Skip to main content
subagent official · Anthropic

explore — Claude Code subagent: what it does, how to install

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

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin install claude-security@claude-plugins-official
Open on GitHub

What explore 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.

What it helps with

  • 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 for the agent

  • 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?

How to install explore

1Plugin marketplace

/plugin install claude-security@claude-plugins-official

2Manually: put the files in place

.claude/agents/explore.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about explore

How to install explore in Claude Code?

Run /plugin install claude-security@claude-plugins-official.

What does the explore subagent do?

It inspects codebases in read-only mode, maps execution flows, and returns answers backed by exact file:line references.

Can explore modify project files or run builds?

No, it has no file-editing capabilities. Terminal commands are restricted to read-only utilities like find, cat, and git grep.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set123

The whole set →
architecture-critic Subagent that audits architectural designs and modernized code with a skeptical lens. Spots over-engineering, unstated latency risks, and redundant service boundaries. ★ 44,635repo stars scan-researcher A read-only security auditing subagent for Claude Code. Traces vulnerabilities from untrusted inputs to risky sinks across repository files without executing project code. ★ 44,635repo stars scan-redactor This Claude Security subagent replaces secret values in completed scan reports with [REDACTED]. Scan jobs dispatch it automatically; it is not for direct invocation. ★ 44,635repo stars scan-inventory Internal cartographer subagent for the Claude Security scan workflow. It partitions repository directories into discrete review targets and tracks intentionally skipped paths. ★ 44,635repo stars claude-security Scans a repository or its changes, then can turn verified findings into targeted patch files. It runs only as the main agent of a session. ★ 44,635repo stars revise-claude-md Reviews your active session to extract practical codebase learnings and updates CLAUDE.md or .claude.local.md. Helpful after discovering new CLI flags or test quirks. ★ 44,635repo stars agent-sdk-verifier-ts Verifies @anthropic-ai/claude-agent-sdk applications before release. It detects type errors, misconfigured TypeScript settings, and exposed credentials. ★ 44,635repo stars agent-sdk-verifier-py Checks a Python Agent SDK application for configuration issues, SDK usage, security gaps, and readiness for testing or deployment. ★ 44,635repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor