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 curiositech/some_claude_skills --skill mdx-sanitizergit clone --depth 1 https://github.com/curiositech/some_claude_skillsWrote 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/curiositech/some_claude_skills/mdx-sanitizer)<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.
<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>- 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 | $0.00103 | $0.01361 |
| Opus 5 | $0.00051 | $0.00681 |
| Sonnet 5 | $0.00021 | $0.00272 |
| Haiku 4.5 | $0.00010 | $0.00136 |
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.
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<T>,Array<string>,Map<K, V> - Comparisons:
<100ms,<=,>= - Arrows:
-->,<--,-> - Invalid tags:
<link>in prose,<tag>placeholders - Empty brackets:
<>
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 filessyncSkillSubpages.ts- Reference filesdoc-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 | < |
< |
| Greater-than | > |
> |
| Generics | <T> |
&lt;T&gt; |
| Comparison | <= |
&lt;= |
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.
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 · 161 lines · 103 tokens per session scan A 5d9aa8d158b9
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.
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.