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 skills add shaharsha/claude-skills --skill brand-assetsgit clone --depth 1 https://github.com/shaharsha/claude-skillsWrote 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/shaharsha/claude-skills/brand-assets)<a href="https://agentmods.dev/skills/shaharsha/claude-skills/brand-assets"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/brand-assets/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.
<a href="https://agentmods.dev/skills/shaharsha/claude-skills/brand-assets"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/brand-assets.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00118 | $0.01075 |
| Opus 5 | $0.00059 | $0.00537 |
| Sonnet 5 | $0.00024 | $0.00215 |
| Haiku 4.5 | $0.00012 | $0.00108 |
Grade A, and why
brand-assets 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 12d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Assets
Four mechanical jobs that sit between a designer's raster source and production-ready assets. Get these wrong and the brand is off by 5° for years.
The four jobs
| Job | Input | Output | Script |
|---|---|---|---|
| Vectorize | PNG of a logo using ≤3 solid brand colors | clean multi-color SVG | scripts/vectorize.sh |
| Finalize | Any SVG with approximate colors or extra paths | SVG with exact brand hexes + filtered counters + square viewBox | scripts/finalize-svg.py |
| Rasterize | SVG | PNG at specific size with tight-trim or centered-on-canvas padding | scripts/rasterize.sh |
| Icon pack | One SVG | favicon.svg + favicon-32x32.png + apple-touch-icon.png + manifest icons |
scripts/icon-pack.sh |
Plus a verification helper:
| Color audit | PNG | histogram of opaque pixels per hex — proves the raster only uses brand colors | scripts/color-audit.sh |
When to use this skill
- "Vectorize this logo PNG" / "turn this into an SVG"
- "Clean up this SVG — the colors are slightly off"
- "Re-render the logo at 2048×2048 with 10% padding"
- "Generate a favicon pack from this logo"
- "Add apple-touch-icon" / "iOS home-screen icon is missing"
- "The PNG looks fuzzy at small sizes — can we redo it crisper?"
- "Audit which colors are in this PNG" / "is this on-brand?"
- Any refresh where brand colors changed and production PNGs need re-rendering from the SVG source.
Workflow
- Read the reference for the job:
- reference/vectorize.md — PNG → multi-color SVG (the non-obvious part is split-by-color-mask + combine, not one-shot trace)
- reference/finalize.md — the "keep only the counter whose bbox contains the focal dot" rule, plus viewBox tricks
- reference/rasterize.md — tight-trim vs centered-on-canvas; when to pre-bake clear space vs ship tight
- reference/icon-pack.md — favicon quirks, apple-touch-icon bg requirement (iOS auto-rounds corners, so NO transparent bg)
- reference/tools.md —
rsvg-convert,vtracer,potrace,rembg,magick, install + quirks
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 85 B
- README.md 5.0 KB
- reference/finalize.md 3.9 KB
- reference/icon-pack.md 3.9 KB
- reference/rasterize.md 3.4 KB
- reference/tools.md 2.9 KB
- reference/vectorize.md 6.3 KB
- scripts/color-audit.sh 2.0 KB runs code
- scripts/finalize-svg.py 13 KB runs code
- scripts/icon-pack.sh 4.4 KB runs code
- scripts/rasterize.sh 3.1 KB runs code
- scripts/README.md 2.1 KB
- scripts/vectorize.sh 4.2 KB runs code
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.
- 12d ago First seen · 64 lines · 118 tokens per session scan A aa7c78318dba
brand-assets is a skill published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 14d ago), licensed MIT. It adds 118 tokens to every session and 1,075 once invoked, about $0.0006 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.