agentmods.dev

adk-java GEMINI.md

Project guidance for Google's Agent Development Kit for Java, a code toolkit for building and running AI agents. It covers the multi-module Maven project and its development commands.

In plain words
What is it for?
Use it when working on the ADK's agent classes, sessions, tools, sub-agents, Maven modules, or local development tasks.
Why use it?
It gives a coding agent the project's structure and workflow, reducing mistakes when building, testing, or changing the Java code.

Instructions file for Gemini CLI

1.7k 4d ago A scan 1,249 tokens original Apache-2.0
View the source file google/adk-java
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 instructions/google/adk-java/gemini-md
Clone the repo
git clone --depth 1 https://github.com/google/adk-java

Made for: Gemini CLI.

Per session 1,249 This file is loaded in full into every session.
When invoked 1,249 The same file — it is already loaded in full.
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 $0.01249 $0.01249
Opus 5 $0.00624 $0.00624
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured yesterday against content hash f8a1b402b1f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adk-java GEMINI.md 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.

GEMINI.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Code Assistant Context

This document provides context for the Gemini Code Assistant to understand the "Agent Development Kit (ADK) for Java" project.

Project Overview

The "Agent Development Kit (ADK) for Java" is an open-source, code-first toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control. It allows developers to define agent behavior, orchestration, and tool use directly in Java code, enabling robust debugging, versioning, and deployment.

The project is a multi-module Maven project with the following key modules:

  • core: The core module contains the main logic of the ADK. It includes the following key components:

    • BaseAgent: The abstract base class for all agents. It defines the basic properties of an agent, such as its name, description, and sub-agents. It also defines the runAsync() and runLive() methods, which are the entry points for running an agent.
    • LlmAgent: The primary implementation of a BaseAgent. It can be configured with a model, instructions, tools, and sub-agents.
    • BaseSessionService: An interface for managing sessions. It provides methods for creating, retrieving, listing, and deleting sessions, as well as listing and appending events to a session.
    • Runner: The main class for running agents. It takes a BaseAgent, a BaseArtifactService, a BaseSessionService, and a BaseMemoryService as input. It provides runAsync() and runLive() methods for running the agent.
    • Core Runtime: The core runtime of the ADK is responsible for orchestrating the execution of agents. It uses the Runner to run the agent and the BaseSessionService to manage the session.

  • dev: This module contains the development UI for testing, evaluating, and debugging agents. It includes a Spring Boot-based web server that can be used to debug agents developed using ADK.

    Agent Loading:

    The dev module provides a flexible mechanism for loading agents into the ADK Web Server through the AgentLoader interface. This interface has two implementations:

Read the full file on GitHub · 98 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 · 98 lines · 1,249 tokens per session scan A f8a1b402b1f7

Subscribe to this mod's changes

adk-java GEMINI.md is an instructions file published in the GitHub repository google/adk-java (1,708 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,249 tokens to every session, about $0.0062 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 2026-08-30.

LanguagesMulti-AgentProductivityagentagentsaiai-agentsmulti-agent-systems
Related

Other instructions, from other repositories

adk-python AGENTS.md

Instructions for google/adk-python, covering project overview, key components, adk knowledge, architecture, and style, project architecture and development setup.

google/adk-python · 322 tokens

clankerchat AGENTS.md

Instructions for simozampa/clankerchat: Preserve changes you did not create. Keep edits small and use Conventional Commits without attribution trailers. Run npm run check before declaring work complete.

simozampa/clankerchat · 62 tokens

clankerchat CLAUDE.md

Instructions for simozampa/clankerchat: Preserve concurrent changes, make small Conventional Commits without attribution trailers, and run npm run check before declaring work complete.

simozampa/clankerchat · 32 tokens

oneagent AGENTS.md

Instructions for 1broseidon/oneagent, covering oneagent, what this is, repo: https://github.com/1broseidon/oneagent, docs and architecture.

1broseidon/oneagent · 540 tokens

oneagent CLAUDE.md

Instructions for 1broseidon/oneagent, a project described as: Config-driven multi-agent CLI. One interface for Claude, Codex, Cursor, OpenCode, Cline, Pi, and any future agent.

1broseidon/oneagent · 3 tokens

open-agents AGENTS.md

AGENTS.md instructions for vercel-labs/open-agents, covering agents.md, quick links, authentication, database & migrations and environment isolation.

vercel-labs/open-agents · 1,250 tokens