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 agentmods add skills/mdcms-ai/mdcms/mdcms-setupnpx skills add mdcms-ai/mdcms --skill mdcms-setupgit clone --depth 1 https://github.com/mdcms-ai/mdcmsWhat 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 | $0.00155 | $0.01911 |
| Opus 5 | $0.00077 | $0.00955 |
| Sonnet 5 | $0.00031 | $0.00382 |
| Haiku 4.5 | $0.00015 | $0.00191 |
Grade A, and why
mdcms-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf "$MDCMS_SERVER_URL/healthz" && echo ok How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDCMS Setup (Master Orchestrator)
Walk the user end-to-end through adding MDCMS to their project. Your job is to detect which phase they are in, delegate to the focused skill that owns that phase, and return here for the next decision.
When to use this skill
Any user intent to add, install, configure, or integrate MDCMS. You are the entry point to the MDCMS skill pack. Do not implement phase work yourself — delegate.
Phases
Work through these sequentially. For each phase, decide whether the user is done already, then either skip or invoke the focused skill. Always say what you're doing and why before you do it.
Phase 1 — Is an MDCMS backend reachable?
Ask the user where their MDCMS server lives.
- If they have a hosted or self-hosted URL they know works: continue.
- If they plan to self-host: invoke
mdcms-self-host-setup. - If they have no server and don't want to self-host: stop. MDCMS needs a backend for the rest of the flow to do anything meaningful.
Verify reachability before continuing:
curl -sf "$MDCMS_SERVER_URL/healthz" && echo ok
If this fails, fix it before moving on.
Phase 2 — Greenfield or brownfield?
Check whether the user's repo already has Markdown or MDX content that MDCMS should manage. Exclude the places where markdown commonly appears but is not user content — repo-level docs, skill packs (including this one), issue/PR templates, and dependency directories:
find . -type f \( -name '*.md' -o -name '*.mdx' \) \
-not -path '*/node_modules/*' \
-not -path '*/.*' \
-not -path './skills/*' \
-not -path './docs/*' \
-not -path './apps/docs/*' \
-not -path './.github/*' \
-not -name 'README*' \
-not -name 'CHANGELOG*' \
-not -name 'LICENSE*' \
-not -name 'SKILL.md' \
| head
If this surfaces files, ask the user which of the top-level directories (content/, pages/, posts/, or a project-specific path) are actually editorial content vs. product docs. Only editorial content belongs in MDCMS.
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.
- 2d ago First seen · 131 lines · 155 tokens per session scan A 9d04a17b9781
mdcms-setup is a skill published in the GitHub repository mdcms-ai/mdcms (22 stars, last pushed 3d ago), licensed MIT. It adds 155 tokens to every session and 1,911 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
wordpress-plugin-to-emdash
Port a WordPress plugin to EmDash CMS. Use this skill when asked to migrate, convert, or port a WordPress plugin, theme functionality, or custom post type to EmDash. Provides concept mapping and implementation patterns.
review
Review one pull request for real bugs, regressions, and convention violations. Enumerate candidate issues across the whole diff, verify each against the code, then return structured line-anchored findings and a verdict. Read-only on GitHub; the orchestrator posts the review.
writing-emdash-docs
Write, revise, and review EmDash documentation for technical accuracy, useful structure, house style, and natural prose. Use when working on user documentation, guides, API reference pages, migration or upgrade guides, READMEs, contributor documentation, technical specifications, or release notes in the EmDash…
building-emdash-site
Build and customize EmDash CMS sites on Astro. Use when creating pages, defining collections, writing seed files, querying content, rendering Portable Text, setting up menus/taxonomies/widgets, configuring deployment, or any task involving an EmDash-powered Astro site. Assumes basic Astro knowledge but provides all…
emdash-cli
Use the EmDash CLI to manage content, schema, media, and more. Use this skill when you need to interact with a running EmDash instance from the command line — creating content, managing collections, uploading media, generating types, or scripting CMS operations.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.