narrative-voice-coach

narrative-voice-coach is a skill for Claude Code, Codex from Ckokoski/AuthorAgent. It costs 23 tokens per session (1,673 once invoked), scanned A, original, MIT.

A writing coach that studies how an author writes, from sentence rhythm and word choice to paragraph patterns, and gives detailed guidance for developing a consistent narrative voice.

In plain words
What is it for?
Use it to examine manuscript chapters, identify recurring voice patterns, compare sections, and guide revisions toward a more consistent style.
Why use it?
It helps writers understand what makes their prose recognizable and find places where the voice becomes uneven or generic.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to examine manuscript chapters, identify recurring voice patterns, compare sections, and guide revisions toward a more consistent style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckokoski/authoragent/narrative-voice-coach
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 Ckokoski/AuthorAgent --skill narrative-voice-coach
Clone the repo
git clone --depth 1 https://github.com/Ckokoski/AuthorAgent

Made for: Claude Code, Codex.

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 narrative-voice-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckokoski/authoragent/narrative-voice-coach/github.svg)](https://agentmods.dev/skills/ckokoski/authoragent/narrative-voice-coach)
Your own site
<a href="https://agentmods.dev/skills/ckokoski/authoragent/narrative-voice-coach"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/narrative-voice-coach/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 narrative-voice-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckokoski/authoragent/narrative-voice-coach"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/narrative-voice-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,673 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.01673
Opus 5 $0.00012 $0.00837
Sonnet 5 $0.00005 $0.00335
Haiku 4.5 $0.00002 $0.00167

Measured 12d ago against content hash 8e84af8cc6cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

narrative-voice-coach 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.

skills/_archived/premium/narrative-voice-coach/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narrative Voice Coach — Premium Skill

Your personal writing coach focused entirely on voice — the thing that makes YOUR writing unmistakably yours. Analyzes your prose at the sentence level, identifies your natural strengths, spots inconsistencies, and helps you develop a voice so distinctive that readers recognize you by paragraph two.

The 47-Marker Voice Analysis

Goes far beyond basic readability scores. Analyzes 47 distinct markers of writing voice:

Rhythm & Cadence (12 markers)

Voice Rhythm Analysis: "The Silent Hour"
Sample: Chapters 1-5 (22,000 words)

Avg Sentence Length:     14.3 words  (Genre avg: 16.2)
Sentence Length Variance: HIGH ✅     (Good — not monotonous)
Short Sentence Ratio:    23%         (Punchy when needed)
Fragment Usage:          8.4%        (Distinctive — intentional?)
Paragraph Length:        4.2 sentences (Tight, thriller-appropriate)

Rhythm Signature:
Long-Short-Short-Medium-Long (your natural pattern)
████░░░██░░████  ← Your rhythm
████████████████  ← Flat rhythm (what to avoid)

Cadence Score: 8.7/10
"Strong rhythmic instinct. Your short sentences hit hard
after long atmospheric setups. This is your superpower."

Word Choice & Diction (10 markers)

  • Latinate vs. Anglo-Saxon word preference
  • Concrete vs. abstract noun ratio
  • Active vs. passive voice percentage
  • Verb strength index (strong verbs vs. was/were/had)
  • Adjective density (sparse vs. lush)
  • Adverb reliance (flagged with alternatives)
  • Unique word ratio (vocabulary breadth)
  • Jargon/technical language level
  • Formality spectrum
  • Sensory word frequency by type (visual, auditory, tactile, etc.)

Sentence Architecture (8 markers)

  • Opening word patterns (how you start sentences)
  • Clause complexity (simple, compound, complex ratios)
  • Subordinate clause placement (front, mid, end)
  • Parallel structure usage
  • List/series patterns (do you use Oxford comma? series of 3?)
  • Sentence type ratio (declarative, interrogative, exclamatory)
  • Embedded thought patterns
  • Punctuation personality (em-dash lover? semicolon user? ellipsis addict?)

Read the full file on GitHub · 191 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 · 191 lines · 23 tokens per session scan A 8e84af8cc6cf

Subscribe to this mod's changes

narrative-voice-coach is a skill published in the GitHub repository Ckokoski/AuthorAgent (110 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 1,673 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.