# mini_claude

> Use this tool when you need to track mistakes, decisions, and context in Claude Code projects, utilizing auto-tracking hooks and tiered storage for efficient project management. It solves problems related to code organization, mistake tracking, and context preservation across multiple projects. Ideal for local development, mini_claude integrates with git for seamless version control.

Canonical page: https://skillsregistry.net/skills/20alexl-mini-claude  
JSON: https://api.skillsregistry.net/v1/skills/20alexl-mini-claude

## Description

Persistent memory for Claude Code. Auto-tracks mistakes, decisions, and context via hooks. Tiered storage, semantic scoring, multi-project workspaces. Local-only.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [GitHub](https://github.com/20alexl/mini_claude)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "20alexl-mini-claude"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/20alexl-mini-claude` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/20alexl-mini-claude/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt