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 skills add orneryd/NornicDB --skill rag-proceduresgit clone --depth 1 https://github.com/orneryd/NornicDBWrote 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/skills/orneryd/nornicdb/rag-procedures)<a href="https://agentmods.dev/skills/orneryd/nornicdb/rag-procedures"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/rag-procedures.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.02892 |
| Opus 5 | $0.00046 | $0.01446 |
| Sonnet 5 | $0.00019 | $0.00578 |
| Haiku 4.5 | $0.00009 | $0.00289 |
Grade A, and why
nornicdb-rag-procedures 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Procedures (Cypher API)
NornicDB exposes the entire retrieval-augmented-generation pipeline as Cypher procedures. The mental model is "Cypher all the way down": write CALL db.<verb>({...}) with a map argument and YIELD the columns you want.
The four verbs
| Procedure | What it does | Stages |
|---|---|---|
db.retrieve(req) |
Hybrid retrieval | vector + BM25, fused with RRF |
db.rretrieve(req) |
Retrieve + rerank when reranker is configured | adds cross-encoder rerank if NORNICDB_SEARCH_RERANK_ENABLED=true |
db.rerank(req) |
Standalone rerank over user-supplied candidates | cross-encoder only |
db.infer(req) |
LLM generation | calls the configured inference manager |
All four take a single map argument. Most fields support both camelCase and snake_case; pick one and stick with it.
db.retrieve — hybrid retrieval
CALL db.retrieve({
query: 'authentication patterns', -- required
limit: 10, -- default 50
failClosed: true, -- require embedding; disable BM25 fallback
minSimilarity: 0.5, -- vector floor
types: ['Document', 'Memory'], -- label filter; alias: labels
filters: {lifecycle: 'active'}, -- property filters
candidateTarget: 50, -- branch depth, independent of limit
rrfK: 60,
vectorWeight: 1.0,
bm25Weight: 1.0,
minRRFScore: 0.0,
fallbackEnabled: false,
rerankEnabled: false, -- explicit on/off
rerankTopK: 100,
rerankMinScore: 0.0,
embedding: $queryVector -- optional pre-computed; alias: queryEmbedding / query_embedding
})
YIELD node, score, rrf_score, vector_rank, bm25_rank, search_method, fallback_triggered
RETURN node.id, node.title, score, search_method
ORDER BY score DESC
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 · 221 lines · 93 tokens per session scan A c9484ae58516
nornicdb-rag-procedures is a skill published in the GitHub repository orneryd/NornicDB (861 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 2,892 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.