brand-kit

brand-kit is a skill for Claude Code, Codex from vinsonconsulting/limner. It costs 38 tokens per session (900 once invoked), scanned A, original, Apache-2.0.

A style-profile workflow for Limner, an image-generation project, that stores a brand's colours, visual descriptions, medium, and preferred generation settings.

In plain words
What is it for?
Use it to set or read a brand kit, generate a consistent series, and pass the results to marking or multi-size export workflows.
Why use it?
It keeps a batch of generated images visually consistent by reusing the same brand profile for each request.

Skill for Claude CodeCodex

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

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 skills/vinsonconsulting/limner/brand-kit
Any agent
npx skills add vinsonconsulting/limner --skill brand-kit
Clone the repo
git clone --depth 1 https://github.com/vinsonconsulting/limner

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-kit

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinsonconsulting/limner/brand-kit.svg)](https://agentmods.dev/skills/vinsonconsulting/limner/brand-kit)
Your own site
<a href="https://agentmods.dev/skills/vinsonconsulting/limner/brand-kit"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/brand-kit.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 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 $0.00038 $0.00900
Opus 5 $0.00019 $0.00450
Sonnet 5 $0.00008 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 5d ago against content hash d19902ba532c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 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.

packages/limner-agent/skills/brand-kit/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brand kit

Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.

Use this skill to make a series look like one brand. A brand kit in Limner is a style profile stored on the project: set the palette, descriptors, medium, and pipeline once, then read it before every generation so the whole batch stays consistent. The reference at the end states the profile shape and the rules.

Procedure

  1. Set the kit. Write the brand into the project's style profile with upsertStyleProfile: palette, descriptors, medium, and pipelinePrefs. Set provenance.source to brand-kit and list approved exemplars under references.
  2. Read before each generation. Load the profile with readStyleProfile so every request starts from the same brand.
  3. Shape the prompt from the kit. Build each prompt from the descriptors and medium, and apply pipelinePrefs (the preferred pipeline and knob defaults).
  4. Hold the look fixed. Keep palette, descriptors, and pipeline settings constant across the set and vary only the subject.
  5. Finish on brand. Hand off to brand-stamp for a mark on each asset, or to multi-size export for a per-platform set.
  6. Keep the kit current. Update with the read, merge, write cycle as the brand evolves, and note the change in provenance.

Judgment

  • Decide the kit once and reuse it. Re-deciding the look per asset is what breaks consistency.
  • Keep pipelinePrefs aligned with the per-pipeline recipes, for example a valid Recraft style and substyle pair.
  • A profile from style-from-images or art-research can seed a kit, since they share one shape; merge it in rather than overwrite.

Reference

The text below is generated from the Limner guidance core (@limner/core), the same source the related MCP surfaces serve, so this skill cannot drift from it. Do not edit the generated region by hand; run pnpm --filter @limner/limner-agent gen:skills instead.

Read the full file on GitHub · 72 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.

  1. 5d ago First seen · 72 lines · 38 tokens per session scan A d19902ba532c

Subscribe to this mod's changes

brand-kit is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 24d ago), licensed Apache-2.0. It adds 38 tokens to every session and 900 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.