adk AGENTS.md

Project instructions for a Go library that helps developers build Agent-to-Agent (A2A) protocol clients and servers. The repository contains several separate Go modules, including examples.

In plain words
What is it for?
Developing A2A clients and servers, running checks, tidying Go modules, and regenerating types, providers, and mocks.
Why use it?
They explain how to build, test, format, lint, and regenerate the project's generated files.

Instructions file for CodexOpenCode

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

Made for: Codex, OpenCode.

Per session 705 This file is loaded in full into every session.
When invoked 705 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 $0.00705 $0.00705
Opus 5 $0.00352 $0.00352
Sonnet 5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 3d ago against content hash 2e0e3d39d44f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adk 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 3d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inference Gateway A2A ADK

This file is a README for AI coding agents working in this repository. See README.md for user-facing docs; CONTRIBUTING.md has the full contributor workflow.

Project Overview

Go library for building Agent-to-Agent (A2A) protocol agents. Core packages: client/ (A2A client), server/ (server builders, storage, middlewares, telemetry), types/ (protocol types). The root module and every examples/<scenario>/client and examples/<scenario>/server directory are separate Go modules.

Build, Test, and Development Commands

Use Task for common workflows (task lists all tasks):

  • task format — gofmt on Go files, Prettier on Markdown
  • task lintgolangci-lint run
  • task testgo test -v -cover ./...
  • task tidygo mod tidy in every module (root + examples)
  • task a2a:generate-types — regenerate types/generated_types.go from schema.yaml
  • task generate:providers — regenerate provider artifacts from providers-schema.yaml
  • task generate:mocks — regenerate Counterfeiter mocks in client/mocks/ and server/mocks/
  • task generate — regenerate types, providers, and mocks; go build . verifies the root package

Install the optional pre-commit hook with task precommit:install.

Generated Files

types/generated_types.go, client/mocks/*.go, and server/mocks/*.go are generated. Never edit them by hand: change the source (schema.yaml, providers-schema.yaml, or the interface) and rerun the matching task target.

Code Style

Tabs for Go, LF endings, final newlines, 120-column guideline (.editorconfig). No inline comments inside function bodies; docblocks sit above exported symbols, at most 3 lines, no issue links. Prefer early returns, interface-driven dependencies, table-driven tests, and structured logging with lowercase messages.

All non-standard-library imports MUST use explicit named imports (aliases), grouped in this order with a blank line between groups: (1) stdlib, (2) external testing libraries, (3) external libraries, (4) internal testing libraries, (5) internal libraries.

Read the full file on GitHub · 45 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. 3d ago First seen · 45 lines · 705 tokens per session scan A 2e0e3d39d44f

Subscribe to this mod's changes

adk AGENTS.md is an instructions file published in the GitHub repository inference-gateway/adk (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 705 tokens to every session, about $0.0035 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.