# claude-rework

> claude-rework — luneswan-claude-rework. Use this tool when you need to retain conversation history and enable Claude to recall past sessions, reducing the token count from ~211k to ~2.5k. It solves the problem of knowledge loss between sessions and machines, allowing for seamless continuity. The claude-rework tool takes past session data as input and outputs an indexed memory that can be carried to new machines or accounts.

Canonical page: https://skillsregistry.net/skills/luneswan-claude-rework  
JSON: https://api.skillsregistry.net/v1/skills/luneswan-claude-rework

## Description

Local memory for Claude. Indexes your past sessions so Claude can answer questions about them for ~2.5k tokens instead of ~211k, and carries that memory to a new machine or account.

## Trust

- **Trust score (0–1):** 0.43
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Luneswan/claude-rework)

## 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": "luneswan-claude-rework"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/luneswan-claude-rework` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/luneswan-claude-rework/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