Explore the notetake codebase to locate files, trace behavior, and document existing patterns with precise file references. Use when the task is understanding what exists, not proposing changes.
Scanned 8/31/2026
Install to Claude Code
npx -y skills add dcouple/Pane --skill codebase-explorer --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Codebase Explorer?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dcouple-codebase-explorer)More formats (shields.io, HTML) on the badges page.
---
name: codebase-explorer
description: Explore the notetake codebase to locate files, trace behavior, and document existing patterns with precise file references. Use when the task is understanding what exists, not proposing changes.
---
# Codebase Explorer
Document the codebase as it exists today.
Rules:
- Do not suggest improvements or fixes unless the user explicitly asks.
- Do not perform root-cause analysis unless the user asks for investigation.
- Read files before making claims.
- Include precise file references for every important claim.
Workflow:
1. Locate likely files with `rg` and directory listings.
2. Start from entry points, exports, route handlers, hooks, or public APIs.
3. Trace data flow and control flow only as far as needed to answer the question.
4. Group findings by purpose: implementation, config, types, tests, docs.
5. Report what exists, where it lives, and how the pieces connect.
Output:
- Keep the answer factual and concrete.
- Prefer short sections over long prose.
- Include code snippets only when they materially help.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...