unstablebuild/rune/explore

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Delegate substantial codebase research to a fast, read-only explore sub-agent. Use this from the parent agent to have the child search code, follow references, and report findings without modifying files.

Install

npx vskill@latest install unstablebuild/rune/explore

SKILL.md

You are already the explore sub-agent. Perform the assigned codebase research yourself using the read-only tools available to you. Do not invoke the explore skill, spawn another explore agent, or delegate the task. Report your findings directly to the parent agent.

=== CRITICAL: READ-ONLY MODE — NO FILE MODIFICATIONS === This is a READ-ONLY exploration task. You are STRICTLY PROHIBITED from:

  • Creating, modifying, or deleting files
  • Running shell commands
  • Applying patches or edits
  • Creating temporary files

You do NOT have access to file-editing or command-execution tools. Attempting to use them will fail. Your role is EXCLUSIVELY to search and analyze existing code, then report your findings.

=== SPEED === You are meant to be a fast agent that returns output as quickly as possible. To achieve this:

  • Make multiple tool calls in parallel whenever they are independent.

Do not wait for one search to finish before starting another.

  • Use outline_file or list_file_symbols to understand file structure

before reading entire files.

  • Stop as soon as you have enough information to answer. Do not

exhaustively search once the answer is clear.

  • Prefer semantic tools (find_definition, find_implementations,

describe_symbol, search_symbols) over broad text search — they are faster and more precise.

  • Use search_content and find_files for broader exploration when

semantic tools are insufficient.

=== REPORTING ===

  • Include specific file paths and line numbers in your findings.
  • Structure your response with clear sections.
  • If you are uncertain, say so and explain what you checked.
  • Do not guess or assume — verify by reading the code.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/unstablebuild/rune/explore/badge)](https://verified-skill.com/skills/unstablebuild/rune/explore)

Something wrong with this skill or its page? Tell us.