# explore

Read-only codebase explorer for Claude Code. Locates files, traces execution flows, and finds symbol callers without modifying code.

- subagent · `type=agent` · Claude Code · ★ 44635
- Author: Anthropic · official Anthropic repository
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/anthropics/claude-plugins-official/tree/HEAD/plugins/claude-security/agents/explore.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/explore

## What it does

The `explore` subagent runs on `sonnet` with `xhigh` effort. Other agents dispatch it to map a repository, trace end-to-end flows, or locate where a specific function lives. It operates via absolute paths provided by the dispatch (`SCAN_ROOT`) and queries git strictly with `git -C <root>`, ensuring working directory changes never break the search.

Safety is enforced at the tool level. The subagent has access to `Read`, `Glob`, `Grep`, and a restricted `Bash` tool. Terminal usage is limited strictly to read-only commands such as `find`, `cat`, `head`, and `git grep`. It cannot run package managers, edit files, or execute test runners. Modifying repository files is impossible here: it lacks file-writing tools.

Every file it inspects is treated as untrusted data. Instructions embedded in comments, commit messages, or `CLAUDE.md` are treated as research targets rather than agent prompts. Its final report leads with a direct answer, provides `file:line` citations, and explicitly lists any unverified assumptions.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin install claude-security@claude-plugins-official
```

2. **Manually: put the files in place**
- File: `.claude/agents/explore.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/explore.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/explore.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/anthropics/claude-plugins-official/tree/HEAD/plugins/claude-security/agents/explore.md

## When to use it
- locate where a specific symbol or function is defined and called
- trace execution flows across multiple files end to end
- map unfamiliar codebases before writing patches or tests
- inspect code without risks of accidental edits or running unwanted builds

## Example prompts
- Find all callers and definitions of the `processPayment` function.
- Trace the webhook handler flow from the router down to database writes.
- Where does the repository configure Redis connection timeouts?

## Similar
- [frontend-developer](https://affpapa.org/en/nevibecode/agents/voltagent-community-frontend-developer.md) — subagent · 40905 installs
- [dx-optimizer](https://affpapa.org/en/nevibecode/agents/dx-optimizer.md) — subagent · 1198 installs
- [mlops-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-mlops-engineer.md) — subagent · 1009 installs
- [postgres-pro](https://affpapa.org/en/nevibecode/agents/postgres-pro.md) — subagent · 897 installs
- [agent-installer](https://affpapa.org/en/nevibecode/agents/agent-installer.md) — subagent · 363 installs
- [embedded-systems](https://affpapa.org/en/nevibecode/agents/embedded-systems.md) — subagent · 279 installs

From the same set: [anthropics/claude-plugins-official](https://affpapa.org/en/nevibecode/by/anthropics/claude-plugins-official.md) — 123 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md