mdview

mdview is a skill for Claude Code, Codex from animalzinc/claude-plugins. It costs 0 tokens per session (2,150 once invoked), scanned A, original, MIT.

A tool that opens a clean, rendered view of a Markdown file in a web browser. Markdown is plain text that uses simple symbols for headings, links, lists, and other formatting.

In plain words
What is it for?
Use it to inspect, proofread, and comment on Markdown documents, then turn inline comments into feedback for the coding agent.
Why use it?
It lets you read and review the formatted document without dealing with raw Markdown syntax or setting up a temporary web page.

Skill for Claude CodeCodex

Part of the mdview plugin — 1 skill shipped together

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 skills/animalzinc/claude-plugins/mdview
Any agent
npx skills add animalzinc/claude-plugins --skill mdview
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins

Made for: Claude Code, Codex.

Or install mdview, the plugin that ships this one along with the rest of its 1 skill.

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 mdview

README.md
[![agentmods](https://agentmods.dev/badge/skills/animalzinc/claude-plugins/mdview.svg)](https://agentmods.dev/skills/animalzinc/claude-plugins/mdview)
Your own site
<a href="https://agentmods.dev/skills/animalzinc/claude-plugins/mdview"><img src="https://agentmods.dev/badge/skills/animalzinc/claude-plugins/mdview.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,150 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02150
Opus 5 $0.00000 $0.01075
Sonnet 5 $0.00000 $0.00430
Haiku 4.5 $0.00000 $0.00215

Measured 5d ago against content hash e225c6875a5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mdview 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (assets/marked.min.js, assets/mermaid.min.js, generate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/mdview/skills/mdview/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: mdview description: Open a clean, rendered (not raw) view of a markdown file in the browser for fast reading, with rich-text copy and an inline-comment to paste-ready-feedback loop. Use when the user says "show me the markdown", "render this markdown", "open that doc so I can read it", "let me review the markdown", "mdview ", or asks to view, read, or proof a .md file you produced. disable-model-invocation: false allowed-tools: []

mdview

Renders a markdown file into a clean, self-contained HTML reading view and opens it in the default browser. The point: the user reads the rendered doc, not the raw syntax, with one command, and can hand back inline comments as a paste-ready prompt. It replaces the "spin up a throwaway HTML file just to read it" step.

This is a lightweight middle ground between a one-off HTML preview and a full collaborative editor. No server, no auth, no live agent editing.

How to invoke

Run the generator bundled with this skill (it sits next to this file as generate.py), passing the absolute path of the markdown file (resolve it first, so this works from any project):

python3 <this-skill-dir>/generate.py /abs/path/to/file.md

On Windows, python3 is usually not a real command: Windows ships a stub under that name that opens the Microsoft Store instead of running anything. Use py -3 there, and fall back to python. If none of the three runs the script, Python 3 is not installed on the machine — say so and point at python.org, rather than retrying variants.

That writes a self-contained file to ~/.cache/mdview/<hash>.html and opens it in the browser. Nothing else to start or stop. Flags (rarely needed): --browser <AppName> to force a specific app (macOS only), --no-open / --print-path to just build and print the path.

To read two files side by side, pass the second with --against:

python3 <this-skill-dir>/generate.py /abs/path/to/current.md --against /abs/path/to/other.md

Read the full file on GitHub · 95 lines

Files

What ships with it

4 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.

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. 5d ago First seen · 95 lines · 0 tokens per session scan A e225c6875a5f

Subscribe to this mod's changes

mdview is a skill published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,150 tokens. 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.