llm-agents

A core agent type in the Agent Development Kit (ADK) that uses a large language model—an AI system that understands and generates text—to reason, make decisions, and use tools. It is supported in several ADK programming languages.

In plain words
What is it for?
Use it to build AI agents that interpret requests, choose actions, generate responses, and work with tools.
Why use it?
It lets an agent decide how to respond or which tools to use from instructions and context, without requiring every step to be hard-coded.

Agent

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/google/adk-docs/llm-agents
Clone the repo
git clone --depth 1 https://github.com/google/adk-docs
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 7,507 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 $0.07507
Opus 5 $0.00000 $0.03753
Sonnet 5 $0.00000 $0.01501
Haiku 4.5 $0.00000 $0.00751

Measured yesterday against content hash 9f7d8c94f0ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-agents 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 yesterday.

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.

docs/agents/llm-agents.md · 913 lines

How it starts

The opening of the file, as written. The whole thing — 913 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Simple agents with LlmAgent

The LlmAgent class, often aliased simply as Agent, is a core component in ADK, acting as the core part of your agent application. It leverages the power of a Large Language Model (LLM) or generative AI model for reasoning, understanding natural language, making decisions, generating responses, and interacting with tools. Since this type of agent uses an AI model to interpret instructions and context, the AI model dynamically decides how to proceed, which tools to use (if any), and what output to provide. As such, the behavior of this type of agent is non-deterministic and must be built and evaluated with this behavior in mind.

Building an effective LlmAgent involves defining its identity, clearly guiding its behavior through instructions, and equipping it with the necessary tools and capabilities.

Define agent identity and purpose

First, you need to establish what the agent is and what it's for.

  • name (Required): Every agent needs a unique string identifier. This name is crucial for internal operations, especially in multi-agent systems where agents need to refer to or delegate tasks to each other. Choose a descriptive name that reflects the agent's function (e.g., customer_support_router, billing_inquiry_agent). Avoid reserved names like user.

  • description (Optional, Recommended for Multi-Agent): Provide a concise summary of the agent's capabilities. This description is primarily used by other LLM agents to determine if they should route a task to this agent. Make it specific enough to differentiate it from peers (e.g., "Handles inquiries about current billing statements," not just "Billing agent").

Read the full file on GitHub · 913 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. yesterday First seen · 913 lines · 0 tokens per session scan A 9f7d8c94f0ff

Subscribe to this mod's changes

llm-agents is an agent published in the GitHub repository google/adk-docs (1,479 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 7,507 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.