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/neo4j-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/neo4j-migration)<a href="https://agentmods.dev/skills/orneryd/nornicdb/neo4j-migration"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/neo4j-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/neo4j-migration"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/neo4j-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 | $0.02530 |
| Opus 5 | $0.00051 | $0.01265 |
| Sonnet 5 | $0.00020 | $0.00506 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade A, and why
nornicdb-neo4j-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 5d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrating from Neo4j to NornicDB
NornicDB speaks Bolt and Cypher. Migration is a Bolt → Bolt replay using the same drivers Neo4j users already have (neo4j, neo4j-driver, neo4j-go-driver/v5). No protocol bridge, no ETL service.
This skill covers the migration plan and the exact query shapes used. Runnable scripts live in scripts/migration/neo4j/.
Phase order (do not reorder)
- Schema — constraints, then indexes (vector and fulltext last). Idempotent via
IF NOT EXISTS. - Nodes —
UNWIND $rows MERGE (n:_Migrated {_neo4j_id: row.id}) SET n += row.propsper label, keyset-paginated byelementId. HitsUnwindSimpleMergeBatch. - Edges —
UNWIND $rows MATCH (a) MATCH (b) CREATE (a)-[:T]->(b)per relationship type. HitsUnwindMultiMatchCreateBatch.
Reordering breaks the edge phase because it depends on _Migrated nodes being present.
Schema replication
Source-side queries used by every script:
SHOW CONSTRAINTS
SHOW INDEXES
Each row maps to a target DDL statement that NornicDB's parser accepts:
| Source row | Emitted DDL |
|---|---|
| Node UNIQUENESS | CREATE CONSTRAINT <name> IF NOT EXISTS FOR (n:L) REQUIRE n.p IS UNIQUE |
| Node NODE_KEY | CREATE CONSTRAINT <name> IF NOT EXISTS FOR (n:L) REQUIRE (n.p1, n.p2) IS NODE KEY |
| Node PROPERTY_EXISTENCE | CREATE CONSTRAINT <name> IF NOT EXISTS FOR (n:L) REQUIRE n.p IS NOT NULL |
| Relationship UNIQUENESS / EXISTENCE | CREATE CONSTRAINT <name> IF NOT EXISTS FOR ()-[r:T]-() REQUIRE r.p IS UNIQUE / IS NOT NULL |
| Range/B-tree node index | CREATE INDEX <name> IF NOT EXISTS FOR (n:L) ON (…) |
| Fulltext node index | CREATE FULLTEXT INDEX <name> IF NOT EXISTS FOR (n:L) ON EACH [n.p1, n.p2] |
| Vector node index | CREATE VECTOR INDEX <name> IF NOT EXISTS FOR (n:L) ON (n.p) OPTIONS {indexConfig: {…dimensions, similarity_function…}} |
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.
- 5d ago First seen · 186 lines · 101 tokens per session scan A 729d9647fe5c
nornicdb-neo4j-migration is a skill published in the GitHub repository orneryd/NornicDB (865 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 2,530 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
payload
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
pydantic-resolve-3step
A three-stage development method for Python projects built with pydantic-resolve, starting with agreed data models and ending with application interfaces. It uses an ER diagram, which shows database entities and their relationships, plus ORM models that represent database records in code.
webiny-api-opensearch-catalog
Name: createOpenSearchClient Import: import { createOpenSearchClient } from "webiny/api/opensearch" Source: @webiny/api-opensearch/client.ts.
fabric-app-sqldb-writeback
Use when a Fabric App needs transactional WRITE-BACK (comments, edits, requests, approvals) on top of Lakehouse data — 'users edit data in my Fabric app', 'write back to the source', 'my saved comment takes forever to appear', 'read-your-own-writes', 'mirror Gold into the app database', 'seed the Rayfin SQL DB…
hasura-graphql-engine
Complete guide for Hasura GraphQL Engine including instant GraphQL APIs, permissions, authentication, event triggers, actions, and production deployment.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.