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 HoangYell/markdy-com --skill markdy-diagram-authorgit clone --depth 1 https://github.com/HoangYell/markdy-comWrote 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/hoangyell/markdy-com/markdy-diagram-author)<a href="https://agentmods.dev/skills/hoangyell/markdy-com/markdy-diagram-author"><img src="https://agentmods.dev/badge/skills/hoangyell/markdy-com/markdy-diagram-author/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/hoangyell/markdy-com/markdy-diagram-author"><img src="https://agentmods.dev/badge/skills/hoangyell/markdy-com/markdy-diagram-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01506 |
| Opus 5 | $0.00029 | $0.00753 |
| Sonnet 5 | $0.00012 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
markdy-diagram-author 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 7d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdy Diagram Authoring Skill
This skill guides AI agents in authoring production-grade, 60fps kinetic architecture diagrams and verified blueprints using the MarkdyScript DSL.
🧭 Scenario Recipe Router
When user prompts match a common architectural domain, start from a proven blueprint:
| Scenario / Domain | Recipe ID | Primary Pattern |
|---|---|---|
| Cache-Aside / Fast Lookups | cache-aside |
Gateway → Service → Redis (Hit) / Postgres (Miss & Warm) |
| Event-Driven / CDC | event-driven-eda |
Service → DB WAL → Debezium CDC → Kafka → Consumers |
| CQRS & Event Sourcing | cqrs-event-sourcing |
Command API → EventStore → Projection Engine → Read DB |
| Microservices Mesh | api-gateway-mesh |
Envoy Ingress → mTLS Sidecars → Distributed Tracing |
| Zero-Trust & Enclave | zero-trust-security |
WAF → OIDC Auth → OPA Policy → AWS Nitro Enclave → Vault |
| Medallion Lakehouse | medallion-lakehouse |
Kafka → Bronze Lake → Spark Cleansing → Silver → Gold Tier |
| Agentic AI & ReAct | agentic-react-tools |
Workspace → Agent Core → Vector RAG → LLM → MCP Tools |
| Active-Active Resilient | active-active-failover |
GeoDNS → Multi-Region Clusters → Bidirectional DB Sync |
| Raft Distributed Consensus | distributed-consensus-raft |
Client → Leader → Follower Quorum → Committed State |
| SRE Incident Runbook | incident-runbook |
Prometheus Alert → PagerDuty → K8s Auto-Healer → Slack Bot |
CLI Helper: Run
markdy guide "<query>"ormarkdy recipe <recipe-id>to output instant canonical MarkdyScript.
🏗️ 4-Step Diagram Structure
Every MarkdyScript file (.markdy or .mdy) follows a clean 4-part structure:
# 1. Directives: Canvas size, theme, and layout flow
scene "Distributed Payment Processing" theme=midnight width=1440 height=800
layout LR
# 2. Node Declarations: <kind> <Id> ["Human Label"] [icon=<glyph>] [@src="path/file.ts#L10"]
browser Client "Web / Mobile Client" icon=chrome
gateway Gateway "Kong API Gateway" icon=nginx @src="src/gateway/router.ts#L15"
service OrderSvc "Order Service" icon=nodejs @src="src/orders/service.ts#L30"
service PaySvc "Payment Service" icon=golang @src="src/payment/handler.go#L40"
queue Kafka "Kafka Event Stream" icon=kafka
database OrdersDB "PostgreSQL 16" icon=postgresql @src="src/db/schema.sql#L1"
cache Redis "Redis Cluster" icon=redis
# 3. Logical Groups (Perimeters & Tiers)
group edgeTier "Edge Tier": Client Gateway
group coreServices "Core Services": OrderSvc PaySvc
group dataLayer "Data & Streaming": Kafka OrdersDB Redis
# 4. Storyboard Beats: Interactive narrative animation steps
beat checkout "1. Client Checkout Request":
show $nodes stagger=40ms
frame Client Gateway OrderSvc zoom=1.12
Client -> Gateway "POST /api/checkout" -> OrderSvc "validate"
OrderSvc -> Redis "check idempotency"
OrderSvc <- Redis "key: new"
glow OrderSvc color=#38bdf8
beat payment "2. Payment Execution & Event Fan-out":
frame OrderSvc PaySvc Kafka OrdersDB zoom=1.15
OrderSvc -> PaySvc "POST /charge"
PaySvc -> OrdersDB "record transaction"
OrderSvc ~> Kafka "topic: order.completed"
Client <- Gateway "201 Created"
glow PaySvc color=#22c55e & glow Kafka color=#f59e0b
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.
- 7d ago Changed · +31 lines · +9 tokens per session f2cf13e64c93
- 12d ago First seen · 92 lines · 49 tokens per session scan A 8879562b0de3
markdy-diagram-author is a skill published in the GitHub repository HoangYell/markdy-com (95 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,506 once invoked, about $0.0003 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
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.
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.
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…
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.