Skip to content
cccskills
FreePublished on GitHub

scout

Map unfamiliar code or research an approach before planning, read-only and fast.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md1.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Scout - Quick Exploration

Delegate exploration tasks to the Scout agent (haiku model - fast & cheap).

Usage

/scout how does authentication work here?
/scout where is the database schema defined?
/scout what options do we have for caching?
/scout                    # will ask what to explore

Process

  1. If no question provided, ask: "What do you want to explore?"

  2. Delegate to Scout agent:

"Scout, explore: [question]

Context:
- Project: [current directory/project name]
- Relevant area: [if obvious from question]

Return:
- What you found
- How it works
- Options (if applicable)
- Unknowns or questions for the user"
  1. Present Scout's findings to the user

  2. Ask: "Want me to dig deeper on anything?"

When to Use

  • "How does X work in this codebase?"
  • "Where is Y implemented?"
  • "What are our options for Z?"
  • "Find all places that do X"
  • Before starting work on unfamiliar area
  • Quick research on approaches

Scout's Strengths

  • Fast (haiku model)
  • Systematic (follows code paths, checks tests, looks at git history)
  • Evidence-based (cites files and line numbers)
  • Surfaces unknowns (doesn't hide gaps)

Examples

Exploring a feature:

/scout how does the scraper handle rate limiting?

Finding implementations:

/scout where are all the API endpoints defined?

Researching options:

/scout what libraries could we use for PDF generation?

Understanding patterns:

/scout what's the error handling pattern in this codebase?

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Branch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.

The English summary is being prepared. Showing the original description.

ToruAI/toru-claude-agents15Updated Jul 26, 2026

Look up how Claude Code itself works — hooks, skills, subagents, MCP, plugins, settings — from the official docs, so answers come from the current spec instead of memory.

The English summary is being prepared. Showing the original description.

ToruAI/toru-claude-agents15Updated Jul 26, 2026

Design better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.

The English summary is being prepared. Showing the original description.

ToruAI/toru-claude-agents15Updated Jul 26, 2026

Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.

The English summary is being prepared. Showing the original description.

ToruAI/toru-claude-agents15Updated Jul 26, 2026

Close out a session — summarise what changed, capture what was learned, and prepare the commit.

The English summary is being prepared. Showing the original description.

ToruAI/toru-claude-agents15Updated Jul 26, 2026

Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.

The English summary is being prepared. Showing the original description.

ToruAI/toru-claude-agents15Updated Jul 26, 2026

See all skills by ToruAI

Report a problem with this skill