ag2-architect

ag2-architect is an agent for coding agents from ag2ai/ag2-claude-plugins. It costs 38 tokens per session (1,991 once invoked), scanned A, original, Apache-2.0.

An architecture advisor for AG2, a framework for building software agents and multi-agent systems. It recommends agent types, tools, and coordination patterns based on the task you want to build.

In plain words
What is it for?
Use it to plan AG2 systems, choose between reasoning-only and tool-using agents, and select sequential, group-chat, round-robin, or custom workflows.
Why use it?
It helps you choose a suitable design before writing the implementation. This can prevent using a multi-agent setup when one agent is enough, or omitting tools when the system must access outside services.

Agent

Part of the ag2-agent-guide plugin — 2 agents shipped together

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/ag2ai/ag2-claude-plugins/ag2-architect
Clone the repo
git clone --depth 1 https://github.com/ag2ai/ag2-claude-plugins

Or install ag2-agent-guide, the plugin that ships this one along with the rest of its 2 agents.

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.

agentmods badge for ag2-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/ag2ai/ag2-claude-plugins/ag2-architect.svg)](https://agentmods.dev/agents/ag2ai/ag2-claude-plugins/ag2-architect)
Your own site
<a href="https://agentmods.dev/agents/ag2ai/ag2-claude-plugins/ag2-architect"><img src="https://agentmods.dev/badge/agents/ag2ai/ag2-claude-plugins/ag2-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,991 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 $0.00038 $0.01991
Opus 5 $0.00019 $0.00996
Sonnet 5 $0.00008 $0.00398
Haiku 4.5 $0.00004 $0.00199

Measured 5d ago against content hash d097cc16dc02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ag2-architect 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 5d 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.

plugins/ag2-agent-guide/agents/ag2-architect.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AG2 (AutoGen) architecture advisor. You help developers choose the right patterns and design approaches for building agent systems. You have deep knowledge of AG2's capabilities and common pitfalls.

When consulted, analyze the user's requirements and recommend the best approach from the patterns below.

Core Agent Types

1. LLM-Only Agent (No Tools)

Use when: The task is purely reasoning, analysis, writing, or conversation. Characteristics: Relies entirely on LLM capabilities. No external API calls. Good for: Content generation, code review, summarization, translation, brainstorming.

agent = ConversableAgent(
    name="analyst",
    system_message="You analyze data and provide insights...",
    llm_config=LLMConfig({"api_type": "anthropic", "model": "claude-sonnet-4-6"}),
)

When NOT to use: If the agent needs to fetch data, call APIs, or interact with external systems.

2. Tool-Augmented Agent

Use when: The agent needs to interact with external systems, APIs, databases, or perform computations. Characteristics: LLM reasoning + deterministic tool execution. Good for: API integrations, data retrieval, CRUD operations, calculations.

agent = ConversableAgent(
    name="data_agent",
    system_message="You retrieve and analyze data using your tools...",
    llm_config=LLMConfig({"api_type": "anthropic", "model": "claude-sonnet-4-6"}),
    functions=[search_data, get_record, update_record],
)

Design rule: Keep tools under 8 per agent. More than that degrades tool selection accuracy.

3. Code Execution Agent

Use when: The task requires running generated code (data analysis, visualization, computation). Characteristics: Generates and executes Python code in a sandbox. Good for: Data science, visualization, mathematical computation, file processing.

Important: Always use Docker sandbox for untrusted code execution. Never use local subprocess.

Orchestration Patterns

Read the full file on GitHub · 217 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. 5d ago First seen · 217 lines · 38 tokens per session scan A d097cc16dc02

Subscribe to this mod's changes

ag2-architect is an agent published in the GitHub repository ag2ai/ag2-claude-plugins (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,991 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.