voice-check

voice-check is a command for Claude Code from stepolan/marketing-repo-template. It costs 11 tokens per session (440 once invoked), scanned A, original, MIT.

A command that checks a draft against an author's voice profile and reports differences. A voice profile is a set of writing preferences for how that author communicates.

In plain words
What is it for?
Use it to review a specified draft file against the author's profile and brand guidelines. It checks items such as contractions, em dashes, spacing, passive voice, jargon, hype, and whether the main point appears early.
Why use it?
It helps find style inconsistencies before a draft is published, including unwanted wording, tone, formatting, or passive sentences.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it to review a specified draft file against the author's profile and brand guidelines. It checks items such as contractions, em dashes, spacing, passive voice, jargon, hype, and whether the main point appears early.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/stepolan/marketing-repo-template/voice-check
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/stepolan/marketing-repo-template

Made for: Claude Code.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/stepolan/marketing-repo-template/voice-check/github.svg)](https://agentmods.dev/commands/stepolan/marketing-repo-template/voice-check)
Your own site
<a href="https://agentmods.dev/commands/stepolan/marketing-repo-template/voice-check"><img src="https://agentmods.dev/badge/commands/stepolan/marketing-repo-template/voice-check/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-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/stepolan/marketing-repo-template/voice-check"><img src="https://agentmods.dev/badge/commands/stepolan/marketing-repo-template/voice-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 440 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 $0.00011 $0.00440
Opus 5 $0.00005 $0.00220
Sonnet 5 $0.00002 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 12d ago against content hash b8b48ea81ca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

voice-check 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.

.claude/commands/voice-check.md · 48 lines

What it actually says

Run a voice consistency check on the specified draft file.

Target file: $ARGUMENTS

  1. Read the target draft file. If no file specified, ask which file to check.

  2. Load the voice profile:

    • Read the relevant author's voice profile at /authors/<name>/voice/voice-profile.md
    • Read /brand/voice-guidelines.md
  3. Check the draft against voice patterns. Flag:

    • Contractions used (don't, won't, it's, etc.) — should be written out
    • Em dashes (—) or double hyphens (--) used — should use periods or colons
    • Single space after punctuation — should be two spaces
    • Passive voice — should be active
    • Preachy or teaching tone toward peers
    • Blame language toward engineers/teams
    • Corporate jargon (synergy, leverage, best-in-class)
    • Hype language (game-changing, revolutionary)
    • Lead is buried — most interesting insight not in first 3 sentences
    • Credentials listed in body (titles, companies, years)
    • Engagement bait closing ("Agree?" "Thoughts?")
    • Single-line poetry formatting (blog should be paragraphs, LinkedIn should be 2-3 sentence paragraphs)
    • Correct title used per brand/author-bios.md
  4. Report results:

    ## Voice Check Results — [filename]
    
    ### PASS
    - [Rule]: [Brief confirmation]
    
    ### FAIL
    - [Rule] (line N): `[offending text]` → `[suggested fix]`
    
    ### Overall: [Strong / Needs Work / Off Voice]
    

    Every FAIL item must include a specific line number and a before/after suggestion.

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 · 48 lines · 11 tokens per session scan A b8b48ea81ca0

Subscribe to this mod's changes

voice-check is a command published in the GitHub repository stepolan/marketing-repo-template (2 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 440 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 2026-08-31.