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.
npx skills add ngocsangyem/MeowKit --skill previewgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/preview)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/preview"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/preview/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/preview"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/preview.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 | $0.00092 | $0.02418 |
| Opus 5.5 | $0.00037 | $0.00967 |
| Sonnet 5.5 | $0.00018 | $0.00484 |
| Haiku 4.5 | $0.00009 | $0.00242 |
Grade A, and why
mk:preview 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 2mo 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mk:preview
Generates visual artifacts — markdown and self-contained HTML — for explaining code, drawing diagrams, building slide decks, and visualizing diffs. Rendering a plan as HTML belongs to mk:visual-plan.
No live server. No Python. Pure markdown + HTML + bash file operations. Output writes to tasks/plans/{active-plan}/visuals/ when an active plan exists; otherwise falls back to tasks/visuals/.
When to Use
- A reader needs to understand an unfamiliar code path, protocol, or architecture
- A diagram (flowchart, sequence, ER) would communicate the topology faster than prose
- Step-by-step content benefits from slides over a single long page
- A pre-PR diff review needs visual KPIs, file map, and change cards
- Stakeholders prefer a self-contained HTML page they can open in a browser without a server
For rendering a plan directory as a shareable HTML page, use mk:visual-plan.
Default (No Arguments)
If invoked with no arguments, present available operations via AskUserQuestion. Header: "Preview Operation". Question: "What would you like to do?".
| Operation | Description |
|---|---|
--explain |
Markdown visual explanation (ASCII + Mermaid + prose) |
--diagram |
Markdown diagram (ASCII + Mermaid) |
--slides |
Markdown presentation slides |
--ascii |
Terminal-friendly ASCII diagram only |
--html --explain |
Self-contained HTML explanation, opens in browser |
--html --diagram |
HTML diagram with zoom/pan controls |
--html --slides |
Magazine-quality HTML slide deck |
--html --diff |
HTML diff visualization (KPI grid + file map + cards) |
Recommended default: --explain or --html --explain.
Usage
Markdown Generation
What ships with it
8 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.
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.
- 2mo ago First seen · 187 lines · 92 tokens per session scan A 359fa9e259d7
mk:preview is a skill published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 7d ago), licensed MIT. It adds 92 tokens to every session and 2,418 once invoked, about $0.0004 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 2026-09-03.
mk:preview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mk:previewngocsangyem/MeowKit | Skill | 15 | 7d ago | MIT | A | 92 | Claude Code |
| deck-course-modulenexu-io/html-anything | Skill | 9.5k | today | Apache-2.0 | A | 25 | Claude Code, Codex |
| mermaid-diagramwecode-ai/Wegent | Skill | 885 | today | Apache-2.0 | A | 102 | Claude Code, Codex |
| mermaid-diagramPM-Shawn/Abu-Cowork | Skill | 419 | today | Apache-2.0 | A | 104 | Claude Code |
| mermaid-skillAgents365-ai/mermaid-skill | Skill | 205 | 2mo ago | MIT | B | 137 | Claude Code, Codex |
| tech-diagramdesirecore/market | Skill | 2 | today | MIT | A | 210 | Claude Code |
| diagram-creatorclaude-office-skills/skills | Skill | 568 | 9mo ago | MIT | A | 34 | Claude Code, Codex |