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 glifxyz/glif-mcp-server --skill app-icons-and-logosgit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/app-icons-and-logos)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/app-icons-and-logos"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/app-icons-and-logos/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/glifxyz/glif-mcp-server/app-icons-and-logos"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/app-icons-and-logos.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 | $0.00198 | $0.01270 |
| Opus 5.5 | $0.00079 | $0.00508 |
| Sonnet 5.5 | $0.00040 | $0.00254 |
| Haiku 4.5 | $0.00020 | $0.00127 |
Grade A, and why
app-icons-and-logos scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Download the finals into the repo, for example `assets/brand/`, with `curl -fsSL "<media url>" -o <path>`. Make the sizes locally from the master with whatever is installed: `sharp`, `magick`, `sips` or `npx png-to-ico`. How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a mark the user picks, then turn it into every file the app needs. The user's explicit instructions come first, within host safety rules.
1. Get the brief
Ask only for what's missing:
- product name and one line on what it does
- feel: playful, serious, technical, warm...
- colors to use or avoid
- any existing logo, sketch, screenshot or site URL to build on (upload files with
upload_file)
If the user already has a logo, use it. Don't redesign it unless asked.
2. Explore, then let the user pick
A request for a logo or icon is approval to spend credits on it. Send one compose_project call asking for 4 clearly different concepts:
- 1:1, at least 1024×1024, centered with even padding
- flat, bold shapes that still read at 32 px and in one color
- plain background, no mockups, no extra text unless it's a wordmark
Show the concepts and stop. The user picks. Never choose for them.
3. Make the finals
Continue the same project by passing its project_id to compose_project. Ask for the chosen concept as:
- an SVG, plus a 2048×2048 transparent PNG master
- one-color versions in black and white
- an icon-only square mark, if the concept has a wordmark
- an opaque square version on the brand background color, for app icons
Glif can make SVG. If a result comes back raster-only, a simple flat mark can be traced locally with vtracer or potrace. Check the trace against the PNG.
For wordmarks, check the spelling letter by letter. A crisper option is to set the name in a real font next to the mark, in SVG or HTML.
4. Export the sizes
Download the finals into the repo, for example assets/brand/, with curl -fsSL "<media url>" -o <path>. Make the sizes locally from the master with whatever is installed: sharp, magick, sips or npx png-to-ico. Never upscale.
Web head kit (in public/ or the framework's static folder):
| File | Size | Notes |
|---|---|---|
favicon.ico |
16, 32, 48 | multi-size ICO |
favicon.svg |
vector | from the SVG master |
apple-touch-icon.png |
180×180 | opaque, with padding |
icon-192.png, icon-512.png |
192, 512 | listed in site.webmanifest |
icon-maskable-512.png |
512×512 | mark inside the center 80% circle, "purpose": "maskable" |
What ships with it
1 file 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.
- 9d ago First seen · 82 lines · 198 tokens per session scan A 2362d9d5706b
app-icons-and-logos is a skill published in the GitHub repository glifxyz/glif-mcp-server (215 stars, last pushed 8d ago), licensed MIT. It adds 198 tokens to every session and 1,270 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
atelier
Two-agent post-generation quality gate for vibe-coded applications. Deterministic, gradeable ruleset enforcing UI/UX design-system craft and backend architectural soundness.
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…