explore

A configurable agent for quickly learning how a codebase is organized and how its main parts fit together. A codebase is the complete collection of files that make up a software project.

In plain words
What is it for?
Use it to inspect folders, identify technologies and entry points, discover patterns, analyze dependencies, and create an overview of a project’s architecture.
Why use it?
It reduces the time needed to understand an unfamiliar project before making changes. Its quick, medium, and very thorough modes let you choose between speed and depth.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/daffy0208/ai-dev-standards/explore
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02329
Opus 5 $0.00000 $0.01164
Sonnet 5 $0.00000 $0.00466
Haiku 4.5 $0.00000 $0.00233

Measured 2d ago against content hash 970c38e65c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/explore.md · 546 lines

How it starts

The opening of the file, as written. The whole thing — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore Agent

Fast, configurable codebase exploration agent for understanding project architecture and structure.

Overview

The Explore Agent is optimized for:

  • Initial codebase assessment
  • Architecture understanding
  • Pattern discovery
  • Rapid familiarization

Key Feature: Three thoroughness modes (quick, medium, very thorough)

Thoroughness Modes

Quick Mode

Speed: Fast (seconds to minutes) Depth: Surface-level overview

Best For:

  • Quick sanity checks
  • Initial repository assessment
  • Finding specific patterns
  • High-level architecture overview

What It Does:

  • Scans directory structure
  • Identifies main technologies
  • Maps key files and folders
  • Generates quick summary

Example:

Task: Get overview of React project structure
Mode: Quick
Time: 30 seconds
Output: Directory tree, tech stack, entry points

Medium Mode (Default)

Speed: Moderate (5-15 minutes) Depth: Balanced exploration

Best For:

  • General codebase exploration
  • Understanding project organization
  • Identifying major components
  • Balanced depth vs. speed

What It Does:

  • Comprehensive directory scan
  • File content sampling
  • Dependency analysis
  • Pattern identification
  • Architecture mapping

Example:

Task: Understand authentication flow
Mode: Medium
Time: 10 minutes
Output: Auth components, API endpoints, data flow, dependencies

Very Thorough Mode

Speed: Slow (30+ minutes) Depth: Deep, comprehensive analysis

Best For:

  • Complete system understanding
  • Pre-refactoring analysis
  • Security audits
  • Documentation generation
  • Complex system mapping

What It Does:

  • Reads all relevant files
  • Deep dependency analysis
  • Cross-reference mapping
  • Pattern correlation
  • Comprehensive reporting

Example:

Task: Map entire microservices architecture
Mode: Very Thorough
Time: 45 minutes
Output: Complete service map, API contracts, data flows, dependencies

When to Use Explore Agent

Read the full file on GitHub · 546 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 546 lines · 0 tokens per session scan A 970c38e65c19

Subscribe to this mod's changes

explore is an agent published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,329 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.