Skill

explore-investigate

Launch a full architecture exploration investigation with hierarchical delegation

Install

npx claudepluginhub justn-hyeok/harness-for-yall --plugin explore-team

Tool Access

This skill uses the workspace's default tool permissions.

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

138.9k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

bmad-help

Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.

bmad-pro-skills

43.8k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitApr 7, 2026

Actions

View Source View Plugin View on GitHub View README

Process

When triggered, orchestrate the exploration:

Launch explore-scout as the lead agent with the user's question:

Use Agent tool with subagent_type: "general-purpose" and model: "opus"
The scout will: a. Survey the codebase structure b. Delegate hypothesis generation to explore-hypothesizer c. Delegate evidence gathering to explore-evidence d. Delegate report synthesis to explore-synthesizer e. Review and deliver the final report

Pass the question verbatim — do not rephrase or narrow the scope unless the user asks

Deliver the final report from explore-scout to the user

Prompt Template for explore-scout

You are explore-scout. The user wants to investigate: "{user_question}" Working directory: {cwd} Follow your agent instructions in .claude/agents/explore-scout.md. Start with broad codebase survey, then delegate to: - explore-hypothesizer: for generating competing hypotheses - explore-evidence: for gathering supporting/refuting evidence - explore-synthesizer: for producing the final architecture report Deliver the final reviewed report.

explore-investigate

Full architecture exploration using the explore agent team.

Usage

/explore-investigate <question or target>

Examples

/explore-investigate how does the auth flow work
/explore-investigate what would break if we remove the legacy adapter
/explore-investigate root cause of flaky payment tests

Process

When triggered, orchestrate the exploration:

Launch explore-scout as the lead agent with the user's question:
- Use Agent tool with subagent_type: "general-purpose" and model: "opus"
- The scout will: a. Survey the codebase structure b. Delegate hypothesis generation to explore-hypothesizer c. Delegate evidence gathering to explore-evidence d. Delegate report synthesis to explore-synthesizer e. Review and deliver the final report
Pass the question verbatim — do not rephrase or narrow the scope unless the user asks
Deliver the final report from explore-scout to the user

Prompt Template for explore-scout

You are explore-scout. The user wants to investigate:

"{user_question}"

Working directory: {cwd}

Follow your agent instructions in .claude/agents/explore-scout.md.
Start with broad codebase survey, then delegate to:
- explore-hypothesizer: for generating competing hypotheses
- explore-evidence: for gathering supporting/refuting evidence  
- explore-synthesizer: for producing the final architecture report

Deliver the final reviewed report.