dgmo-mcp: Instructions file for Claude Code

CLAUDE.md

dgmo-mcp CLAUDE.md is an instructions file for Claude Code from diagrammo/dgmo-mcp. It costs 3,740 tokens per session, scanned A, original, MIT.

Instructions for dgmo-mcp, an MCP server that lets compatible coding tools create, check, and render DGMO diagrams. MCP is a standard way for AI clients to connect to external tools and servers.

In plain words
What is it for?
Use it when working on dgmo-mcp commands, transports such as stdio or HTTP, tests, formatting checks, trigger checks, or release preparation.
Why use it?
It explains how to build, test, validate, run, and release this diagram server correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is diagrammo/dgmo-mcp's own configuration. It tells Claude Code how to work on dgmo-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 dgmo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to diagrammo/dgmo-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/diagrammo/dgmo-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/diagrammo/dgmo-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 dgmo-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/diagrammo/dgmo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/diagrammo/dgmo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,740 This file is loaded in full into every session.
When invoked 3,740 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 $0.03740 $0.03740
Opus 5.5 $0.01496 $0.01496
Sonnet 5.5 $0.00748 $0.00748
Haiku 4.5 $0.00374 $0.00374

Measured 15d ago against content hash 2f8be4604e3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dgmo-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 15d 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dgmo-mcp — @diagrammo/dgmo-mcp

The MCP server that gives Claude Code, Claude Desktop, Cursor and any MCP client the ability to author, validate and render DGMO — over stdio, or over streamable HTTP since 0.19.0. Published to npm as @diagrammo/dgmo-mcp, listed on the MCP registry as io.github.diagrammo/dgmo-mcp, and shipped as a .mcpb bundle on the GitHub release.

Commands

pnpm build            # tsup — 4 ESM entries + .d.ts
pnpm test             # vitest run
pnpm check:all        # deadcode + duplication + deps + test — what CI runs, and the gate before a release
pnpm check:triggers   # drift guard: triggers.json vs dgmo-content/registry.json — NOT in check:all, NOT in CI
./preflight.sh        # version sync, pack, fresh-install MCP probe. Runs on tag push (.githooks/pre-push). Runs NO tests
pnpm studio           # guidance studio (the README's `pnpm hub` / `pnpm harness` scripts do not exist)
pnpm studio:report    # write the studio session out to a committed results/<date>.md — the run's only shareable output

✅ check:all enforces prettier — format:check runs first in the gate, so pnpm format is safe to run bare. If check:all fails on formatting, run pnpm format and commit that alone — never as a rider on a feature.

Depending on dgmo

It consumes the published @diagrammo/dgmo from npm, never the workspace checkout — there is no symlink here, unlike the app. Workspace dgmo edits are invisible until dgmo is published and the dep bumped, or until pnpm link ../dgmo (see CONTRIBUTING.md; pnpm install undoes it).

🔴 Since 2026-08-07 the library is a devDependency and is INLINED into the bundle (noExternal in tsup.config.ts), exactly as @diagrammo/dgmo-cli does it. Declaring it at runtime meant every install of this server — and every npm i -g @diagrammo/dgmo-cli, which spawns it — unpacked the library plus its d3, dagre and lz-string trees: 17,028 KB, on top of a CLI bundle that already inlines the same library and never loads that copy. A CLI install measured 73,956 KB before and 63,344 KB after.

Read the full file on GitHub · 76 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. 15d ago Changed · +1 lines · +123 tokens per session 2f8be4604e3d
  2. 20d ago Changed · +3 lines · +278 tokens per session 8db9b4fff5ff
  3. 1mo ago Changed · +1 lines · +143 tokens per session 22a3879b9341
  4. 1mo ago Changed · -206 tokens per session fcfc746d88d2
  5. 1mo ago Changed · +1 lines · +29 tokens per session 60a36bcc7866
  6. 2mo ago First seen · 70 lines · 3,373 tokens per session scan A 56de33cd5c0a

Subscribe to this mod's changes

dgmo-mcp CLAUDE.md is an instructions file published in the GitHub repository diagrammo/dgmo-mcp (3 stars, last pushed today), licensed MIT. It adds 3,740 tokens to every session, about $0.0150 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 2026-08-31.

Related

dgmo-mcp CLAUDE.md compared with instructions from other repositories

dgmo-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dgmo-mcp CLAUDE.mddiagrammo/dgmo-mcpInstructions file3todayMITA3,740Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281ktodayMITA4,335Codex, OpenCode