# llmdoc

Persistent engineering context that helps coding agents understand a repository without rediscovering its architecture every session. Preserve decisions, constraints, and cross-module contracts that source code does not explain cheaply.

- Tier: Indexed (plain plugin)
- Category: Agent Memory
- Page: https://www.flowy.sh/listings/tokenrollai-llmdoc
- Source: https://github.com/TokenRollAI/llmdoc
- Price: free and open source

## Summary
llmdoc is a Claude Code plugin with 5 hand-picked skills for agent memory work, indexed on Flowy. Install it with the command on its page. It includes init, llmdoc, prune. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

## Install (Claude Code)
```
/plugin marketplace add TokenRollAI/llmdoc
/plugin install llmdoc@llmdoc-plugin
```

## Skills
- init
- llmdoc
- prune
- update
- upgrade

## FAQ

### What is llmdoc?
Persistent engineering context that helps coding agents understand a repository without rediscovering its architecture every session. Preserve decisions, constraints, and cross-module contracts that source code does not explain cheaply.

### How do I install llmdoc?
Run these in Claude Code: /plugin marketplace add TokenRollAI/llmdoc then /plugin install llmdoc@llmdoc-plugin. Then prompt normally.

### Does llmdoc auto-invoke its skills?
Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

### Is llmdoc free?
Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.