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.
npx agentmods add skills/vinsonconsulting/limner/brand-kitnpx skills add vinsonconsulting/limner --skill brand-kitgit clone --depth 1 https://github.com/vinsonconsulting/limnerWrote 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.
[](https://agentmods.dev/skills/vinsonconsulting/limner/brand-kit)<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>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 | $0.00038 | $0.00900 |
| Opus 5 | $0.00019 | $0.00450 |
| Sonnet 5 | $0.00008 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
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.
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
- 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.
- Read before each generation. Load the profile with readStyleProfile so every request starts from the same brand.
- Shape the prompt from the kit. Build each prompt from the descriptors and medium, and apply pipelinePrefs (the preferred pipeline and knob defaults).
- Hold the look fixed. Keep palette, descriptors, and pipeline settings constant across the set and vary only the subject.
- Finish on brand. Hand off to brand-stamp for a mark on each asset, or to multi-size export for a per-platform set.
- 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.
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.
- 5d ago First seen · 72 lines · 38 tokens per session scan A d19902ba532c
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.
Other skills, from other repositories
flux-3-product-ads
Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.
bfl-api
BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.
flux-3-archival-formats
Use when a FLUX 3 video needs a period or archival look. Covers naming a recording format instead of a mood, per-format artifacts, and templates.
flux-3-keyframes-continuation
Use when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v).
flux-3-prompt-doctor
Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.
flux-image-best-practices
Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.