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 satoshiman/mdsvr --skill mdsvr-course-generatorgit clone --depth 1 https://github.com/satoshiman/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/mdsvr-course-generator)<a href="https://agentmods.dev/skills/satoshiman/mdsvr/mdsvr-course-generator"><img src="https://agentmods.dev/badge/skills/satoshiman/mdsvr/mdsvr-course-generator/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/mdsvr-course-generator"><img src="https://agentmods.dev/badge/skills/satoshiman/mdsvr/mdsvr-course-generator.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 | $0.00200 | $0.01919 |
| Opus 5.5 | $0.00080 | $0.00768 |
| Sonnet 5.5 | $0.00040 | $0.00384 |
| Haiku 4.5 | $0.00020 | $0.00192 |
Grade A, and why
mdsvr-course-generator 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdsvr Course Generator
Create a personalized course as a set of .md files served by mdsvr.
The course is shaped by a survey of the learner first, never by a generic template.
Core principles
- Survey before writing. Never generate lessons before the brief is confirmed.
- Context-driven questions. Round 2 questions MUST be derived from the topic and the learner's Round 1 answers. Generic questions are a failure.
- Time-based ratio. The theory : practice ratio is measured by estimated learning time, not by number of lessons or word count.
- Expert perspective. Every lesson teaches what experts prioritize, not just facts.
- No artificial limits. Course size follows the requested knowledge scope. Only shorten when the user explicitly asks to condense.
Reference files (read when needed)
| File | Read when |
|---|---|
references/mdsvr-rules.md |
Before writing ANY file. Contains the mdsvr file, link, heading, frontmatter, callout and Mermaid rules |
references/survey-guide.md |
Starting Step 1 and Step 2 (question bank and how to derive contextual questions) |
references/lesson-templates.md |
Step 4 and Step 5 (syllabus, lesson, quiz, expert corner, cheatsheet templates) |
If the environment also has the markdown-for-mdsvr skill, read it too and prefer it
where it is more detailed — especially rules/mermaid.md for the full Mermaid syntax
reference. If not, references/mdsvr-rules.md is sufficient. Never skip the rules
because another skill is missing.
Step 0 — Capture the request
Extract from the user's message what is already known: topic, goal, audience, language, output location, constraints. Do NOT ask about anything already stated.
Language: use the language the user requests. If none is requested, use the language the user is writing in, and confirm it in the Step 3 brief.
Output location: if the user specified a directory, use it. Otherwise default to
./<course-slug>/ in the current working directory and confirm it in the Step 3 brief.
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 First seen · 182 lines · 200 tokens per session scan A cf5208129e87
mdsvr-course-generator is a skill published in the GitHub repository satoshiman/mdsvr (6 stars, last pushed 1mo ago), licensed MIT. It adds 200 tokens to every session and 1,919 once invoked, about $0.0008 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 2026-10-06.
mdsvr-course-generator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mdsvr-course-generatorsatoshiman/mdsvr | Skill | 6 | 1mo ago | MIT | A | 200 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |