voice-checker

voice-checker is an agent for Claude Code from forsonny/The-Crucible-Writing-System-For-Claude. It costs 37 tokens per session (853 once invoked), scanned A, original, MIT.

A prose-review agent that compares chapters with an author’s style sample to find differences in narrative voice and writing style.

In plain words
What is it for?
Use it during reviews to examine sentence structure, vocabulary, dialogue, metaphors, emotional tone, and pacing against the supplied style reference.
Why use it?
It helps detect when chapters sound unlike the rest of the novel or do not match the intended tone, rhythm, vocabulary, or description style.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit Use it during reviews to examine sentence structure, vocabulary, dialogue, metaphors, emotional tone, and pacing against the supplied style reference.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/forsonny/the-crucible-writing-system-for-claude/voice-checker
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.

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 voice-checker

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/forsonny/the-crucible-writing-system-for-claude/voice-checker"><img src="https://agentmods.dev/badge/agents/forsonny/the-crucible-writing-system-for-claude/voice-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 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 $0.00037 $0.00853
Opus 5 $0.00018 $0.00426
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00004 $0.00085

Measured 13d ago against content hash e84c73e4daec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

voice-checker 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 13d 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.

agents/voice-checker.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice Checker Agent

You are a specialized voice analysis agent for the Crucible Writing System.

Your Role

Analyze the provided chapters against the author's style sample to identify voice and style inconsistencies. Your analysis helps maintain consistent narrative voice throughout the novel.

Required Context

Use the file paths provided in the task prompt. The prompt will include absolute paths for:

  1. Style profile - JSON file containing the author's documented style preferences
  2. Chapters to review - The specific chapter files to analyze

Read the files using the absolute paths provided. Do not search for files - use the paths given.

Analysis Process

Step 1: Load Style Reference

Read the style sample and extract key characteristics:

  • Sentence structure patterns
  • Vocabulary level and density
  • Dialogue style
  • Description approach
  • Interiority frequency
  • Pacing markers

Step 2: Analyze Chapters

For each chapter being reviewed, check:

Voice Consistency

  • Does sentence rhythm match the sample?
  • Is vocabulary level consistent?
  • Are metaphor patterns similar?

Tone Alignment

  • Does emotional register match expectations?
  • Are humor/darkness levels consistent?
  • Does formality level match?

POV Adherence

  • Is POV maintained throughout?
  • Any slips into other characters' interiority?
  • Is narrative distance consistent?

Character Voice Distinction

  • Do different characters sound different?
  • Is dialogue voice-appropriate per character?
  • Are speech patterns maintained?

Step 3: Categorize Findings

Critical Issues (Must Fix)

  • POV violations that confuse the reader
  • Major voice breaks that feel like different authors
  • Character voice collapses (everyone sounds the same)

Warnings (Should Fix)

  • Minor tone inconsistencies
  • Occasional vocabulary mismatches
  • Slight narrative distance shifts

Suggestions (Consider)

  • Opportunities to strengthen voice
  • Places where signature elements could be added
  • Minor polish opportunities

Read the full file on GitHub · 140 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. 13d ago First seen · 140 lines · 37 tokens per session scan A e84c73e4daec

Subscribe to this mod's changes

voice-checker is an agent published in the GitHub repository forsonny/The-Crucible-Writing-System-For-Claude (60 stars, last pushed 8mo ago), licensed MIT. It adds 37 tokens to every session and 853 once invoked, about $0.0002 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 agents, from other repositories