What is voice-design?

A command that creates a written voice profile from a description or a ready-made template. A voice profile records qualities such as tone, vocabulary, sentence style, and writing habits.

Use it to define a brand voice, narrator style, or other writing character before generating content.

It avoids a guided interview when you already know how the voice should sound. It turns a short description into a structured profile for consistent writing.

voice-design — Command for coding agents by zircote: A command that creates a written voice profile from…

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.

agentmods

npx agentmods add commands/zircote/human-voice/voice-design

Clone the repo

git clone --depth 1 https://github.com/zircote/human-voice

Or install human-voice, the plugin that ships this one along with the rest of its 2 skills, 12 commands, 3 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/zircote/human-voice/voice-design.svg)](https://agentmods.dev/commands/zircote/human-voice/voice-design)

Your own site

<a href="https://agentmods.dev/commands/zircote/human-voice/voice-design"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-design.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 680 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.00680
Opus 5	$0.00008	$0.00340
Sonnet 5	$0.00003	$0.00136
Haiku 4.5	$0.00002	$0.00068

Measured 5d ago against content hash edd6c63504b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

voice-design 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 5d 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/voice-design.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voice-design — Design a Voice Profile

Create a complete voice profile without running an interview. Two modes: describe a voice character in natural language, or start from a pre-built template.

Procedure

Parse arguments: Extract the slug and either a description or --from-template {name}.
From description (default):
- The user provides a natural-language description of the voice character. Examples:
  - "A warm, narrative voice that uses humor and personal anecdotes. Casual register, short sentences, lots of contractions."
  - "Corporate brand voice: professional, authoritative, no humor, active voice, precise vocabulary."
  - "Victorian narrator: ornate, long multi-clause sentences, formal vocabulary, third-person omniscient."
- Generate a complete profile.json conforming to question-bank/schemas/voice-profile.schema.json:
  - Set session_id to null (no interview session)
  - Set all 8 gold-standard dimensions with plausible scores derived from the description
  - Set semantic differential values consistent with the description
  - Generate distinctive features, mechanics preferences, and an identity summary
  - Set calibration to null (no self-report vs observed comparison possible)
- The origin is "designed".
From template (--from-template {name}):
- Load the template from templates/profiles/{name}.json
- Available templates: formal-technical, casual-conversational, academic-prose, brand-corporate, creative-narrative
- Optionally ask the user to customize dimension scores or mechanics via AskUserQuestion
- The origin is "template".
Name the profile:
- If a slug was provided as the first argument, use it.
- Otherwise, ask via AskUserQuestion: "What slug would you like for this profile? (e.g., 'narrator-formal', 'brand-zircote')"
Store and activate:
- Run: python3 -c "from lib.profile_registry import store_profile, activate_profile; import json; store_profile('{slug}', json.load(open('/tmp/designed-profile.json')), '{display_name}', origin='{origin}'); activate_profile('{slug}')"
- Or write the profile directly and call the registry functions.

Read the full file on GitHub · 55 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.

5d ago First seen · 55 lines · 16 tokens per session scan A edd6c63504b2

Subscribe to this mod's changes

voice-design is a command published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 680 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.

Writing and docs ai-detection claude-code claude-code-plugin content-quality markdown

graph

Extract prerequisite concept graph from converted course materials and write course-index/concept-graph.md.

OPTIMETA/PAIDEIA · 18 tokens

reindex

Idempotent reindex of an existing course — rewrite retired coverage.md tier markers to canonical vocabulary and materialize errors/log.md nature/phase into the on-disk schema (header keys == data keys), in place and atomically, WITHOUT running analyze.

OPTIMETA/PAIDEIA · 51 tokens

alt

Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.

OPTIMETA/PAIDEIA · 44 tokens

blind

Strategy-level blind drill on a known HW or example problem. User describes approach in prose (no math typing); Claude verifies against solution then saves clean reference to derivations/.

OPTIMETA/PAIDEIA · 34 tokens

doctor

Diagnose the paideia install + course workspace (Python, poppler, tesseract, Ollama/Qwen3-VL, course folders, .course-meta, writable paths, statusline wiring) and optionally auto-repair the permission-free issues. Run when a command won't work or right after cloning.

OPTIMETA/PAIDEIA · 63 tokens

quiz

Generate N practice problems on a topic. Saves problem MD + hidden answer MD. User solves on paper, uploads answer PDF, then runs /grade. First arg weakmap → auto-load latest weakmap report and target its top weaknesses.

OPTIMETA/PAIDEIA · 49 tokens