Borrowing it
Nothing to install: this file belongs to mck-s/minirag-pgvector-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mck-s/minirag-pgvector-mcp/main/.claude/commands/minirag.mdgit clone --depth 1 https://github.com/mck-s/minirag-pgvector-mcpWrote 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/commands/mck-s/minirag-pgvector-mcp/minirag)<a href="https://agentmods.dev/commands/mck-s/minirag-pgvector-mcp/minirag"><img src="https://agentmods.dev/badge/commands/mck-s/minirag-pgvector-mcp/minirag/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/commands/mck-s/minirag-pgvector-mcp/minirag"><img src="https://agentmods.dev/badge/commands/mck-s/minirag-pgvector-mcp/minirag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.00399 |
| Opus 5 | $0.00006 | $0.00199 |
| Sonnet 5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
minirag 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 8d 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 about to answer a question using the minirag MCP server's search_context tool.
Instructions:
-
Extract the query from the user's message. The user may provide:
- Just a search query:
/minirag how do I configure the embedder? - A query with a doctype filter:
/minirag [spec] architecture decisions - The query may be in natural language
- Just a search query:
-
Parse optional doctype filter. If the user includes
[doctype]syntax, extract it:- Valid doctypes:
meeting-notes,spec,codebase,default - Example:
/minirag [meeting-notes] who attended the sync?→ query="who attended the sync?", doctype="meeting-notes"
- Valid doctypes:
-
Call the MCP tool
search_context:- Pass the extracted query
- If a doctype was specified, pass it as the doctype parameter
- Use default k=5 unless the user specifies otherwise
-
Answer based on the retrieved chunks:
- Ground your answer in the returned content. Do not speculate beyond what the chunks say.
- Cite every fact using the format:
[source: heading_path] - If multiple chunks support a point, cite all relevant sources
- If the chunks don't contain enough information to answer, say so explicitly
-
Format your response:
- Start with a direct answer to the question
- Use citations inline:
The embedder dimension is 384 [architecture.md: Configuration > Embedder] - If helpful, add a "Sources" section at the end listing all referenced documents
Example interaction:
User: /minirag [spec] What's the database schema for chunks?
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.
- 8d ago First seen · 36 lines · 12 tokens per session scan A 243649413b4d
minirag is a command published in the GitHub repository mck-s/minirag-pgvector-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 399 once invoked, about $0.0001 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 commands, from other repositories
querying
Query documents from a search index using type-safe filters with support for pagination, sorting, field selection, scoring, and highlighting. Count matching documents efficiently without returning results.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
ingest
Manually add knowledge to the Weaviate store.
inference.embed
Embed one or more texts into vectors.
vector.batch_exists
Check existence for multiple vector keys.
vector.batch_upsert
Upsert multiple vectors in one itemwise batch.