agentmods.dev

markview CLAUDE.md

markview CLAUDE.md is an instructions file for coding agents from paulhkang94/markview. It costs 1,604 tokens per session, scanned A, original, MIT.

A development guide for MarkView, a macOS app that previews and processes HTML files, with an MCP server for AI tool integration. It maps the Swift libraries, app targets, extensions, command-line tools, and checks.

In plain words
What is it for?
Use it when changing MarkView rendering, previews, file watching, Quick Look support, MCP tools, or automated browser tests.
Why use it?
It shows how the different parts fit together and provides the commands needed to build, test, verify, and package the app.

Instructions file

not rated 38 13d ago A scan 1,604 tokens original MIT
View the source file paulhkang94/markview paulkang.dev
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/paulhkang94/markview/claude-md
Clone the repo
git clone --depth 1 https://github.com/paulhkang94/markview

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 markview CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paulhkang94/markview/claude-md.svg)](https://agentmods.dev/instructions/paulhkang94/markview/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paulhkang94/markview/claude-md"><img src="https://agentmods.dev/badge/instructions/paulhkang94/markview/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,604 This file is loaded in full into every session.
When invoked 1,604 The same file — it is already loaded in full.
Security scan A 1 finding. 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 5.1 $0.01604 $0.01604
Opus 5 $0.00802 $0.00802
Sonnet 5 $0.00321 $0.00321
Haiku 4.5 $0.00160 $0.00160

Measured 5d ago against content hash 9229127c9cbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

markview CLAUDE.md scanned grade A with 1 finding 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.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. The npm package name is `mcp-server-markview`. Never curl the npm registry with a guessed name — always run the script.
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.

MarkView — AI Development Guide

Quick Reference

  • Build: swift build
  • Test: swift run MarkViewTestRunner (304 Swift tests + 91 MCP tests + script tests)
  • Playwright e2e: make playwright (66 tests — builds fixture binary, runs Playwright, installs MarkView.app)
  • Verify all: python3 scripts/verify.py (writes verify stamp automatically on pass)
  • App bundle: bash scripts/bundle.sh --install
  • MCP tests: bash scripts/test-mcp.sh
  • PHK debug logging: PHK_DEBUG=1 swift run MarkViewTestRunner (verbose HTML pipeline output)

Architecture

Hybrid SPM + Xcode (XcodeGen) — .xcodeproj is gitignored, regenerate with xcodegen generate.

Target Type Purpose
MarkViewCore SPM library Rendering, file watching, linting — no UI deps
MarkView Xcode app SwiftUI app with WKWebView preview
MarkViewQuickLook Xcode extension Quick Look preview provider
MarkViewMCPServer SPM executable MCP server for AI tool integration
MarkViewTestRunner SPM executable Full test suite (no XCTest dependency)
MarkViewHTMLGen SPM executable CLI fixture generator for Playwright tests

Key files:

  • Sources/MarkViewCore/MarkdownRenderer.swift — core GFM rendering via swift-cmark
  • Sources/MarkViewCore/HTMLPipeline.swift — full injection pipeline (Prism → Mermaid → KaTeX → controls)
  • Sources/MarkViewCore/template.html — preview HTML template with Prism.js
  • Sources/MarkViewMCPServer/main.swift — MCP server (tools: preview_markdown, open_file)
  • Sources/MarkViewHTMLGen/main.swift — Playwright fixture generator (used by make playwright)
  • Sources/MarkViewApp/ — SwiftUI views
  • project.yml — XcodeGen config (source of truth for Xcode targets)
  • tests/ — Playwright e2e test suite (Node.js, Chromium)

MCP Tools (for AI integration)

The MarkViewMCPServer exposes two tools:

preview_markdown — render markdown content in MarkView:

{ "content": "# Hello\nThis is **markdown**" }

Writes to a temp file and opens in MarkView with live reload.

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. 5d ago First seen · 114 lines · 1,604 tokens per session scan A 9229127c9cbc

Subscribe to this mod's changes

markview CLAUDE.md is an instructions file published in the GitHub repository paulhkang94/markview (38 stars, last pushed 13d ago), licensed MIT. It adds 1,604 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsgfmmacosmarkdownmarkdown-previewnative-appswift
Related

Other instructions, from other repositories

mindle AGENTS.md

AGENTS.md instructions for nonatofabio/mindle, covering agents.md, what mindle is — and isn't, tenets, architecture in 60 seconds and coding style.

nonatofabio/mindle · 3,255 tokens

Peekaboo AGENTS.md

AGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions.

openclaw/Peekaboo · 1,070 tokens

Applite CLAUDE.md

Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.

milanvarady/Applite · 2,572 tokens

scarf AGENTS.md

AGENTS.md instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant…

awizemann/scarf · 1,827 tokens

palmier-pro AGENTS.md

AGENTS.md instructions for palmier-io/palmier-pro, covering palmierpro, build, agents, engineering approach and code style.

palmier-io/palmier-pro · 6,680 tokens

scarf copilot-instructions.md

Copilot instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be…

awizemann/scarf · 571 tokens