A setup command for creating or updating a brand profile: a small set of files that records a brand's voice, messaging, style, and compliance rules. It can build the profile from answers or from existing examples.

Use it to define a default brand or a market-specific version, copy starter profile files, interview the user about their preferences, or learn the rules from three to eight existing pieces of content.

It gives content-generation tools a shared reference for how the brand should sound and what it must avoid. This reduces repeated explanations and inconsistent writing.

brand-setup — Command by localplugins

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/localplugins/plugins/brand-setup

Clone the repo

git clone --depth 1 https://github.com/localplugins/plugins

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 459 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	$0.00016	$0.00459
Opus 5	$0.00008	$0.00230
Sonnet 5	$0.00003	$0.00092
Haiku 4.5	$0.00002	$0.00046

Measured yesterday against content hash bb3d411631dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brand-setup 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 yesterday.

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.

content-multiplier/commands/brand-setup.md · 25 lines

What it actually says

Brand Setup

You are setting up a brand profile for the content-multiplier plugin. The profile lives in the user's repo at content/brand/ (default brand) or content/brands/<name>/ when --brand <name> is given; per-market overrides go in .../locales/<xx-XX>/ when --locale is given.

Arguments: $ARGUMENTS

Steps

Determine the target directory from any --brand / --locale flags (default content/brand/). Create it if needed.
Copy the four starter templates from this plugin's templates/brand/ into the target directory if they don't already exist: brand-voice.md, messaging.md, style-guide.md, compliance.md. Never overwrite an existing profile file without confirming.
Choose a mode:
- Interview mode (default when no example files are given): ask the user a short, focused set of questions — target audience, 3-5 personality adjectives, tone, words they love and words to avoid, main competitors, and any must-have disclaimers. Ask them a few at a time, not one giant wall.
- Learn-from-examples mode (when the user passes paths to 3-8 existing on-brand pieces): read those files and infer voice, vocabulary, sentence rhythm, formatting, and recurring phrases.
Fill in every section of the four files based on the answers/examples. Keep entries concrete and specific — no empty  placeholders left behind.
Run a self-audit: re-read the filled profile and flag any gaps, contradictions, or vague entries. Report them to the user and offer to fix.
Summarize what you created and tell the user they can commit content/brand/ to share it with their whole team.

Never fetch anything from the network. Only read files the user explicitly provides.

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.

yesterday First seen · 25 lines · 16 tokens per session scan A bb3d411631dc

Subscribe to this mod's changes

brand-setup is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 459 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 branding claude-code claude-code-marketplace claude-code-plugins content-generation developer-tools

brand-setup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Brand Setup

Steps

What this file has done since we first saw it

Other commands, from other repositories

security-audit-static

performance-audit-static

sprint

analyze-test

plan-okrs

write-stories