Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ngocsangyem/MeowKitnpx agentmods add skills/ngocsangyem/meowkit/markdown-readerWrote 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.
[](https://agentmods.dev/skills/ngocsangyem/meowkit/markdown-reader)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/markdown-reader"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/markdown-reader/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.
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/markdown-reader"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/markdown-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00081 | $0.00789 |
| Opus 5 | $0.00041 | $0.00394 |
| Sonnet 5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
mk:markdown-reader 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mk:markdown-reader
Local HTTP server rendering markdown files with a calm, book-like reading experience.
Note: mk:brainstorming --html and mk:plan-creator --html produce self-contained
HTML files that open directly in the browser — they do not use or need this server.
Installation (Required Before First Use)
This skill requires npm dependencies. Install once from the project root:
cd .claude/skills/markdown-reader
npm install
Dependencies: marked, highlight.js, gray-matter
Without installation you will get Error 500: Error rendering markdown.
Usage
# View a markdown file (opens browser automatically)
node .claude/skills/markdown-reader/scripts/server.cjs \
--file ./tasks/plans/my-plan/plan.md
# Browse a directory
node .claude/skills/markdown-reader/scripts/server.cjs \
--dir ./tasks/plans
# Background mode (foreground process for Claude Code task runners)
node .claude/skills/markdown-reader/scripts/server.cjs \
--file ./README.md \
--foreground
# Stop all running instances
node .claude/skills/markdown-reader/scripts/server.cjs --stop
The server binds to 127.0.0.1 (localhost) only. Served files are not reachable from
other devices on the network — this is intentional.
Lifecycle
Start with --file or --dir; use --foreground when the host needs to keep the process
attached. The default port is 3456 and increments through 3500 if busy. End the lifecycle with
--stop; never leave a reader process running after the task.
| Need | Route |
|---|---|
| CLI flags, routes, persistent state | references/reader-operations.md |
| Reader features, plan navigation, shortcuts, Mermaid | references/reader-experience.md |
| Architecture and troubleshooting | references/reader-operations.md |
The server binds only to 127.0.0.1. It validates every file against its allowed directories;
traversal attempts return 403. Referenced images must be relative to the source markdown file.
What ships with it
24 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.
- assets/directory-browser.css 2.9 KB
- assets/favicon.ico 15 KB
- assets/novel-theme.css 612 B
- assets/reader.js 26 KB runs code
- assets/styles/novel-theme-base.css 1013 B
- assets/styles/novel-theme-components.css 3.8 KB
- assets/styles/novel-theme-content.css 2.9 KB
- assets/styles/novel-theme-header.css 3.9 KB
- assets/styles/novel-theme-mermaid.css 3.1 KB
- assets/styles/novel-theme-overlays.css 3.6 KB
- assets/styles/novel-theme-responsive.css 4.5 KB
- assets/styles/novel-theme-sidebar.css 6.2 KB
- assets/styles/novel-theme-variables.css 1.4 KB
- assets/template.html 6.0 KB
- package.json 368 B
- references/reader-experience.md 625 B
- references/reader-operations.md 1.1 KB
- scripts/lib/http-server.cjs 11 KB runs code
- scripts/lib/markdown-renderer.cjs 9.7 KB runs code
- scripts/lib/plan-navigator.cjs 10 KB runs code
- scripts/lib/plan-table-parser.cjs 9.9 KB runs code
- scripts/lib/port-finder.cjs 1.2 KB runs code
- scripts/lib/process-mgr.cjs 3.7 KB runs code
- scripts/server.cjs 9.6 KB runs code
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.
- 8d ago First seen · 88 lines · 81 tokens per session scan A 532843676829
mk:markdown-reader is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 789 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
document_export
Export text content to various formats (PDF, Excel, Markdown, Mermaid mindmap).
code-to-diagram
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…