nornicdb-bolt-client

nornicdb-bolt-client is a skill for Claude Code, Codex from orneryd/NornicDB. It costs 98 tokens per session (2,689 once invoked), scanned A, original, MIT.

A guide for connecting applications to NornicDB through Bolt, the database connection protocol also used by Neo4j. It explains how to use standard Neo4j drivers and handle connection, batching, and retry details.

In plain words
What is it for?
Use it to configure Bolt connections, send Cypher queries, batch writes with UNWIND, classify errors, and implement retries for concurrent workloads.
Why use it?
It removes uncertainty about client settings and error handling when many writes run at once. Existing Neo4j-compatible drivers can be used instead of a custom client.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to configure Bolt connections, send Cypher queries, batch writes with UNWIND, classify errors, and implement retries for concurrent workloads.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orneryd/nornicdb/bolt-client
Install

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.

Any agent
npx skills add orneryd/NornicDB --skill bolt-client
Clone the repo
git clone --depth 1 https://github.com/orneryd/NornicDB

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for nornicdb-bolt-client

README.md
[![agentmods](https://agentmods.dev/badge/skills/orneryd/nornicdb/bolt-client/github.svg)](https://agentmods.dev/skills/orneryd/nornicdb/bolt-client)
Your own site
<a href="https://agentmods.dev/skills/orneryd/nornicdb/bolt-client"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/bolt-client/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.

agentmods 80×15 button for nornicdb-bolt-client

Your own site · 80×15
<a href="https://agentmods.dev/skills/orneryd/nornicdb/bolt-client"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/bolt-client.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,689 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.02689
Opus 5.5 $0.00039 $0.01076
Sonnet 5.5 $0.00020 $0.00538
Haiku 4.5 $0.00010 $0.00269

Measured 24d ago against content hash cd21036af182, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nornicdb-bolt-client 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 24d 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.

docs/skills/bolt-client.skill.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NornicDB Bolt Client (Cypher API)

NornicDB exposes Bolt on port 7687 and is wire-compatible with Neo4j 5. Any upstream Bolt driver works — neo4j-go-driver/v5, neo4j-driver (Python), neo4j-javascript-driver, etc. This skill is what a client must pin to drive NornicDB safely under concurrency.

Connection

Setting Value
URI bolt://<host>:7687
Driver any Neo4j 5 Bolt driver (do not vendor a NornicDB-specific fork)
Database name the literal database name; address it directly via Session.Run(... database=<name>)
HTTP port (search REST, admin) 7474

Server defaults (parsed from LoadDefaults() — these are stable):

Field Default Notes
Database.AsyncWritesEnabled true Async write-behind is on by default. Set NORNICDB_ASYNC_WRITES_ENABLED=false if you need synchronous commit so a queue can drain to a known terminal state.
Database.PersistSearchIndexes false Search-index persistence is opt-in. Set NORNICDB_PERSIST_SEARCH_INDEXES=true if you want BM25/vector indexes to survive restart.
Auth.Enabled false Auth is off by default. Production deployments enable via the YAML auth: field.
Server.BoltPort 7687
Server.HTTPPort 7474

Error classes you will see

NornicDB returns Neo4j-shaped error codes (Neo.ClientError.*, Neo.TransientError.*) plus a stable message text. You can classify by either the code or the substring; the wire shape is intentionally consistent across both commit paths.

For explicit BEGIN/COMMIT transactions, a retryable COMMIT failure is delivered as FAILURE without closing the Bolt connection. The session remains in the normal failed-until-RESET state, so drivers can reset and retry on the same socket. A COMMIT rejected by a constraint check (Neo.ClientError.Schema.ConstraintValidationFailed) is found before anything is written, so it also keeps the connection: nothing of the transaction is stored. Non-retryable uncertain commit failures still close the connection.

Read the full file on GitHub · 197 lines

Changes

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.

  1. 24d ago Changed · +5 lines cd21036af182
  2. 1mo ago Changed · +7 lines 572d2aa35a4b
  3. 1mo ago First seen · 185 lines · 98 tokens per session scan A ee9b5daf86f5

Subscribe to this mod's changes

nornicdb-bolt-client is a skill published in the GitHub repository orneryd/NornicDB (912 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 2,689 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.

Related

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.

payloadcms/payload · 43 tokens

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.

KLR-Pattern/pydantic-resolve · 56 tokens

webiny-api-opensearch-catalog

Name: createOpenSearchClient Import: import { createOpenSearchClient } from "webiny/api/opensearch" Source: @webiny/api-opensearch/client.ts.

webiny/webiny-js · 19 tokens

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…

gusbavia/fabric-apps-skills · 150 tokens

hasura-graphql-engine

Complete guide for Hasura GraphQL Engine including instant GraphQL APIs, permissions, authentication, event triggers, actions, and production deployment.

manutej/luxor-claude-marketplace · 32 tokens

api-integration-architect

Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.

sickn33/agentic-awesome-skills · 33 tokens