Claude Memory KitSAFE

The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 14 MCP configs, 26 companion apps, 52 ecosystem entries, and more.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: claude-memory-kit
description: "Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero external dependencies."
author: awrshift
version: 3.2.0
tags: [memory, context-management, productivity, agent-memory]
repository: https://github.com/awrshift/claude-memory-kit
license: MIT
---

# Claude Memory Kit

Your Claude agent remembers everything across sessions and projects.

## What it does

- **Persistent memory** — MEMORY.md hot cache + knowledge wiki with [[wikilinks]]
- **Multi-project support** — per-project backlogs and context isolation
- **Safety hooks** — prevent context loss during compression and long sessions
- **`/close-day`** — one command captures your entire day
- **`/tour`** — interactive guided walkthrough

## Quick Start

```bash
git clone https://github.com/awrshift/claude-memory-kit.git my-project
cd my-project
claude
```

## Built from production

700+ sessions across 7 projects. Adapted from Karpathy/Cole Medin's knowledge base pattern, simplified for daily CLI use.

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.