Borrowing it
Nothing to install: this file belongs to HoangYell/markdy-com. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HoangYell/markdy-com/main/.agents/skills/markdy-mcp-debug/SKILL.mdgit 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-mcp-debug)<a href="https://agentmods.dev/skills/hoangyell/markdy-com/markdy-mcp-debug"><img src="https://agentmods.dev/badge/skills/hoangyell/markdy-com/markdy-mcp-debug.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.02162 |
| Opus 5 | $0.00022 | $0.01081 |
| Sonnet 5 | $0.00009 | $0.00432 |
| Haiku 4.5 | $0.00004 | $0.00216 |
Grade A, and why
markdy-mcp-debug 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdy MCP Debug & Syntax Healing Skill
This skill equips AI agents and developers to diagnose, debug, and heal MarkdyScript (.markdy) diagram syntax errors, typos, grammar mistakes, undefined node references, and architectural flow cycles using the Markdy MCP Server tools.
🧭 The Canonical 4-Step Mental Model
Every valid MarkdyScript diagram is structured linearly in 4 distinct steps:
# Step 1: Directives (Canvas theme and layout orientation)
scene theme=paper
layout LR
# Step 2: Semantic Node Declarations (<kind> <Id> ["Human Label"])
browser WebApp "Web Application"
mobile MobileApp "Mobile Client"
gateway ApiGateway "Cloud Gateway"
service OrderService "Order Service"
database MainDB "PostgreSQL"
cache RedisCache "Redis Cluster"
# Step 3: Groups (Logical tier boundaries)
group clients "User Surfaces": WebApp MobileApp
group backend "Service Tier": ApiGateway OrderService
group dataTier "Data Tier": MainDB RedisCache
# Step 4: Storyboard Beats (Narrative steps with indented flows & cues)
beat reveal "System Overview":
show $nodes stagger=40ms
beat checkout "Process Order":
MobileApp -> ApiGateway "POST /checkout" -> OrderService "create_order"
OrderService -> RedisCache "check inventory"
OrderService -> MainDB "insert order"
MobileApp <- ApiGateway "201 Created"
glow MobileApp color=#10b981
🛠️ MCP Tools for Debugging & Healing
The Markdy MCP server exposes specialized tools for diagnostic inspection and automatic repair:
1. diagnose_markdy_syntax
Performs deep AST parsing, fuzzy typo matching (using Damerau-Levenshtein distance), undefined node resolution, and flow cycle detection.
Input:
{
"code": "scen theme=papr\nlayput LR\nservce API\ndatabse DB\nbeat main\n API -> DB"
}
Output:
- Comprehensive error summary with line numbers and snippets.
- Precise
"Did you mean?"suggestions for misspelled keywords, node kinds, or node IDs. - Concrete rule explanations.
- Proposed auto-repaired MarkdyScript code.
- AI healing prompt formatted for LLMs.
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 First seen · 257 lines · 44 tokens per session scan A 27a97a9ab98d
markdy-mcp-debug is a skill published in the GitHub repository HoangYell/markdy-com (88 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,162 once invoked, about $0.0002 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
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.
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.
investigate
Investigate a single EmDash issue end to end -- classify, choose a repro path, reproduce, diagnose, verify, and (only on an explicit maintainer fix directive) fix and confirm. Every verdict carries its evidence.
fix
Implement diagnose's proposed fix when verify says bug, the cause is pinned, and a maintainer triggered a fix. Follow EmDash conventions, run focused checks, publish the candidate, and report the results accurately.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
implement
Implement a maintainer-directed EmDash enhancement or change without forcing it through bug-reproduction fields. Run focused checks, publish the candidate, and report the results accurately.