Example CommandSAFE

Official, Anthropic-managed directory of high quality Claude Code Plugins.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: example-command
description: An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
argument-hint: <required-arg> [optional-arg]
allowed-tools: [Read, Glob, Grep, Bash]
---

# Example Command (Skill Format)

This demonstrates the `skills/<name>/SKILL.md` layout for user-invoked slash commands. It is functionally identical to the legacy `commands/example-command.md` format — both are loaded the same way; only the file layout differs.

## Arguments

The user invoked this with: $ARGUMENTS

## Instructions

When this skill is invoked:

1. Parse the arguments provided by the user
2. Perform the requested action using allowed tools
3. Report results back to the user

## Frontmatter Options Reference

Skills in this layout support these frontmatter fields:

- **name**: Skill identifier (matches directory name)
- **description**: Short description shown in /help
- **argument-hint**: Hints for command arguments shown to user
- **allowed-tools**: Pre-approved tools for this skill (reduces permission prompts)
- **model**: Override the model (e.g., "haiku", "sonnet", "opus")

## Example Usage

```
/example-command my-argument
/example-command arg1 arg2
```

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.