adk-java: Instructions file for Codex

AGENTS.md

adk-java AGENTS.md is an instructions file for Codex, OpenCode from google/adk-java. It costs 23 tokens per session, scanned A, original, Apache-2.0.

A placeholder AGENTS.md instruction file for Google's Java Agent Development Kit project. It currently says that guidance for AI coding agents is coming soon.

In plain words
What is it for?
Use it as the repository's AGENTS.md reference when working in google/adk-java; there are no detailed instructions here yet.
Why use it?
It tells an agent where repository-specific instructions are expected, while making clear that this file does not yet provide substantive guidance.

Instructions file for CodexOpenCode ✓ vendor

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is google/adk-java's own configuration. It tells Codex and OpenCode how to work on adk-java itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adk-java configures →

About the project

ADK for Java is a code-first Java toolkit for building, evaluating, and deploying AI agents, including systems made from multiple cooperating agents and tools. Java developers use it to define agent behavior and orchestration in code, from local development through cloud deployment. The catalogue provides skills and instructions for working with the toolkit.

google/adk-java · 1,765 stars · on GitHub · google.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to google/adk-java. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/google/adk-java/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/google/adk-java

Made for: Codex, OpenCode.

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 adk-java AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/google/adk-java/agents-md/github.svg)](https://agentmods.dev/instructions/google/adk-java/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/google/adk-java/agents-md"><img src="https://agentmods.dev/badge/instructions/google/adk-java/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for adk-java AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/google/adk-java/agents-md"><img src="https://agentmods.dev/badge/instructions/google/adk-java/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 This file is loaded in full into every session.
When invoked 23 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00023 $0.00023
Opus 5.5 $0.00009 $0.00009
Sonnet 5.5 $0.00005 $0.00005
Haiku 4.5 $0.00002 $0.00002

Measured 1mo ago against content hash 8fa4c8d44147, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adk-java AGENTS.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 1mo 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.

AGENTS.md · 5 lines

What it actually says

AGENTS.md

Placeholder - guidance for AI coding agents working in this repository is coming soon.

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. 1mo ago First seen · 5 lines · 23 tokens per session scan A 8fa4c8d44147

Subscribe to this mod's changes

adk-java AGENTS.md is an instructions file published in the GitHub repository google/adk-java (1,765 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session, about $0.0001 per session on Opus 5.5. 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 2026-10-01.

Related

adk-java AGENTS.md compared with instructions from other repositories

adk-java AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adk-java AGENTS.mdgoogle/adk-javaInstructions file1.8kyesterdayApache-2.0A23Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode