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 marc0der/reveng --skill validate-mermaidgit clone --depth 1 https://github.com/marc0der/revengWrote 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/marc0der/reveng/validate-mermaid)<a href="https://agentmods.dev/skills/marc0der/reveng/validate-mermaid"><img src="https://agentmods.dev/badge/skills/marc0der/reveng/validate-mermaid/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/marc0der/reveng/validate-mermaid"><img src="https://agentmods.dev/badge/skills/marc0der/reveng/validate-mermaid.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 | $0.00027 | $0.00685 |
| Opus 5 | $0.00014 | $0.00342 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
validate-mermaid 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You validate every Mermaid diagram block in a markdown file. For each broken diagram you attempt to fix it in place, retrying up to 2 times.
Input
The markdown file path is: $ARGUMENTS
Steps
-
Check that the Mermaid MCP is available. Before doing anything else, confirm the
mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagramtool is present in the available tool list. If it is not available, print the following message verbatim and stop with a success exit (do not fail the caller's workflow):⚠ validate-mermaid skipped: the "Mermaid Chart" connector is not enabled. This skill depends on the Mermaid Chart MCP hosted on claude.ai. To enable it: 1. Sign in at https://claude.ai 2. Open Settings → Connectors 3. Enable "Mermaid Chart" 4. Restart Claude Code Skipping validation — your other outputs are unaffected. -
Read the file using the Read tool.
-
Extract all fenced Mermaid blocks. Identify every occurrence of a
```mermaidcode fence and its closing```. Note the line numbers and content of each block. If no Mermaid blocks are found, report "No Mermaid diagrams found in [file path]" and stop. -
Validate each block by calling
mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagramwith:mermaidCode: the content between the fences (excluding the fence lines themselves)prompt: "Validate this Mermaid diagram"diagramType: inferred from the first line of the block (e.g.flowchart,sequenceDiagram,gantt,classDiagram)clientName: "claude"
If the tool call fails mid-run (e.g. transient error after the precheck passed), report the error and continue to the next block — do not fail the caller's workflow.
-
Fix broken diagrams. For each block that fails validation:
- Read the error details from the tool response
- Determine the fix based on the error message
- Use the Edit tool to replace the broken mermaid content with the corrected version (use the full block content as
old_stringand the fixed content asnew_string) - Re-validate by calling the MCP tool again
- If it still fails, attempt one more fix (maximum 2 retries per block)
- If a block remains broken after 2 retries, mark it as unfixable and continue to the next block
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 · 54 lines · 27 tokens per session scan A 38bb8eae04d9
validate-mermaid is a skill published in the GitHub repository marc0der/reveng (5 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 685 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
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.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.