# Filesystem Navigation

> Guidelines for systematically exploring and understanding directory structures.

- **Type:** Skill
- **Install:** `agentstack add skill-esurovtsev-langchain-lab-filesystem-navigation`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [esurovtsev](https://agentstack.voostack.com/s/esurovtsev)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [esurovtsev](https://github.com/esurovtsev)
- **Source:** https://github.com/esurovtsev/langchain-lab/tree/main/experiments/01-agent-skills/skills/filesystem_navigation

## Install

```sh
agentstack add skill-esurovtsev-langchain-lab-filesystem-navigation
```

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

## About

# Filesystem Navigation

## When to Use This Skill

When you are asked to explore, understand, or map a project's file structure. This includes requests like "what is this project?", "show me the structure", or "help me find where X is".

## Strategy

### Start at the Root

Always begin by listing the top-level directory. The root reveals the project type faster than anything else:

- `README.md` or `README.rst` → start here, it's the author's own summary
- `requirements.txt`, `pyproject.toml`, `package.json` → tells you the language and dependencies
- `Dockerfile`, `docker-compose.yml` → the project is containerized
- `Makefile`, `justfile` → there are predefined commands to run
- `.env.example` → environment variables are needed; never read `.env` itself

### Explore Breadth Before Depth

List all top-level directories before diving into any single one. Build a mental map:

- `src/` or `app/` → application code lives here
- `tests/` or `test/` → test suite
- `config/` or `conf/` → configuration
- `docs/` → documentation
- `scripts/` or `bin/` → utility scripts
- `migrations/` or `alembic/` → database migrations

### Go Deeper with Purpose

Don't read every file. Choose what to read based on what you're trying to answer:

- To understand **what the project does** → README, then entry point
- To understand **how it's structured** → list `src/` recursively
- To understand **how to run it** → README, Makefile, Dockerfile, config
- To understand **dependencies** → requirements.txt, package.json, pyproject.toml

## Things to Avoid

- Don't assume a file's purpose from its name alone — `utils.py` could contain anything
- Don't read binary files (images, compiled files, databases)
- Don't read `.env` files — they may contain secrets
- Don't try to read `node_modules/`, `__pycache__/`, `.git/`, or other generated directories
- Don't list deeply nested directories all at once — go level by level

## Signals That Help

- A `__main__.py` or `if __name__ == "__main__"` block indicates an entry point
- A file named `app.py`, `main.py`, or `server.py` is usually the entry point
- `__init__.py` files in Python indicate a package; they may re-export key symbols
- Hidden files (`.gitignore`, `.flake8`, `.pre-commit-config.yaml`) reveal tooling choices

## Source & license

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

- **Author:** [esurovtsev](https://github.com/esurovtsev)
- **Source:** [esurovtsev/langchain-lab](https://github.com/esurovtsev/langchain-lab)
- **License:** MIT

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:** yes
- **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-esurovtsev-langchain-lab-filesystem-navigation
- Seller: https://agentstack.voostack.com/s/esurovtsev
- 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%.