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 evan-steinhilb/md2hd --skill writing-md2hd-mapsgit clone --depth 1 https://github.com/evan-steinhilb/md2hdWrote 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/evan-steinhilb/md2hd/writing-md2hd-maps)<a href="https://agentmods.dev/skills/evan-steinhilb/md2hd/writing-md2hd-maps"><img src="https://agentmods.dev/badge/skills/evan-steinhilb/md2hd/writing-md2hd-maps/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/evan-steinhilb/md2hd/writing-md2hd-maps"><img src="https://agentmods.dev/badge/skills/evan-steinhilb/md2hd/writing-md2hd-maps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 340 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00094 | $0.04225 |
| Opus 5 | $0.00047 | $0.02112 |
| Sonnet 5 | $0.00019 | $0.00845 |
| Haiku 4.5 | $0.00009 | $0.00422 |
Grade A, and why
writing-md2hd-maps 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 10d 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 — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing markdown for md2hd
md2hd turns a folder of markdown into a graph. Every YAML frontmatter block is a
node, rel: entries and [[wikilinks]] are edges, the prose under a
block is that node's notes, and one block with type: map configures the
whole map.
The governing fact: the parser never rejects anything. Malformed YAML, a misspelled setting, a block that never opened — all of it parses to something and draws something. There is no error state. Every mistake below is silent, so the job is not "does it parse" but "does it draw what I meant".
Everything in this document was verified against the parser (src/lib/parse.ts
in the md2hd repo). Where a friendlier user guide disagrees, this wins.
The shape of a file
One file may hold the whole map. A --- line opens a new block, and the body
runs until the next line that opens one.
---
type: map
title: Partnerships
---
---
id: riverside-council
type: org
title: Riverside City Council
---
Prose here is this node's notes.
---
id: dana-whitfield
type: person
title: Dana Whitfield
---
And this is Dana's.
- Blank lines around blocks are optional. Tight
---runs parse identically. - Prose before the first block is dropped. It belongs to no node.
- A
---followed by prose stays a horizontal rule and remains inside the current node's body. Only a---whose next non-blank line looks like a YAML key opens a block, which is why existing notes full of rules still work. ***and___never open a block.
The rule that decides it
The line after --- must match /^[A-Za-z_][\w .-]*\s*:(\s|$)/.
Line after --- |
Opens a block? | Why |
|---|---|---|
id: acme |
yes | letter, colon, space |
id:acme |
no | needs whitespace or end-of-line after the colon |
rel: |
yes | colon at end of line is fine |
_id: acme |
yes | leading underscore allowed |
2026: thing |
no | must start [A-Za-z_] |
my key.v: x |
yes | spaces, dots, hyphens legal inside a key |
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.
- 10d ago First seen · 459 lines · 94 tokens per session scan A af203cace77a
writing-md2hd-maps is a skill published in the GitHub repository evan-steinhilb/md2hd (132 stars, last pushed 14d ago), licensed MIT. It adds 94 tokens to every session and 4,225 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.