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.
git clone --depth 1 https://github.com/j4flmao/agent-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/rules/j4flmao/agent-skills/rag-vector-standards)<a href="https://agentmods.dev/rules/j4flmao/agent-skills/rag-vector-standards"><img src="https://agentmods.dev/badge/rules/j4flmao/agent-skills/rag-vector-standards/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/rules/j4flmao/agent-skills/rag-vector-standards"><img src="https://agentmods.dev/badge/rules/j4flmao/agent-skills/rag-vector-standards.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 | $0.00017 | $0.00334 |
| Opus 5.5 | $0.00007 | $0.00134 |
| Sonnet 5.5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
rag-vector-standards 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 1mo 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
RAG & Vector Search Standards
Cursor/AI MUST follow these rules when writing code for Retrieval-Augmented Generation (RAG) or interacting with Vector Databases (Pinecone, Qdrant, Milvus, pgvector).
1. Hybrid Search is Mandatory
- Rule: Never implement a purely Dense Vector (Cosine Similarity) search unless explicitly commanded. You MUST implement Hybrid Search (Dense Vector + Sparse Keyword/BM25).
- Why: Dense vectors are terrible at exact keyword matching (e.g., searching for a specific product ID like
XJ-928or a unique name). Combining Semantic Search with Keyword Search guarantees maximum recall.
2. Implement Re-ranking
- Rule: Standard pipeline implementation must include a Two-Stage Retrieval process.
- Fetch Top-K (e.g., 50) results using the Vector DB.
- Re-rank the results using a Cross-Encoder (e.g., Cohere Rerank) down to Top-N (e.g., 5) before passing them to the final LLM.
3. Forbid Naive Chunking
- Rule: Do not use blind character splitters (e.g.,
RecursiveCharacterTextSplitter(chunk_size=1000)). - Alternative: You must implement Semantic Chunking or Parent-Child Chunking (where the retrieved chunk is small, but the context returned to the LLM encompasses the larger parent document).
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.
- 1mo ago First seen · 22 lines · 17 tokens per session scan A b1271bf4f35e
rag-vector-standards is a cursor rule published in the GitHub repository j4flmao/agent-skills (33 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 334 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other cursor rules, from other repositories
cardano-mcp
These rules complement our main development collaboration rules, focusing specifically on the Model Context Protocol (MCP) server project with TypeScript. This project serves as a specialized RAG (Retrieval-Augmented Generation) gateway to existing Cardano resources, documentation, and tools to assist with dApp…
005_Dynamo_KV_Cache_Management_KVBM
NVIDIA Dynamo KV Cache Management (KVBM) - Advanced memory management and offloading strategies for optimal performance.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.