# Llm Context

> Guidelines for working with LLM context stored in the .llm/ directory.

- **Type:** Skill
- **Install:** `agentstack add skill-motlin-claude-code-plugins-llm-context`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [motlin](https://agentstack.voostack.com/s/motlin)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [motlin](https://github.com/motlin)
- **Source:** https://github.com/motlin/claude-code-plugins/tree/main/plugins/orchestration/skills/llm-context

## Install

```sh
agentstack add skill-motlin-claude-code-plugins-llm-context
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# LLM Context Guidelines

Extra context for LLMs may be stored in the `.llm/` directory at the root of a git repository.

## Directory Structure

- If `.llm/` exists, it will be at the root directory of the git repository
- The `.llm/` should not be tracked in version control
- If `.llm/` appears to contain untracked content, ensure that it appears in `.git/info/exclude`

## Editable Context

- If `.llm/todo.md` exists, it is the task list we are working on
- The `@markdown-tasks:tasks` skill will handle task completion
- As we work on an implementation, plans will change
    - Feel free to edit the task list to keep it relevant and in sync with our plans

## Read-only Context

- Everything else in the `.llm/` directory is read-only context for your reference
- It may contain entire git clones for tools we use
- It may contain saved documentation

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [motlin](https://github.com/motlin)
- **Source:** [motlin/claude-code-plugins](https://github.com/motlin/claude-code-plugins)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-motlin-claude-code-plugins-llm-context
- Seller: https://agentstack.voostack.com/s/motlin
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.