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 managed-embeddingsgit 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/managed-embeddings)<a href="https://agentmods.dev/skills/orneryd/nornicdb/managed-embeddings"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/managed-embeddings.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 | $0.00090 | $0.02349 |
| Opus 5 | $0.00045 | $0.01175 |
| Sonnet 5 | $0.00018 | $0.00470 |
| Haiku 4.5 | $0.00009 | $0.00235 |
Grade A, and why
nornicdb-managed-embeddings 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 yesterday.
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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managed Embeddings (Cypher API)
NornicDB can generate embeddings server-side and store them on nodes for you. From the consumer's point of view this is a Cypher feature: a WITH EMBEDDING clause on writes, and a db.index.vector.embed procedure for ad-hoc embedding.
Two storage slots, both readable
Every node has two embedding slots:
ChunkEmbeddings— managed by NornicDB.[][]float32— one entry per chunk;ChunkEmbeddings[0]is the primary embedding. Built by the embedding worker or byWITH EMBEDDING. Internal metadata (model,dimensions,chunk_count,embedded_at) is stored separately so it does not polluteProperties.NamedEmbeddings— client-managed.map[string][]float32, keyed by vector name (e.g."default","openai-small"). Set viadb.create.setNodeVectorPropertyor the Qdrant gRPC compatibility layer.
Vector index lookup order is NamedEmbeddings[indexProperty] → node.Properties[indexProperty] → ChunkEmbeddings. You usually want a vector index on a label whose nodes have managed embeddings, in which case nothing extra is needed.
Enabling managed embeddings
export NORNICDB_EMBEDDING_ENABLED=true
export NORNICDB_EMBEDDING_PROVIDER=ollama # ollama | openai | local
export NORNICDB_EMBEDDING_MODEL=mxbai-embed-large
export NORNICDB_EMBEDDING_API_URL=http://localhost:11434
export NORNICDB_EMBEDDING_DIMENSIONS=1024
YAML form:
embedding:
enabled: true
provider: ollama # ollama | openai | local
model: mxbai-embed-large
url: http://localhost:11434
dimensions: 1024
The OpenAI provider also reads embedding.api_key (or NORNICDB_EMBEDDING_API_KEY). The local provider resolves the model file inside NORNICDB_MODELS_DIR.
Defaults shipped with NornicDB: provider=local, model=bge-m3, dimensions=1024.
Per-database configuration
For a named database, use canonical keys in the YAML databases: map or
PUT /admin/databases/{name}/config: db.nornic.embedding.provider,
db.nornic.embedding.model, db.nornic.embedding.api.url,
db.nornic.embedding.api.key, and db.nornic.embedding.dimensions. Their
NORNICDB_* forms remain supported global environment alternatives and
alternate input names; canonical keys win collisions.
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.
- yesterday First seen · 216 lines · 90 tokens per session scan A 917d103874ef
nornicdb-managed-embeddings is a skill published in the GitHub repository orneryd/NornicDB (858 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,349 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.
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.
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…