Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/orneryd/NornicDBnpx agentmods add skills/orneryd/nornicdb/qdrant-migrationWrote 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/qdrant-migration)<a href="https://agentmods.dev/skills/orneryd/nornicdb/qdrant-migration"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/qdrant-migration/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/skills/orneryd/nornicdb/qdrant-migration"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/qdrant-migration.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 | $0.00101 | $0.01825 |
| Opus 5.5 | $0.00040 | $0.00730 |
| Sonnet 5.5 | $0.00020 | $0.00365 |
| Haiku 4.5 | $0.00010 | $0.00183 |
Grade A, and why
nornicdb-qdrant-migration 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrating from Qdrant to NornicDB
NornicDB's Qdrant-compatible gRPC service means migration is a same-API replay: the source and target speak the same wire, so the script reading from Qdrant can write into NornicDB through the same client library. There is no protocol bridge to build, no schema translation to invent.
This skill covers the migration surface itself. Runnable scripts are in scripts/migration/qdrant/.
Prerequisites
- Enable the gRPC server on NornicDB. Off by default:
export NORNICDB_QDRANT_GRPC_ENABLED=true export NORNICDB_QDRANT_GRPC_LISTEN_ADDR=":6334" - Match dimension limits. If your source has vectors above
4096, raiseNORNICDB_QDRANT_GRPC_MAX_VECTOR_DIMbefore running. - Match auth. If your source enforces auth, your migration script needs an API key (Qdrant) and your target needs the same if
Auth.Enabled=true.
Migration phases
1. List source collections
Use the source SDK's standard collection listing:
- Python:
client.get_collections().collections - Go:
client.ListCollections(ctx) - Node:
client.getCollections().collections
Pick a subset with a --collections a,b flag if the migration is partial.
2. Replicate vector config per collection
Read the source collection's VectorParams (or named-vector dict/map) and apply them to NornicDB. Both sides accept the same shape:
client.create_collection(
collection_name="docs",
vectors_config=m.VectorParams(size=1024, distance=m.Distance.COSINE),
)
Named-vector collections are passed as a dict/map where each entry has its own size and distance. NornicDB stores each named vector independently in node.NamedEmbeddings[<vectorName>].
If the target already has a collection of the same name, skip the create with --skip-existing.
3. Stream points and upsert
Scroll source points in batches and upsert into target:
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 · 146 lines · 101 tokens per session scan A ff694b593139
nornicdb-qdrant-migration is a skill published in the GitHub repository orneryd/NornicDB (912 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,825 once invoked, about $0.0004 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 skills, from other repositories
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.
dkg-importer
Bulk-import a large RDF graph (code graph, corpus, GitHub history, etc.) into a DKG node's working memory. Use this skill when you need to push more than a few thousand triples in a single import — it codifies the chunking budgets, the assertion-loop shape, the resumability manifest, and the canonical URI rules so…
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.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.