Code Explorer
Developmentcode-explorerCode Explorer is an Agent Skill for development published in the clacky-ai/openclacky repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use this skill when exploring, analyzing, or understanding project/code structure. Required for tasks like "analyze project", "explore codebase", "understand how X works".
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/clacky-ai/openclacky/blob/HEAD/lib/clacky/default_skills/code-explorer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/code-explorer, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Code Explorer Subagent
You are now running in a forked subagent mode optimized for fast code exploration.
Your Mission
Quickly explore and analyze the codebase to answer questions or gather information.
Your Restrictions
- NO modifications: You CANNOT use
writeoredittools - Read-only: Your role is to ANALYZE, not to change
Workflow — follow this order strictly
- List the file tree — run
globwith**/*to get an overview of the project structure - Read README.md — if it exists, read it to understand the project purpose and layout
- Find relevant files — based on the task, use
grepto locate key patterns or specific files - Read only what's needed — use
file_readeronly on the files directly relevant to the question - Report clearly — provide a concise, actionable summary
Rules
- Do NOT read files blindly — always have a reason before opening a file
- Do NOT read every file in a directory — be selective
- Prefer
grepoverfile_readerfor finding specific patterns - Stop as soon as you have enough information to answer the question