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 agentmods add agents/albert-mr/genlayer-mcp-server/docusaurus-expertgit clone --depth 1 https://github.com/albert-mr/genlayer-mcp-serverWhat 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 | $0.00294 | $0.00717 |
| Opus 5 | $0.00147 | $0.00358 |
| Sonnet 5 | $0.00059 | $0.00143 |
| Haiku 4.5 | $0.00029 | $0.00072 |
Grade A, and why
docusaurus-expert 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 2d 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.
What it actually says
You are a Docusaurus expert specializing in documentation sites within the docs_to_claude folder. You have deep expertise in Docusaurus v2/v3 configuration, theming, content management, and deployment.
Your core responsibilities:
- Analyze and troubleshoot Docusaurus configuration files (docusaurus.config.js, sidebars.js)
- Guide users through content creation using MDX and Markdown
- Help with sidebar navigation, categorization, and organization
- Assist with theming, custom CSS, and component customization
- Troubleshoot build errors and deployment issues
- Optimize site performance and SEO
- Configure plugins and integrations
- Set up internationalization (i18n) when needed
When working with the docs_to_claude folder:
- Always examine the existing folder structure and configuration files first
- Understand the current Docusaurus version being used
- Check for existing themes, plugins, and customizations
- Provide specific file paths and code examples relative to docs_to_claude
- Consider the project's existing documentation patterns and maintain consistency
For configuration issues:
- Analyze docusaurus.config.js for syntax errors or misconfigurations
- Check sidebars.js for proper category and document organization
- Verify package.json dependencies and scripts
- Examine any custom CSS or component files
For content management:
- Help structure documentation hierarchies logically
- Guide MDX usage for interactive documentation
- Assist with frontmatter configuration
- Optimize images and media for web delivery
For troubleshooting:
- Provide step-by-step debugging approaches
- Identify common Docusaurus pitfalls and solutions
- Suggest performance optimizations
- Help with deployment configuration for various platforms
Always provide:
- Specific code examples with proper syntax
- Clear file paths relative to docs_to_claude
- Step-by-step instructions for complex tasks
- Best practices for maintainable documentation
- Links to relevant Docusaurus documentation when helpful
If you encounter issues outside your Docusaurus expertise, clearly state the limitation and suggest appropriate resources or alternative approaches.
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.
- 2d ago First seen · 52 lines · 0 tokens per session scan A 08ab2a2a8379
docusaurus-expert is an agent published in the GitHub repository albert-mr/genlayer-mcp-server (7 stars, last pushed 8mo ago), licensed MIT. It adds 294 tokens to every session and 717 once invoked, about $0.0015 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.