adk CLAUDE.md

adk CLAUDE.md is an instructions file for coding agents from inference-gateway/adk. It costs 2,546 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the A2A Agent Development Kit, a Go library for building software agents and clients that communicate through the Agent-to-Agent protocol. It covers the repository structure, commands, architecture, examples, and its upstream schema.

In plain words
What is it for?
Use it when developing the Go server, client, or types packages, running project checks, maintaining example applications, tidying multiple Go modules, or downloading the latest A2A schema.
Why use it?
It prevents contributors from treating the repository like a standalone application or guessing how its protocol definitions and examples work. It also provides the standard commands for testing, linting, formatting, and updating dependencies or schemas.

Instructions file

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/inference-gateway/adk/claude-md
Clone the repo
git clone --depth 1 https://github.com/inference-gateway/adk

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inference-gateway/adk/claude-md.svg)](https://agentmods.dev/instructions/inference-gateway/adk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inference-gateway/adk/claude-md"><img src="https://agentmods.dev/badge/instructions/inference-gateway/adk/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,546 This file is loaded in full into every session.
When invoked 2,546 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 $0.02546 $0.02546
Opus 5 $0.01273 $0.01273
Sonnet 5 $0.00509 $0.00509
Haiku 4.5 $0.00255 $0.00255

Measured 4d ago against content hash 415f270fce64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adk CLAUDE.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 4d 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.

CLAUDE.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

The A2A Agent Development Kit (ADK) — a Go library for building servers and clients that speak the Agent-to-Agent (A2A) protocol. Module path: github.com/inference-gateway/adk. It is not a binary — main.go is a placeholder; consumers import the server, client, and types packages. Runnable end-to-end demos live under examples/.

This repo is one of many in the inference-gateway GitHub org polyrepo. The A2A schema is owned by inference-gateway/schemas (see "Schema is upstream" below).

Commands

All commands run from the repo root. Discover the full list with task --list.

Command Purpose
task test Run all tests (go test -v -cover ./...)
task lint golangci-lint run
task format gofmt -w on Go + prettier -w on Markdown
task tidy Walks every go.mod in the tree (root + each examples/*/{server,client}) and runs go mod tidy
task a2a:download-schema Pull the latest A2A schema YAML from inference-gateway/schemas into schema.yaml
task a2a:generate-types Regenerate types/generated_types.go from schema.yaml
task providers:download-schema Pull the canonical openapi.yaml from inference-gateway/schemas into providers-schema.yaml
task generate:providers Regenerate all provider-enumerating artifacts (.env.example, docker-compose.yaml, READMEs) from providers-schema.yaml
task generate Umbrella: runs a2a:generate-types, generate:providers, and generate:mocks
task generate:mocks Regenerate every counterfeiter mock under client/mocks/ and server/mocks/
task generate:mocks:clean Wipe and regenerate all mocks
task lint:examples markdownlint --fix 'examples/**/*.md'
task precommit:install Copy .githooks/pre-commit into .git/hooks/ (recommended)

Read the full file on GitHub · 122 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. 4d ago First seen · 122 lines · 2,546 tokens per session scan A 415f270fce64

Subscribe to this mod's changes

adk CLAUDE.md is an instructions file published in the GitHub repository inference-gateway/adk (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,546 tokens to every session, about $0.0127 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.