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/darcos-loft/fluid/brandkitnpx skills add Darcos-Loft/fluid --skill brandkitgit clone --depth 1 https://github.com/Darcos-Loft/fluidWrote 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/darcos-loft/fluid/brandkit)<a href="https://agentmods.dev/skills/darcos-loft/fluid/brandkit"><img src="https://agentmods.dev/badge/skills/darcos-loft/fluid/brandkit.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 | $0.00070 | $0.00517 |
| Opus 5 | $0.00035 | $0.00259 |
| Sonnet 5 | $0.00014 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
brandkit 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.
What it actually says
Brandkit
Premium reference imagery for a brand: the visual north-star before code. Works with any image model. Pairs with the design-system skill, which provides the palette and type; this renders them.
What it produces
- Logo concepts: a mark and a wordmark, on the brand palette.
- A brand board: palette swatches, type specimens, the mood in one frame.
- Product mockups: the site or app in context, premium product-photography style.
- Optional hero: an "open and reveal" sequence (below).
Prompt formula (premium product photography)
[Subject + material and finish], centered in frame, 3/4 front angle.
Clean [brand background hex] background, soft studio lighting, subtle shadows.
[Detail specific to the brand]. Photorealistic, 16:9, catalog quality,
Apple-style product photography. No text, no logos, no other objects in frame.
The "open and reveal" hero (two-image to video)
A signature, attention-grabbing hero: an intact object that opens and whose contents spill out.
- Image A, closed: the object intact and clean.
- Image B, open: the same object, opened, contents floating around it. Golden rule: identical subject, angle, light, and background, only the state changes, or the animation will jump.
- Animate A to B with an image-to-video model (Higgsfield, Kling, Veo): set A as the start frame, B as the end frame, plus a motion prompt describing the opening. Fallback: animate image B alone with a floating motion.
Rules
- The brand palette and type come from the
design-system, not invented here. Render the system, do not redesign it. - Real material, premium light, no clutter. Generated does not mean cheap.
- One consistent style across the whole kit.
- Remove any model watermark before use (crop or a clean export).
Pairs with: design-system (the identity this renders).
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 · 38 lines · 70 tokens per session scan A f79a6e6879c2
brandkit is a skill published in the GitHub repository Darcos-Loft/fluid (3 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 517 once invoked, about $0.0003 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
tailwind-design-system
Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
paint
Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).
component-family-consistency
Buttons, inputs, pills, badges, calendars, and other interactive components form a visual family — they share the same border-radius, colour logic, shadow scale, border style, and spacing rhythm. Inconsistency between them breaks the sense of a coherent product. Use when building or reviewing a component library…
extract-design
Extract a complete design system — colors, typography, spacing, components, shadows, and W3C design tokens — from any live website using Dembrandt. Runs a headless browser against the URL and returns real computed values from the DOM. Use when you need a site's actual design tokens, want to reverse-engineer a visual…
data-display-and-selection
Complex data deserves multiple view modes — grid, list, table — chosen by the user based on their task. Row and item selection should use large hit areas (the whole row or card, not just a checkbox). Selected state is communicated through a subtle background colour shift. Mass actions appear when items are selected.…