Borrowing it
Nothing to install: this file belongs to ymo6/illustrator-figure-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ymo6/illustrator-figure-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ymo6/illustrator-figure-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/instructions/ymo6/illustrator-figure-mcp/claude-md)<a href="https://agentmods.dev/instructions/ymo6/illustrator-figure-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ymo6/illustrator-figure-mcp/claude-md/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/instructions/ymo6/illustrator-figure-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ymo6/illustrator-figure-mcp/claude-md.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 | $0.01304 | $0.01304 |
| Opus 5 | $0.00652 | $0.00652 |
| Sonnet 5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
illustrator-figure-mcp CLAUDE.md 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
This is a fork of ie3jp/illustrator-mcp-server (MIT), retargeted from general Illustrator automation to one job: rebuilding scientific figures as editable artwork, with proof that the result is structurally correct.
Upstream gave us hands — 66 Illustrator tools, UUID identity, note metadata, PNG export. It had no way to prove a rebuilt figure is right. That proof is what this fork adds.
Do not publish
Upstream's release process (npm publish via CI, MCP Registry, mcpb attachment) does not apply here and its CLAUDE.md describing it has been replaced by this file. The npm publish job has been removed from CI. Do not publish this package, do not tag releases expecting a publish, and do not push to upstream.
The upstream remote points at ie3jp's repository. Fetch from it to merge improvements; never push to it.
The two channels
The whole design rests on separating two kinds of evidence:
| Channel | Mechanism | Proves |
|---|---|---|
| Geometry | audit_figure — deterministic, read-only |
internal correctness: containment, alignment, text fit, connector routing, raster declarations, trace signatures |
| Appearance | export to PNG, compared by the model against the reference crop |
resemblance |
Neither is sufficient. A traced figure passes every geometric check and is worthless; a good-looking render says nothing about structure. Never let audit_figure returning passed: true be reported as "the figure is correct" — it means "no hard geometric failure".
Layout
src/jsx/helpers/common.jsx upstream helpers — keep merges clean, edit sparingly
src/jsx/helpers/sifm.jsx this fork's helpers (prepended to every tool call)
src/jsx/audit.jsx the auditor — loaded on demand
src/jsx/connector.jsx connector emulation — loaded on demand
src/jsx/sequence.jsx batched construction — loaded on demand
src/tools/utility/audit-figure.ts
src/tools/modify/{add-connector,reflow-connectors,draw-sequence,raster-gate}.ts
skills/ the four Claude Code role skills
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.
- 8d ago First seen · 69 lines · 1,304 tokens per session scan A 529b8e0e872b
illustrator-figure-mcp CLAUDE.md is an instructions file published in the GitHub repository ymo6/illustrator-figure-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 1,304 tokens to every session, about $0.0065 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.