qmd-hardenedLocal search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Install via ClawdBot CLI:
clawdbot install snazar-faberlens/qmd-hardenedInstall qmd (node):
Install qmd (node)Requires:
Grade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
send → https://hooks.example.com/webhookPotentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://tobi.lutke.comAudited Apr 30, 2026 · audit v1.0
Generated May 13, 2026
A team indexes their markdown documentation and uses BM25 or hybrid search to quickly find relevant guides, APIs, or troubleshooting steps. This reduces time spent navigating file hierarchies and improves knowledge retrieval.
Law firms index contracts, case files, and legal briefs as markdown files. They use vector search to semantically find clauses or precedents relevant to a case, enhancing e-discovery efficiency.
Researchers index a collection of papers or notes in markdown and use hybrid search to locate related work, methodologies, or data references. The local-only guarantee ensures sensitive pre-publication content stays secure.
An individual indexes personal notes, journals, or project files. They search across topics with reranked results, helping them recall past ideas or decisions without relying on cloud-based search tools.
Offer the CLI tool for free with core indexing and search. Charge for premium features like advanced reranking models, custom embeddings, or team collaboration hooks via a hosted MCP server.
License qmd-hardened as a local search module for existing documentation platforms or note-taking apps. Integrate via its MCP mode, charging per-seat or per-deployment.
Package qmd-hardened with pre-configured guardrails for regulated industries (legal, healthcare, finance). Offer audit logs, policy enforcement, and support as a compliance-ready search solution.
💬 Integration Tip
Install via npm as described, ensure Ollama is running locally for embeddings/rerank, and set OLLAMA_URL only to localhost to maintain security. For scripted use, pipe output carefully to avoid network leaks.
Scored May 13, 2026
Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Use when designing database schemas, writing migrations, optimizing SQL queries, fixing N+1 problems, creating indexes, setting up PostgreSQL, configuring EF Core, implementing caching, partitioning tables, or any database performance question.
Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and managing tables. Triggers on requests involving databases, vector stores, embeddings, or Supabase specifically.
Airtable API integration with managed OAuth. Manage bases, tables, and records. Use this skill when users want to read, create, update, or delete Airtable records, or query data with filter formulas. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Use SQLite correctly with proper concurrency, pragmas, and type handling.
AI-driven multi-format SVG content generation system for presentations, social media graphics, and marketing materials. Use when creating PPTs, posters, or v...