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/satoshiman/mdsvrnpx agentmods add skills/satoshiman/mdsvr/markdown-for-mdsvrWrote 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/satoshiman/mdsvr/markdown-for-mdsvr)<a href="https://agentmods.dev/skills/satoshiman/mdsvr/markdown-for-mdsvr"><img src="https://agentmods.dev/badge/skills/satoshiman/mdsvr/markdown-for-mdsvr/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/satoshiman/mdsvr/markdown-for-mdsvr"><img src="https://agentmods.dev/badge/skills/satoshiman/mdsvr/markdown-for-mdsvr.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 | $0.00111 | $0.02558 |
| Opus 5.5 | $0.00044 | $0.01023 |
| Sonnet 5.5 | $0.00022 | $0.00512 |
| Haiku 4.5 | $0.00011 | $0.00256 |
Grade A, and why
markdown-for-mdsvr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown for mdsvr Skill
Generate a complete, valid, multi-file Markdown documentation set for use with mdsvr — supports both server mode and static export.
When this skill is triggered, produce multiple .md files that form a cohesive
documentation site, following all mdsvr conventions strictly.
Step 1 — Understand the Request
Before generating files, extract from the user's request:
- Topic / product name — what is being documented?
- Target audience — developers, end-users, ops teams, etc.
- Scope — how many pages / sections are needed?
- Language — Vietnamese, English, or bilingual?
- Diagrams needed? — if yes, read
rules/mermaid.mdfor syntax rules. - Quizzes needed? — if the doc set includes self-check questions or chapter
quizzes, read
rules/quiz.mdfor the```quizJSON format. - Math needed? — if the doc set includes formulas or equations, read
rules/math.mdfor the$...$/$$...$$/```mathLaTeX syntax.
If any of these are unclear, ask ONE focused question before proceeding.
Step 2 — Plan the File Structure
Design the file structure before writing content. Prefer a flat structure because it is easier to browse, link, reorder, and maintain:
docs/
├── README.md ← Homepage (required)
├── 01-installation.md
├── 02-quickstart.md
├── 03-configuration.md
├── 04-basic-usage.md
├── 05-advanced.md
├── 06-api-reference.md
└── 07-troubleshooting.md
Create subdirectories only when the documentation is large enough that a flat list becomes difficult to navigate, such as when a section contains many closely related pages or needs its own index. Do not create a subdirectory for only one or two pages. When subdirectories are justified, each must contain a README.md section index.
Adapt the structure to the user's topic and scale it up or down as needed.
Step 3 — Apply mdsvr File & Link Rules (MANDATORY)
What ships with it
3 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.
- 1mo ago Changed · +26 lines 69cd7e3f6959
- 1mo ago Changed · +13 lines dff68c5c165b
- 2mo ago First seen · 227 lines · 111 tokens per session scan A 35e98df69998
markdown-for-mdsvr is a skill published in the GitHub repository satoshiman/mdsvr (6 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 2,558 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 2026-08-31.
markdown-for-mdsvr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| markdown-for-mdsvrsatoshiman/mdsvr | Skill | 6 | 1mo ago | MIT | A | 111 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |