Skills / explore
explore
Map an unfamiliar codebase before changing it, reading only what the question needs. Use when asked to understand, survey or find where something lives in a repository, or before changing code you have not seen. Do not use when you already know where the change goes.
OfficialAuditA
- Author
- agentsaisle
- Latest
- v1.1.0
- Aisle
- code
- Works with
- Claude Code, Codex, Cursor
- Source
- HazemSalah29/agentsaisle
- Stars
- 2
Install
Install explore
npx @agentsaisle/cli add exploreInstalls into your project's skills folder. Add --global to install it for every project.
Audit
A
- Critical
- 0
- High
- 0
- Medium
- 0
- Low
- 0
3 files · audited 2026-10-29 · rules 1.0.0
No findings.
What this skill can use
Tools
- Read
- Grep
- Glob
- Bash(git log *)
- Bash(git ls-files *)
Scripts
None
Domains mentioned
None
Automated checks found no known risky patterns. This is not a guarantee of safety. How audits work · Read the rules
Show this grade in a README
The badge updates when the registry is rebuilt. Paste this Markdown into the README:
[](https://agentsaisle-vercel.vercel.app/skills/explore)SKILL.md
Rendered from commit 4036c95
Explore
Use when
- You are asked how something works or where it lives.
- You are about to change code in an area you have not read.
Don't use when
- You already know the files involved.
- The task is to change code, not to understand it.
Steps
- Restate the question in one line and say what would count as an answer.
- Start from entry points: the README, manifest files (package.json, pyproject.toml, go.mod) and the top-level folders.
- Search before reading: look for symbols, routes and config keys, then open only the files that matter.
- Follow one real path end to end (input to handler to storage) instead of skimming everything.
- Note conventions to follow and anything surprising.
Budget
- Search first (grep, glob, symbol search). Read line ranges, not whole files.
- Read at most 8 files per step. If you need more, write down what you learned and narrow the question.
- Do not re-read a file you just wrote or edited.
- Prefer the smallest command output that answers the question: head, tail, quiet flags, filtered lists.
- Never edit files, run migrations or execute project scripts while exploring.
Output
- Where the relevant code lives (
path:line), how data flows, conventions to follow, open questions. - At most 30 lines.
Done when
- The question is answered with specific files and lines.
- No file was changed.
Version history
| Version | Commit | Install |
|---|---|---|
| 1.1.0latest | 4036c95 | add explore |