mdx-sanitizer

mdx-sanitizer is a skill for Claude Code from curiositech/some_claude_skills. It costs 103 tokens per session (1,361 once invoked), scanned A, original, MIT.

A content-cleaning guide for Docusaurus documentation written in MDX. MDX combines Markdown with JSX, so ordinary text such as TypeScript angle brackets or template syntax can be mistaken for code.

In plain words
What is it for?
Fixing escaped brackets, comparisons, arrows, generic type examples, template expressions, and inline-code edge cases in MDX documentation.
Why use it?
It helps stop documentation builds from failing when prose contains symbols that MDX interprets as markup. It checks content during syncing, commits, and builds.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the mdx-sanitizer plugin — 1 skill shipped together

Good fit Fixing escaped brackets, comparisons, arrows, generic type examples, template expressions, and inline-code edge cases in MDX documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curiositech/some_claude_skills/mdx-sanitizer
Install

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.

Any agent
npx skills add curiositech/some_claude_skills --skill mdx-sanitizer
Clone the repo
git clone --depth 1 https://github.com/curiositech/some_claude_skills

Made for: Claude Code.

Or install mdx-sanitizer, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for mdx-sanitizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/curiositech/some_claude_skills/mdx-sanitizer/github.svg)](https://agentmods.dev/skills/curiositech/some_claude_skills/mdx-sanitizer)
Your own site
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/mdx-sanitizer"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/mdx-sanitizer/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.

agentmods 80×15 button for mdx-sanitizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/mdx-sanitizer"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/mdx-sanitizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.01361
Opus 5 $0.00051 $0.00681
Sonnet 5 $0.00021 $0.00272
Haiku 4.5 $0.00010 $0.00136

Measured 7d ago against content hash 5d9aa8d158b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mdx-sanitizer 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.

.claude/skills/mdx-sanitizer/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDX Sanitizer

Comprehensive MDX content sanitizer that prevents JSX parsing errors caused by angle brackets, generics, and other conflicting patterns.

The Problem

MDX 2.x treats unescaped < and { as JSX syntax. This causes build failures when content contains:

  • TypeScript generics: Promise&lt;T&gt;, Array&lt;string&gt;, Map&lt;K, V&gt;
  • Comparisons: &lt;100ms, &lt;=, &gt;=
  • Arrows: --&gt;, &lt;--, -&gt;
  • Invalid tags: &lt;link&gt; in prose, &lt;tag&gt; placeholders
  • Empty brackets: &lt;&gt;

Solution Architecture

This skill implements a three-layer defense:

1. Sync-Time Sanitization (Proactive)

Content is sanitized when syncing from .claude/skills/ to website/docs/:

  • syncSkillDocs.ts - Main skill files
  • syncSkillSubpages.ts - Reference files
  • doc-generator.ts - Generated docs

2. Pre-Commit Validation (Reactive)

The git pre-commit hook validates files before commit using validate-brackets.js.

3. Build-Time Validation (Final Check)

npm run validate:all runs as part of prebuild to catch any issues.

Usage

Check for Issues (Dry Run)

cd website
npm run sanitize:mdx
# or with verbose output
npm run sanitize:mdx -- --verbose

Fix All Issues

cd website
npm run sanitize:mdx -- --fix
# or shorthand
npm run fix:mdx

Programmatic API

import { sanitizeForMdx, validateMdxSafety, isMdxSafe } from './lib/mdx-sanitizer';

// Sanitize content
const result = sanitizeForMdx(content, { useHtmlEntities: true });
if (result.modified) {
  console.log(`Fixed ${result.issues.length} issues`);
  fs.writeFileSync(path, result.content);
}

// Validate without modifying
const issues = validateMdxSafety(content, 'path/to/file.md');

// Quick check
if (!isMdxSafe(content)) {
  // Handle issues
}

Escaping Strategies

The sanitizer uses HTML entities for maximum compatibility:

Pattern Original Escaped
Less-than < &lt;
Greater-than > &gt;
Generics &lt;T&gt; &amp;lt;T&amp;gt;
Comparison &lt;= &amp;lt;=

Read the full file on GitHub · 161 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 7d ago First seen · 161 lines · 103 tokens per session scan A 5d9aa8d158b9

Subscribe to this mod's changes

mdx-sanitizer is a skill published in the GitHub repository curiositech/some_claude_skills (219 stars, last pushed 5d ago), licensed MIT. It adds 103 tokens to every session and 1,361 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 2026-09-03.

Related

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

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.

open-metadata/OpenMetadata · 37 tokens

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.

emdash-cms/emdash · 43 tokens

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.

emdash-cms/emdash · 48 tokens

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…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens