What is build-brand-kit?

A planning command for thinking through how a business or group of businesses should be structured before speaking with a lawyer. It covers the current and possible future structure, jurisdictions, holding companies, and questions to ask.

Use it to prepare an entity-structure discussion and checklist; it is not legal or tax advice.

It organises the business and legal questions so a professional consultation can focus on specific trade-offs.

build-brand-kit — Command for Claude Code by frankxai

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/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 8 skills, 122 commands, 7 agents, 4 hooks.

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/frankxai/starlight-intelligence-system/build-brand-kit/github.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/build-brand-kit)

Your own site

<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/build-brand-kit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/build-brand-kit/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/build-brand-kit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/build-brand-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,447 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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.02447
Opus 5.5	$0.00030	$0.00979
Sonnet 5.5	$0.00015	$0.00489
Haiku 4.5	$0.00007	$0.00245

Measured 2mo ago against content hash 33950ff022db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-brand-kit 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 2mo 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/build-brand-kit.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/build-brand-kit

Load SIP.md, VOICES.md, agents/starlight-visionary.md, skills/vision/design-coherence.md. Assemble a coherent Brand Kit grounded in the person's Genius Profile + Vision Architecture. Hand off to /align-voice for voice coherence enforcement on future content.

Input

$ARGUMENTS

When this command fires

Genius Profile exists at genius/profile-<slug>.md
Vision Architecture exists at vision/vision-<slug>.md
The person is ready to install a brand that compounds across every surface

When this command does NOT fire

No Genius Profile → halt and route to /discover-genius
No Vision Architecture → halt and route to /define-vision (vision drives mood; brand without vision drifts)
Single-asset request (one logo, one post) → use frankx-brand / brand-voice / infogenius directly
Existing brand kit in place → use /align-voice to audit, not re-build

Process

Load upstream.
- Resolve <person-slug>.
- Load genius/profile-<slug>.md, genius/freedom-path-<slug>.md, vision/vision-<slug>.md.
- If any missing, halt and route to the appropriate upstream command.
- Parse optional --style hint. Style biases mood derivation but never overrides genius-derived voice.
Check for @arcanea/design-system pattern.
- If integrations/starter-packs/friend-starter/ or an adopter's repo contains a @arcanea/design-system reference, note it. Brand Kit outputs integrate with that system's token format where present (CSS variables, design tokens JSON).
- If absent, emit standalone Brand Kit. Do not fabricate integration.
Derive positioning statement.
- From Genius Profile's cross-domain synthesis + Vision Architecture's 10-year horizon.
- Format: "For who , <person/brand> is the that , because ."
- One sentence. If it runs more than two lines, rework.
Author voice rules (6–10).
- Derive from Genius Profile voice samples. Every rule cites a voice sample.
- Examples of rule shapes:
  - "First-person only. Never corporate-we. (cf. sample #2)"
  - "No listicles. One framework per piece. (cf. sample #1, #4)"
  - "Register: . Not: . (cf. sample #3)"
- Rules that cannot cite a sample are deleted.

Read the full file on GitHub · 204 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.

2mo ago First seen · 204 lines · 75 tokens per session scan A 33950ff022db

Subscribe to this mod's changes

build-brand-kit is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (10 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 2,447 once invoked, about $0.0003 per session on Opus 5.5. 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.

Claude Code Design and UX Marketing and SEO Memory and context Multi-Agent Orchestration ai-agents intelligence

build-brand-kit next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
build-brand-kitfrankxai/Starlight-Intelligence-System	Command	10	yesterday	MIT	A	75	Claude Code
ui-auditIbrahim-3d/orchestrator-supaconductor	Command	381	1mo ago	AGPL-3.0	A	21	Claude Code
ux-designerIbrahim-3d/orchestrator-supaconductor	Command	381	1mo ago	AGPL-3.0	A	26	Claude Code
design-reviewseokan-jeong/team-shinchan	Command	9	3mo ago	MIT	A	25	Claude Code
memoriesseokan-jeong/team-shinchan	Command	9	3mo ago	MIT	A	5	Claude Code
mpm-session-resumebobmatnyc/claude-mpm	Command	158	2mo ago	none	A	5	Claude Code
forgetseokan-jeong/team-shinchan	Command	9	3mo ago	MIT	A	3	Claude Code