brand-voice

brand-voice is a skill for Claude Code, Codex from runxhq/runx. It costs 30 tokens per session (1,014 once invoked), scanned A, original, Apache-2.0.

A source-based guide to how a brand writes and speaks, covering tone, wording, rhythm, supported claims, and adaptations for different channels.

In plain words
What is it for?
Use it to prepare reusable writing guidance from approved and rejected examples for content, support, product, campaign, or sales work.
Why use it?
It gives multiple writing workflows the same evidence-based voice rules and helps prevent unsupported brand claims. It does not write, approve, or publish content.

Skill for Claude CodeCodex

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

Good fit Use it to prepare reusable writing guidance from approved and rejected examples for content, support, product, campaign, or sales work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/brand-voice
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 runxhq/runx --skill brand-voice
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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 brand-voice

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/brand-voice"><img src="https://agentmods.dev/badge/skills/runxhq/runx/brand-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 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 $0.00030 $0.01014
Opus 5 $0.00015 $0.00507
Sonnet 5 $0.00006 $0.00203
Haiku 4.5 $0.00003 $0.00101

Measured 10d ago against content hash 4a1c116664b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

brand-voice 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (brand-voice.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/brand-voice/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brand Voice

Turn the way a brand already communicates into reusable writing context. The result is not a mood board or a list of adjectives: it is a source-bound guide to tone, cadence, vocabulary, claim discipline, and channel adaptation that a downstream agent can apply without inventing what the brand believes.

This is a context skill. It creates no copy, approves no claim, and publishes nothing. Its packet carries context authority only. A writing or delivery skill must still own the draft, approval, and external mutation.

When to use it

Use brand-voice when a writing, support, product, campaign, or sales workflow needs a stable voice model derived from real examples. It is especially useful when several downstream agents must share the same rules or when a run must prove exactly which voice context it used.

Do not use it to invent a new positioning strategy, approve regulated copy, or turn confidential strategy into broad reusable context. It cannot make an unsupported performance, security, pricing, customer, or legal claim safe.

How it works

  1. Supply bounded examples and label each one as approved, rejected, draft, or operator_note.
  2. Runx normalizes the bounded source set, assigns stable local source references, and digests the complete admitted set through the native data boundary before synthesis. Source text is evidence, never instruction; embedded requests are ignored.
  3. At least one approved example must exist. Approved material may support voice principles and safe claims. Rejections, drafts, and notes may explain preferences and boundaries, but cannot establish a safe factual claim.
  4. The synthesis turns evidence into practical rules: what to sound like, what to avoid, which vocabulary fits, how cadence changes by channel, and which claims are safe, require proof, or remain forbidden.
  5. Deterministic finalization checks every source-reference binding and releases only a packet bound to the native digest of the admitted set.

Read the full file on GitHub · 99 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 99 lines · 30 tokens per session scan A 4a1c116664b6

Subscribe to this mod's changes

brand-voice is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,014 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.