overview

An overview of the Agent Starter Pack, a collection of ready-made templates for building software agents with different frameworks and languages. It follows a bring-your-own-agent approach, so developers can choose their preferred framework or pattern.

In plain words
What is it for?
Use it to choose a starting template for conversational agents, document search and question answering, Go, Java, TypeScript, LangGraph, or agents that communicate through the Agent2Agent protocol.
Why use it?
It helps developers compare the available templates before starting an agent project.

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/googlecloudplatform/agent-starter-pack/overview
Clone the repo
git clone --depth 1 https://github.com/GoogleCloudPlatform/agent-starter-pack
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 1,670 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 $0.01670
Opus 5 $0.00000 $0.00835
Sonnet 5 $0.00000 $0.00334
Haiku 4.5 $0.00000 $0.00167

Measured 2d ago against content hash 171c248f8509, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

overview 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.

docs/agents/overview.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Templates

The Agent Starter Pack follows a "bring your own agent" approach. It provides several production-ready agent templates designed to accelerate your development while offering the flexibility to use your preferred agent framework or pattern.

Available Templates

Agent Name Description Use Case
adk A base ReAct agent implemented using Google's Agent Development Kit General purpose conversational agent
adk_go A base ReAct agent implemented using Google's Agent Development Kit for Go Go-based conversational agent
adk_ts A base ReAct agent implemented using Google's Agent Development Kit for TypeScript TypeScript/Node.js-based conversational agent
adk_java A base ReAct agent implemented using Google's Agent Development Kit for Java Java-based conversational agent
adk_a2a An ADK agent with Agent2Agent (A2A) Protocol support Distributed agent communication and interoperability across frameworks
agentic_rag A RAG agent for document retrieval and Q&A Document search and question answering
langgraph A base ReAct agent implemented using LangChain's LangGraph Graph based conversational agent
adk_live A real-time multimodal RAG agent Audio/video/text chat with knowledge base

Choosing the Right Template

When selecting a template, consider these factors:

  1. Primary Goal: Are you building a conversational bot, a Q&A system over documents, a task-automation network, or something else?
  2. Programming Language: Do you prefer Python, Go, TypeScript, or Java? Most templates are Python-based, but adk_go, adk_ts, and adk_java provide Go, TypeScript, and Java alternatives.
  3. Core Pattern/Framework: Do you have a preference for Google's ADK, LangChain/LangGraph, or implementing a pattern like RAG directly? The Starter Pack supports various approaches.
  4. Reasoning Complexity: Does your agent need complex planning and tool use (like ReAct), or is it more focused on retrieval and synthesis (like basic RAG)?
  5. Collaboration Needs: Do you need multiple specialized agents working together?
  6. Modality: Does your agent need to process or respond with audio, video, or just text?

Read the full file on GitHub · 115 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 · 115 lines · 0 tokens per session scan A 171c248f8509

Subscribe to this mod's changes

overview is an agent published in the GitHub repository GoogleCloudPlatform/agent-starter-pack (6,547 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,670 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.