A wrapper around qmd that lets Claude search indexed reference code repositories. It combines word matching, meaning-based search, and result reranking, and can clone and index a GitHub repository.

Use it to search indexed projects such as Convex, Expo, or Next.js, or to add a GitHub repository to the searchable index.

It reduces the time spent looking through external example repositories for relevant implementation patterns or documentation.

qmd — Plugin for Claude Code by ramonclaudio

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.

Clone the repo

git clone --depth 1 https://github.com/ramonclaudio/skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/ramonclaudio/skills/qmd.svg)](https://agentmods.dev/plugins/ramonclaudio/skills/qmd)

Your own site

<a href="https://agentmods.dev/plugins/ramonclaudio/skills/qmd"><img src="https://agentmods.dev/badge/plugins/ramonclaudio/skills/qmd.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 2 skills, 18 commands, 1 MCP server cost 536 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

qmd 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.

plugins/qmd/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "qmd",
  "version": "1.9.0",
  "description": "Wraps the qmd MCP server so Claude can search indexed reference repos (Convex, Expo, Next.js, etc) with hybrid BM25 + vector + reranking. Ships a search SKILL that teaches Claude how to compose typed sub-queries with intent, plus an /qmd:add SKILL that clones and indexes a GitHub repo end-to-end.",
  "author": {
    "name": "ramonclaudio",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/ramonclaudio/skills/tree/main/plugins/qmd",
  "repository": "https://github.com/ramonclaudio/skills",
  "license": "MIT",
  "keywords": ["search", "mcp", "bm25", "vector-search", "rag", "reference-repos", "embeddings", "qmd"]
}

Contents

What it installs

The manifest is a name and a version. 2 skills, 18 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 536 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

7d ago First seen · 14 lines scan A e7b39ce830fa

Subscribe to this mod's changes

qmd is a plugin published in the GitHub repository ramonclaudio/skills (4 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Data and AI RAG and vectors Research

clip-aware-embeddings

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…

curiositech/some_claude_skills · not measured

rag-reviewer

Agentic PR review: hybrid RAG + code graph via MCP, review skills for Claude Code.

mimfort/rag_for_git · not measured

mixedbread-skills

Agent skills for search, RAG, parsing, completions, and model harnesses with Mixedbread.

mixedbread-ai/skills · not measured

veritasreason

Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.

bibinprathap/VeritasGraph · not measured

graph-source

Connect a property graph (knowledge graph, GraphRAG corpus, Apache AGE / openCypher data) to Skardi and query it through SQL, end to end: provision the AGE backend with a least-privilege role, declare the type: graph source and its views in context YAML, verify registration health, write correct queries (cypherquery.

SkardiLabs/skardi-skills · not measured

Claude Dev Assistant marketplace

An intelligent development workflow featuring Socratic interviewing, dual-agent debate, expert team coordination, and RAG system design. Built on Claude Code for seamless AI-assisted development.

an8079/take-skills · not measured