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 rampstackco/claude-skills --skill logo-designgit clone --depth 1 https://github.com/rampstackco/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/rampstackco/claude-skills/logo-design)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/logo-design"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/logo-design/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/rampstackco/claude-skills/logo-design"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/logo-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00201 | $0.04918 |
| Opus 5 | $0.00101 | $0.02459 |
| Sonnet 5 | $0.00040 | $0.00984 |
| Haiku 4.5 | $0.00020 | $0.00492 |
Grade A, and why
logo-design 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 6d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logo Design
A logo is a system of marks, not a single drawing. This skill produces multiple production-grade variants exploring different architectural approaches, each with rationale, application specs, and a clear position on what it signals and rejects.
The output is decision material, not a finished logo. The brand owner selects from the variants and the skill produces production refinement on the chosen direction.
When to use
- The brand has a name and tonal direction; the deliverable is logo work specifically
- Generating 6 to 12 variants for client review and selection
- Refining a wordmark to production: kerning, optical adjustments, weight selection
- Exploring symbol options to pair with an existing wordmark
- Designing a monogram from a longer name for use in constrained contexts
- Adapting an existing logo across application contexts (small-size, signage, motion, embroidery)
- The brand owner has reviewed a first round and wants iteration on a specific direction
When NOT to use
- Use
brand-identityinstead when the deliverable is the complete identity system (logo plus color plus type plus voice plus applications). This skill is the logo-specific layer; brand-identity is the system layer. - Use
brand-discoveryfor brand positioning, audience, and voice work. A logo without strategy is a drawing. - Use
creative-directionfor project-wide aesthetic direction. Creative direction calibrates many decisions; logo design produces specific marks. - One-off illustration, icon, or pictogram work
- Designing brand patterns, textures, or supporting graphics
- Pure typographic exploration unrelated to a brand name
Required inputs
- Brand name. Exact spelling. Capitalization and punctuation preferences if any. Whether the name has a category descriptor that travels with it (e.g., "Atlas Coffee" vs just "Atlas").
- Industry or category. Legal firm, consumer goods, B2B SaaS, hospitality, etc. Category implies defaults that can be honored or broken.
- Audience. Who sees the logo, where, in what state of mind. The audience-side perception drives selection more than the founder-side aesthetic.
- Tonal direction. Where on the formal-to-casual axis. Where on the restrained-to-expressive axis. Where on the heritage-to-modern axis.
- Application contexts. Common set: web header, mobile app icon (28px), favicon (16 to 32px), business card, letterhead, email signature, social profile picture, signage (large format), embroidery patch (1.5 inch), single-color print, video motion lockup, merch (apparel, hats, totes).
- Reference logos liked, with a sentence each on what specifically resonates. The reference clarifies which architecture and register fit better than abstract description does.
- Reference logos disliked, with a sentence on what to avoid. Negative space sharpens positive selection.
- Hard constraints. Must include element X. Must avoid color Y due to industry conventions. Must reproduce in single color. Must work as a 16px favicon. Must survive embroidery.
- Optional: existing brand assets if the project is a refresh, not greenfield. Existing wordmark if the work is symbol-only. Existing color palette if it must remain locked.
What ships with it
7 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.
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.
- 6d ago First seen · 207 lines · 201 tokens per session scan A 81f4dce86b45
logo-design is a skill published in the GitHub repository rampstackco/claude-skills (830 stars, last pushed yesterday), licensed MIT. It adds 201 tokens to every session and 4,918 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
presentation-design-enhancer
Transform text-heavy slides into visual storytelling. Suggest layout improvements, icon usage, and data visualization.
stock-photo-finder
Search multiple free stock photo sites simultaneously. Filter by license type, orientation, and color scheme.
deck-factory
A design system and working method for hand-building polished HTML presentation slides from a brief or script.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
design-trends-2026
Apply 2026's top graphic design trends to any creative brief. Based on Kittl × Savee's 2026 Design Trends Report (10 trends + 2 honorable mentions), backed by Adobe, Figma, and Pinterest data. Use when: Designing a brand identity — pick the right aesthetic for your audience; Creating social media assets — use trending…
ux-sound-design
Create functional and emotionally resonant audio for digital products using Audio UX methodology—from notification sounds to complete sonic systems. Use when: Designing notification sounds for an app; Creating a complete audio system for a digital product; Adding audio feedback to UI interactions; Building accessible…