excalidraw-icons-mcp: Instructions file for Claude Code

CLAUDE.md

excalidraw-icons-mcp CLAUDE.md is an instructions file for Claude Code from iagogfe/excalidraw-icons-mcp. It costs 1,233 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that lets an AI client search vendor icons and work with an Excalidraw canvas. Excalidraw is a tool for making diagrams and hand-drawn-style drawings.

In plain words
What is it for?
Use them when developing the icon search, canvas server, automated checks, container images, or CI workflows.
Why use it?
They clarify how to install, build, run, test, and distribute the TypeScript project, including its current testing limitations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is iagogfe/excalidraw-icons-mcp's own configuration. It tells Claude Code how to work on excalidraw-icons-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything excalidraw-icons-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iagogfe/excalidraw-icons-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.

Copy the file
curl -O https://raw.githubusercontent.com/iagogfe/excalidraw-icons-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/iagogfe/excalidraw-icons-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for excalidraw-icons-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/iagogfe/excalidraw-icons-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/iagogfe/excalidraw-icons-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/iagogfe/excalidraw-icons-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iagogfe/excalidraw-icons-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.

agentmods 80×15 button for excalidraw-icons-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/iagogfe/excalidraw-icons-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iagogfe/excalidraw-icons-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,233 This file is loaded in full into every session.
When invoked 1,233 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01233 $0.01233
Opus 5 $0.00616 $0.00616
Sonnet 5 $0.00247 $0.00247
Haiku 4.5 $0.00123 $0.00123

Measured 11d ago against content hash 9b078bd40247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

excalidraw-icons-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 11d 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.

CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

excalidraw-icons-mcp

MCP server for Excalidraw with vendor-icon search (AWS/Azure/GCP/OCI/Kubernetes), plus a canvas server the MCP talks to over HTTP. TypeScript, Node >= 20, npm. Public repository, MIT.

  • Install: npm ci
  • Type check: npm run type-check
  • Build: npm run build (frontend via Vite, server via tsc)
  • Run locally: npm run canvas then point an MCP client at dist/index.js
  • Tests: the test:* scripts are standalone probes (scripts/*.mjs), not a suite. There is no npm test yet — adding one is the single highest-value change to this repo's CI.
  • Linter: none. The style gate is the only automated style check.

Distribution is by container image (ghcr.io/iagogfe/excalidraw-icons-mcp and -canvas) and by cloning. The npm package name is reserved in package.json but has never been published.

CI

Four workflows, all self-contained. The style gate is vendored under .github/actions/gate-estilo, and changes to it have to be carried across by hand when the shared implementation changes.

  • ci.yml — build matrix (Node 20/22/24), testes determinísticos, E2E Playwright e style gate
  • security.yml — Gitleaks, osv-scanner, Semgrep, CodeQL
  • docker.yml — Hadolint, build, Trivy, publish to ghcr.io
  • scorecard.yml — OpenSSF Scorecard (public repositories only)

Actions are pinned by full SHA with the version in a trailing comment; tags are mutable and were the vector of the tj-actions and trivy-action attacks. Dependabot bumps both together.

Conventions

Rules tagged [gate] are measured on every PR by .github/actions/gate-estilo, which compares this branch against the base and fails if the count got worse. Old debt never blocks — only what the PR adds. Where the gate threshold differs from the rule, the rule is the target and the threshold is the point where you get interrupted. To exclude vendored or generated code, list the globs in a .gate-estilo-ignore file at the root; this repo does not need one today.

On a pull request from a fork the token is read-only, so the gate cannot post its comment. It still runs and still fails — the table goes to the job summary.

Read the full file on GitHub · 114 lines

Changes

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.

  1. 11d ago First seen · 114 lines · 1,233 tokens per session scan A 9b078bd40247

Subscribe to this mod's changes

excalidraw-icons-mcp CLAUDE.md is an instructions file published in the GitHub repository iagogfe/excalidraw-icons-mcp (31 stars, last pushed 20d ago), licensed MIT. It adds 1,233 tokens to every session, about $0.0062 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens