# Tool Tree

> tool-tree

- Skill: `niksavis/tool-tree-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add niksavis/tool-tree-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/niksavis/tool-tree-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: niksavis (https://skillmd.com/u/niksavis)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/niksavis/tool-tree-2

---

# tool-tree

## When To Use

- Understand repository structure at a glance.
- Share compact hierarchy snapshots in terminal workflows.
- Verify output locations for generated files and folders.

## Trusted Commands

```bash
tree
tree -L 2
tree -d
tree -I 'node_modules|dist|__pycache__'
tree -sh
tree -J .
```

## Safe Defaults

- Limit depth (`-L`) to keep output concise.
- Exclude heavy or generated directories with `-I`.
- Use `--charset ascii` for plain-text CI logs.

## Common Pitfalls

- Large trees can flood context and hide important paths.
- Hidden files may be missed without explicit options.
- Tree output does not represent git status semantics.

## Output Interpretation

- Text output shows parent-child structure and totals.
- `-J` outputs structured JSON with type/name/children fields.

## Why It Matters For Agents

- `tree -J` provides a one-call structural map for programmatic workflows.
- It is often the most token-efficient way to understand project shape.

## Repo Conventions

- Prefer concise tree snapshots for architecture and layout discussions.
- Filter caches and generated directories unless task scope needs them.

## Trigger Examples

- Should trigger: "Show me the top-level shape of this workspace."
- Should trigger: "Verify where generated skill files landed."
- Should not trigger: "Find every regex match inside Python files."