# Kg Core

> | Knowledge Graph — persistent, granular, evolving memory. Part of memory initially arrives preloaded: a "KG MEMORY PRELOADED" block carrying the sessionid and most important portion of memory. Then the full read is on you: kgread(cwd="<project root") comes before any work, whatever the task. Full read still brings up only most important memories. Memory is highly optimised and served in layers. Recall: if needed details are not in preload/read and there is a gist that points in the right direction, recall full node; Capture: at the moment of learning, once the dots connect; Connect rather than duplicate — an edge beats a new node; Search for more — the read/sync shows the top of graph, not all of it. In a rich graph the fact you need is often buried under fresher work; search reaches every tier. A node found when needed earns credit that keeps it alive. Mechanics live in the kg tool descriptions; operations in /kg-ops.

## Facts
- Page: https://tashan.sh/capability/skill-mironmax-kg-core
- tashan id: skill:mironmax/kg-core
- Source: https://github.com/mironmax/claudecode-plugins
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 79.0
- Freshness: 94.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r kg-core ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-20 by tashan (https://tashan.sh) from public evidence. Scorer s5.