What is mmdp CLAUDE.md?

A macOS command-line preview tool for displaying Mermaid diagrams in a frameless native window. Mermaid is a text format for describing diagrams such as flowcharts and sequences.

Use it to preview Mermaid text from standard input, Mermaid files, or Markdown files. File previews can support live reloading while the file changes.

It lets coding agents inspect diagrams visually without waiting for a command to remain running, and can reuse an already open preview window.

mmdp CLAUDE.md — Instructions file by mxcoppell

Install

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.

agentmods

npx agentmods add instructions/mxcoppell/mmdp/claude-md

Clone the repo

git clone --depth 1 https://github.com/mxcoppell/mmdp

Per session 1,301 This file is loaded in full into every session.

When invoked 1,301 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01301	$0.01301
Opus 5	$0.00651	$0.00651
Sonnet 5	$0.00260	$0.00260
Haiku 4.5	$0.00130	$0.00130

Measured 2d ago against content hash 44bd3d9e8a25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mmdp 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 2d 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 · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mmdp

Lightweight CLI to preview Mermaid diagrams in a native frameless window (macOS only).

For LLM Agents

To display a mermaid diagram, pipe it to stdin. The CLI opens a native frameless window and exits immediately (exit code 0).

echo "graph TD; A-->B-->C" | mmdp

On success, the CLI prints Previewing <name> to stdout so agents can confirm the window opened. If a file is already open, it prints Previewing <name> (reused) and activates the existing window (no duplicate).

This is the recommended way for agents to show diagrams. The window stays open after the CLI exits.

You can also preview an existing file (this starts a server with live reload):

mmdp diagram.mmd

Quick Usage

# Fire-and-forget preview (stdin — CLI exits immediately)
echo "graph LR; A-->B" | mmdp

# Live preview with file watching
mmdp diagram.mmd

# Multiple files — each gets its own window
mmdp flow.mmd sequence.mmd arch.md

# Extracts ```mermaid blocks from markdown
mmdp README.md

Flags

Flag	Default	Description
`-p, --port PORT`	auto	Server port
`-t, --theme THEME`	system	dark, light, or system
`-w, --no-watch`	false	Disable file watching
`--poll INTERVAL`	-	Stat-based polling (e.g. 500ms)
`--verbose`	false	Show informational messages on stderr
`-v, --version`	-	Print version
`-h, --help`	-	Print help

Exit Codes

0 — success
1 — argument error (bad flags, missing file)
2 — runtime error (port in use, read failure)

Output Format

Stdout (agent-consumable confirmation):

Previewing flowchart.mmd              # new window opened
Previewing flowchart.mmd (reused)     # existing window activated
Previewing stdin                      # stdin input

Stderr (structured diagnostics, --verbose for info messages):

mmdp: listening on http://127.0.0.1:52341 (flow.mmd)  # --verbose only
mmdp: shutting down
mmdp: error: <message>                                # exit code 1 or 2

Read the full file on GitHub · 141 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.

2d ago First seen · 141 lines · 1,301 tokens per session scan A 44bd3d9e8a25

Subscribe to this mod's changes

mmdp CLAUDE.md is an instructions file published in the GitHub repository mxcoppell/mmdp (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,301 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.

Creative and media ai-agents claude-code cli live-reload macos mermaid

mmdp CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

mmdp

For LLM Agents

Quick Usage

Flags

Exit Codes

Output Format

What this file has done since we first saw it

Other instructions, from other repositories

markout CLAUDE.md

Applite CLAUDE.md

wispterm AGENTS.md

HomeClaw AGENTS.md

best-claude-hud AGENTS.md

moonproxy-desktop AGENTS.md