claude
Install

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.

Claude Code
/plugin marketplace add forsonny/The-Crucible-Writing-System-For-Claude
Claude Code
/plugin install 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-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/forsonny/the-crucible-writing-system-for-claude/crucible-review"><img src="https://agentmods.dev/badge/commands/forsonny/the-crucible-writing-system-for-claude/crucible-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,813 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 $0.00023 $0.01813
Opus 5 $0.00012 $0.00907
Sonnet 5 $0.00005 $0.00363
Haiku 4.5 $0.00002 $0.00181

Measured 12d ago against content hash 9a7568a90cdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

crucible-review 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.

commands/crucible-review.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/crucible-review

Trigger a manual review of your chapters using specialized review agents.

Usage

  • /crucible-suite:crucible-review latest - Review most recent 2 chapters
  • /crucible-suite:crucible-review 5-6 - Review chapters 5 and 6
  • /crucible-suite:crucible-review 1-4 - Review chapters 1 through 4

Execution Instructions

IMPORTANT: When this command is invoked, you MUST:

  1. ALWAYS use the AskUserQuestion tool for presenting options to the user (NOT plain text A/B/C options)

  2. Detect project root - Find the Crucible project directory:

    • Use Glob to search for .crucible/ directory: Glob(pattern="**/.crucible")
    • The project root is the PARENT of the .crucible/ directory found
    • Store this as PROJECT_ROOT (absolute path) for all subsequent steps
    • If no .crucible/ found, inform user this must be run from within a Crucible project

  3. Determine chapter range from the argument:

    • latest → Read {PROJECT_ROOT}/.crucible/state/draft-state.json to find the last 2 completed chapters
    • X-Y → Use chapters X through Y
    • Single number → Review that chapter only

  4. Resolve all file paths - Build absolute paths for agents:

    • Chapter files: {PROJECT_ROOT}/draft/chapters/ch{NN}.md
    • Story bible: {PROJECT_ROOT}/story-bible.json
    • Style profile: {PROJECT_ROOT}/style-profile.json
    • Master outline: {PROJECT_ROOT}/outline/master-outline.md
    • Scene breakdown: {PROJECT_ROOT}/outline/scene-breakdown.md
    • World forge: {PROJECT_ROOT}/planning/world-forge.md

  5. Launch ALL 5 review agents in parallel using the Task tool with ABSOLUTE PATHS:

Task(subagent_type="crucible-suite:voice-checker", prompt="Review chapters X-Y for voice consistency.

PROJECT ROOT: {PROJECT_ROOT}

CHAPTERS TO REVIEW:
- {PROJECT_ROOT}/draft/chapters/ch05.md
- {PROJECT_ROOT}/draft/chapters/ch06.md

REFERENCE FILES:
- Style profile: {PROJECT_ROOT}/style-profile.json

Analyze for voice consistency against the style profile. Return a structured report following your output format.")

Task(subagent_type="crucible-suite:continuity-checker", prompt="Review chapters X-Y for continuity errors.

PROJECT ROOT: {PROJECT_ROOT}

CHAPTERS TO REVIEW:
- {PROJECT_ROOT}/draft/chapters/ch05.md
- {PROJECT_ROOT}/draft/chapters/ch06.md

REFERENCE FILES:
- Story bible: {PROJECT_ROOT}/story-bible.json
- Planning docs: {PROJECT_ROOT}/planning/

Check for continuity errors against the story bible. Return a structured report following your output format.")

Task(subagent_type="crucible-suite:outline-checker", prompt="Review chapters X-Y for outline adherence.

PROJECT ROOT: {PROJECT_ROOT}

CHAPTERS TO REVIEW:
- {PROJECT_ROOT}/draft/chapters/ch05.md
- {PROJECT_ROOT}/draft/chapters/ch06.md

REFERENCE FILES:
- Master outline: {PROJECT_ROOT}/outline/master-outline.md
- Scene breakdown: {PROJECT_ROOT}/outline/scene-breakdown.md
- Forge points: {PROJECT_ROOT}/planning/forge-points/

Verify adherence to the outline. Return a structured report following your output format.")

Task(subagent_type="crucible-suite:timeline-checker", prompt="Review chapters X-Y for timeline consistency.

PROJECT ROOT: {PROJECT_ROOT}

CHAPTERS TO REVIEW:
- {PROJECT_ROOT}/draft/chapters/ch05.md
- {PROJECT_ROOT}/draft/chapters/ch06.md

REFERENCE FILES:
- Story bible (timeline data): {PROJECT_ROOT}/story-bible.json
- World forge (travel times): {PROJECT_ROOT}/planning/world-forge.md

Analyze chronological consistency and temporal logic. Return a structured report following your output format.")

Task(subagent_type="crucible-suite:prose-checker", prompt="Review chapters X-Y for prose quality.

PROJECT ROOT: {PROJECT_ROOT}

CHAPTERS TO REVIEW:
- {PROJECT_ROOT}/draft/chapters/ch05.md
- {PROJECT_ROOT}/draft/chapters/ch06.md

REFERENCE FILES:
- Style profile: {PROJECT_ROOT}/style-profile.json

Analyze prose craft including pacing, show vs tell, and dialogue. Return a structured report following your output format.")

Read the full file on GitHub · 234 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 · 234 lines · 0 tokens per session scan A 9a7568a90cdd

Subscribe to this mod's changes

crucible-review 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 1,813 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.

Writing and docs
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

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.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

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.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens