nornicdb-knowledge-policies

nornicdb-knowledge-policies is a skill for Claude Code, Codex from orneryd/NornicDB. It costs 93 tokens per session (5,280 once invoked), scanned A, original, MIT.

A guide to NornicDB knowledge-layer policies written in Cypher. These policies control how database entities and relationships lose or gain score over time and how they are promoted.

In plain words
What is it for?
It helps create, change, remove, and inspect decay profiles, promotion profiles, and promotion policies, and read related entity scores.
Why use it?
It explains the different policy objects and how to attach them to selected database entities, avoiding confusion between reusable settings and active rules.

Skill for Claude CodeCodex

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

Good fit It helps create, change, remove, and inspect decay profiles, promotion profiles, and promotion policies, and read related entity scores.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/orneryd/nornicdb/knowledge-policies"><img src="https://agentmods.dev/badge/skills/orneryd/nornicdb/knowledge-policies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,280 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 $0.00093 $0.05280
Opus 5 $0.00046 $0.02640
Sonnet 5 $0.00019 $0.01056
Haiku 4.5 $0.00009 $0.00528

Measured 4d ago against content hash 2ab34f183cb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nornicdb-knowledge-policies 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 4d 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/knowledge-policies.skill.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NornicDB Knowledge-Layer Policies (Cypher API)

NornicDB scores every node and edge through a Cypher-controlled pipeline. The mental model is Neo4j Cypher: CREATE/ALTER/DROP/SHOW statements plus CALL procedures.

The four object kinds (and exactly what each one does)

There is one targeting mechanism (FOR (...)) used in two places. Object kinds:

Kind Carries a target? What it does Effect on scores by itself
Decay bundleCREATE DECAY PROFILE <name> OPTIONS { ... } No Names a reusable parameter set: halfLifeSeconds, function, visibilityThreshold, scoreFloor, scope, scoreFrom, scoreFromProperty None. A bundle on its own is inert.
Decay bindingCREATE DECAY PROFILE <name> FOR (...) APPLY { ... } Yes (FOR) Attaches decay math to a label / multi-label / edge type / wildcard. The APPLY block either references a bundle (DECAY PROFILE 'name') or sets parameters inline, plus per-property overrides. Decay is active for entities matching FOR.
Promotion profileCREATE PROMOTION PROFILE <name> OPTIONS { ... } No Names a reusable boost: multiplier, scoreFloor, scoreCap, scope. None on its own.
Promotion policyCREATE PROMOTION POLICY <name> FOR (...) APPLY { ON ACCESS { ... } WHEN ... APPLY PROFILE '...' } Yes (FOR) Attaches access-counter mutations and conditional boosts to a target. ON ACCESS mutations write to access metadata; WHEN clauses select which promotion profile applies. Mutates access metadata; promotion math applies when a WHEN matches.

So:

  • Bundles and profiles are inert parameter packages. They never select entities, never run code on their own, and never change scores until a binding or policy references them.
  • Bindings and policies are the only objects that reference entities. Both use the same FOR (...) target syntax.
  • Yes, the keyword CREATE DECAY PROFILE has two shapes — the parser chooses bundle vs binding based on whether OPTIONS or FOR follows the name. Same keyword, two distinct objects.

Read the full file on GitHub · 349 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. 4d ago First seen · 349 lines · 93 tokens per session scan A 2ab34f183cb0

Subscribe to this mod's changes

nornicdb-knowledge-policies is a skill published in the GitHub repository orneryd/NornicDB (864 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 5,280 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.

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

graphjin-eval

Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.

dosco/graphjin · 27 tokens

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.

dosco/graphjin · 61 tokens

infrahub-sot

OpsMill Infrahub — infrastructure source of truth with schema-driven nodes, GraphQL queries, and branch-isolated changes. Use when querying Infrahub for device/IPAM inventory, browsing infrastructure schemas, running GraphQL queries, or making infrastructure changes safely via an auto-created session branch and a…

automateyournetwork/netclaw · 71 tokens

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…

OriginTrail/dkg · 87 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