brand-voice

brand-voice is a cursor rule for Cursor from ssheleg/super-ux. It costs 39 tokens per session (424 once invoked), scanned A, original, MIT.

A set of writing rules that defines how a product communicates, with its brand documents treated as the source of truth.

In plain words
What is it for?
Use it when changing user-visible copy, adding interface strings or checking brand documentation with the included linter.
Why use it?
It prevents inconsistent wording, invented facts and unclear names across public text and interface messages.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 docs/brand/lint.py.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Cursor.

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/rules/ssheleg/super-ux/brand-voice.svg)](https://agentmods.dev/rules/ssheleg/super-ux/brand-voice)
Your own site
<a href="https://agentmods.dev/rules/ssheleg/super-ux/brand-voice"><img src="https://agentmods.dev/badge/rules/ssheleg/super-ux/brand-voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00424
Opus 5 $0.00019 $0.00212
Sonnet 5 $0.00008 $0.00085
Haiku 4.5 $0.00004 $0.00042

Measured 5d ago against content hash 5a88b9fac547, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

cursor/rules/brand-voice.mdc · 38 lines

What it actually says

Brand voice (super-ux)

docs/ux/ decides what the product does. docs/brand/ decides how it speaks, under brand-contract v1.

Before writing any user-visible text

Read docs/brand/voice.md, terminology.md, and the channels.md record for the surface. No pack yet → run /brand-init rather than improvising a voice; a product whose copy was invented surface by surface is the drift this layer removes.

Rules

  • Any change to public text updates docs/brand/ in the same change.
  • Never quote a figure with no row in facts.md. Never invent a fact, statistic, quote or expert — report the gap.
  • One action, one name, everywhere it appears. Check strings.md first.
  • A register moves the voice axes; it never crosses the invariants listed in voice.md.
  • No humor, exclamation marks or emoji on error, destructive confirm, billing or paywall surfaces, in any voice.
  • New interface strings get a strings.md row: key, file:line, scenario.

Check

python3 docs/brand/lint.py

Exit 0 clean or warnings only, 1 warnings under --strict, 2 any error. That is the policy docs/ux/lint.py has always had, and one pack cannot hold two opposite meanings for a warning: this linter returned 1 on warnings alone until 2026-08-20, so 13 of its 39 codes turned a build red while printing 0 error(s), 1 warning(s). Clean means checkable, not good — the judgement half is /ux-audit copy.

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. 5d ago First seen · 38 lines · 39 tokens per session scan A 5a88b9fac547

Subscribe to this mod's changes

brand-voice is a cursor rule published in the GitHub repository ssheleg/super-ux (3 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 424 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 2026-08-31.