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 gherardo200-glitch/illustrator-mcp --skill agensi-skillgit clone --depth 1 https://github.com/gherardo200-glitch/illustrator-mcpWrote 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/gherardo200-glitch/illustrator-mcp/agensi-skill)<a href="https://agentmods.dev/skills/gherardo200-glitch/illustrator-mcp/agensi-skill"><img src="https://agentmods.dev/badge/skills/gherardo200-glitch/illustrator-mcp/agensi-skill/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/gherardo200-glitch/illustrator-mcp/agensi-skill"><img src="https://agentmods.dev/badge/skills/gherardo200-glitch/illustrator-mcp/agensi-skill.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 | $0.00162 | $0.02370 |
| Opus 5.5 | $0.00065 | $0.00948 |
| Sonnet 5.5 | $0.00032 | $0.00474 |
| Haiku 4.5 | $0.00016 | $0.00237 |
Grade A, and why
illustrator-mcp 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 today.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Illustrator MCP
What this is
Illustrator MCP is an MCP server that bridges an AI assistant and a real,
running copy of Adobe Illustrator. Every tool call becomes a small
ExtendScript program that Illustrator executes on the document that is
actually open on the user's screen: not a sandbox, not a one-shot render.
The result is a normal .ai file, layers, artboards, and editable text the
user can keep tweaking by hand after the agent is done.
Use this skill for tasks like "create a poster", "draw three circles and align them", "vectorize this logo", "recolor everything named 'badge'", or "export the artboard as a PNG": any time the user wants to produce or modify vector artwork inside Illustrator rather than get a flat picture back.
Do not reach for this skill for pure image generation (no Illustrator document involved); that's a different kind of tool.
Prerequisites and setup
- Adobe Illustrator installed and, ideally, already running with a document open (most tools auto-launch it, but an already-open document is the whole point of this skill).
- Node.js 18+ and the server built (
npm install && npm run build, producesdist/index.js). - The server already added to the current MCP client's config (Claude
Desktop / Claude Code / Cursor: point at the absolute path of
dist/index.js; ChatGPT: via a local HTTP transport plus secure tunnel). If the Illustrator tools are not visible, tell the user it still needs to be connected. Don't try to install or configure it yourself from inside a chat; point them at the project'sREADME.md(sections "Install" and "Connect it to your AI client") for the exact steps per client. - macOS first run: Illustrator asks for Automation permission the first time a tool runs. If a call fails with "Not authorized to control Illustrator", tell the user to grant it in System Settings → Privacy & Security → Automation.
- To sanity-check the connection without side effects, call
illustrator_get_statusfirst: it never launches Illustrator and just reports whether it's running.
What ships with it
2 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.
- today First seen · 163 lines · 0 tokens per session scan A 5caaa566611d
illustrator-mcp is a skill published in the GitHub repository gherardo200-glitch/illustrator-mcp (7 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 2,370 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
anatomy
Explain an idea as an interactive isometric machine figure.
ip-as-logo
Design minimal cute IP mascot marks readable at 32px.
mono-color
Generate one- or two-ink editorial print poster images.
pr-lens
Draw code changes as animated architecture/data-flow SVGs.
scrollcraft
Premium scroll-driven landing pages; scroll = timeline.
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).