A catalogue of the agent types available in Claude Code and the ai-dev-standards repository. It explains the difference between built-in agents and skill-based agents, including their purposes and typical tasks.

Use it to compare agents for bug fixes, feature work, refactoring, code review preparation, codebase exploration, research, and other development tasks.

It gives developers a map of the available choices before they decide which agent to use. This avoids treating every agent as interchangeable.

How daffy0208/ai-dev-standards configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to daffy0208/ai-dev-standards. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/daffy0208/ai-dev-standards/main/.claude/agents/agent-types.md

Clone the repo

git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/agent-types/github.svg)](https://agentmods.dev/agents/daffy0208/ai-dev-standards/agent-types)

Your own site

<a href="https://agentmods.dev/agents/daffy0208/ai-dev-standards/agent-types"><img src="https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/agent-types/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/daffy0208/ai-dev-standards/agent-types"><img src="https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/agent-types.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 3,597 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.03597
Opus 5.5	$0.00000	$0.01439
Sonnet 5.5	$0.00000	$0.00719
Haiku 4.5	$0.00000	$0.00360

Measured 1mo ago against content hash c87346e45f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-types 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 1mo 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/agent-types.md · 711 lines

How it starts

The opening of the file, as written. The whole thing — 711 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Types: Complete Taxonomy

Comprehensive classification of all agent types available in Claude Code and the ai-dev-standards repository.

Overview

Total Agent Types: 10

4 Claude Code Built-in Agents - Native CLI agents
6 Skill-Based Agents - Skills that function as autonomous agents

1. Claude Code Built-in Agents (4)

1.1 General-Purpose Agent

Type: Default, Multi-Purpose Status: Active Invocation: Default mode

Purpose: Comprehensive development agent for most tasks including code search, analysis, editing, and multi-step research.

Core Capabilities:

Multi-file analysis and editing
Complex codebase exploration
System architecture understanding
Multi-step research tasks
File operations (read, write, edit)
Pattern recognition and matching

Best For:

Bug investigation and fixes
Feature implementation
Refactoring
Code review preparation
Ongoing development work

Performance:

Speed: Variable (depends on task)
Depth: High
Memory: Handles large files efficiently

Integration:

Can invoke any of 59 skills
Access to 36 MCP servers
Works with all tools and components

Documentation: general-purpose.md

1.2 Explore Agent

Type: Codebase Discovery Status: Active Invocation: Via explore mode

Purpose: Fast, configurable codebase exploration with three thoroughness levels.

Modes:

Quick - Fast overview (seconds to minutes)
Medium - Balanced exploration (5-15 minutes) [Default]
Very Thorough - Deep analysis (30+ minutes)

Core Capabilities:

Initial repository assessment
Architecture understanding
Pattern discovery
Rapid familiarization
Dependency mapping

Best For:

New codebase onboarding
Pre-refactoring analysis
Security audit preparation
Architecture documentation
Migration planning

Performance:

Speed: Configurable (Quick/Medium/Very Thorough)
Depth: Configurable by mode
Memory: Scales with thoroughness level

Read the full file on GitHub · 711 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.

1mo ago First seen · 711 lines · 0 tokens per session scan A c87346e45f75

Subscribe to this mod's changes

agent-types is an agent published in the GitHub repository daffy0208/ai-dev-standards (38 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,597 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.

Building agents

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

ai-dev-standards: Agent for Claude Code