index

An agent framework component for building software units that use an AI model, instructions, and optionally tools to work toward goals. It supports Python, TypeScript, Go, and Java.

In plain words
What is it for?
Use it to build autonomous agents, connect them to tools, and coordinate several agents or code tasks.
Why use it?
It helps you split a complex AI application into smaller agents and workflows that are easier to manage.

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/index
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 1,247 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 $0.01247
Opus 5 $0.00000 $0.00624
Sonnet 5 $0.00000 $0.00249
Haiku 4.5 $0.00000 $0.00125

Measured yesterday against content hash 6f2924f7c12a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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/index.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

An Agent, or LlmAgent, in Agent Development Kit (ADK) is a self-contained execution unit designed to act autonomously to achieve specific goals. Agents can perform tasks, interact with users, utilize external tools, and coordinate with other agents. The basic components of an Agent are an artificial intelligence (AI) model, task instructions, and optionally, a set of tools to be used by the agent. As agent tasks and complexity grow, you can use the ADK development framework to expand them into workflows, which allow you to combine and orchestrate multiple agents and code execution tasks.

Figure 1. Simple Agents and Agent Workflows in ADK

Building an agent with just a model, instructions, and tools is a great place to start for most developers. As your agent grows in capability and complexity, you are likely to want to break up the capabilities of your agent application in order to better manage its behavior, work within model operating context limits, and modularize your code to keep it manageable. ADK agent Workflow architectures allow you to evolve an agent from a monolithic structure to more modular code and project structures.

Grow from single agent to workflows

In ADK, any agent application that has more than one agent or executable Node is considered a workflow. ADK does not impose any hard requirements to move from a single-agent architecture to a multi-agent or graph-based Workflow architecture. You can decide when to make that change based on the needs of your project, or as you discover limitations of a single-agent approach, such as:

  • Instruction following performance: Beyond a certain length or complexity of a multiple step set of instructions, you may discover that a single agent does not reliably complete all instructions, or perform them with the required level of quality or speed.
  • Context limitations: You may discover that the amount of data required to perform an agent task exceeds the context window limitations of the AI model you are using.
  • Agent code modularity: As the complexity and organization of your agent code grows, you may want to break up the agent capabilities to make your code more manageable or enable re-use of agent code for other agent projects.
  • Mixing deterministic and non-deterministic tasks: As you build agents for solving more complex problems, you may want to design and build agents that interweave the non-deterministic functionality of AI models with deterministic code, rather than relying on non-deterministic AI models to manage the full execution of a task. For more details, see Graph-based workflows.

Read the full file on GitHub · 112 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 · 112 lines · 0 tokens per session scan A 6f2924f7c12a

Subscribe to this mod's changes

index 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 1,247 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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

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

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