What is kaiden AGENTS.md?

A set of instructions for working on Kaiden, an Electron desktop application for managing containers and Kubernetes through an AI-assisted interface. It explains the application's processes, plugin system, and dependency setup.

Use it when changing Kaiden's Electron processes, Svelte interface, container or Kubernetes features, AI provider integrations, or plugin architecture.

It helps coding agents understand where desktop logic, the user interface, secure communication, and extensions belong in a multi-process application.

How openkaiden/kaiden configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to openkaiden/kaiden. 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/openkaiden/kaiden/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/openkaiden/kaiden

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/openkaiden/kaiden/agents-md/github.svg)](https://agentmods.dev/instructions/openkaiden/kaiden/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/openkaiden/kaiden/agents-md"><img src="https://agentmods.dev/badge/instructions/openkaiden/kaiden/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/openkaiden/kaiden/agents-md"><img src="https://agentmods.dev/badge/instructions/openkaiden/kaiden/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,725 This file is loaded in full into every session.

When invoked 3,725 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.03725	$0.03725
Opus 5.5	$0.01490	$0.01490
Sonnet 5.5	$0.00745	$0.00745
Haiku 4.5	$0.00373	$0.00373

Measured 1mo ago against content hash 5890094eec7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kaiden AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- No synchronous APIs (`execSync`, `fs.*Sync`) in async code; no `void promise`; `async/await` over `.then` chains

AGENTS.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI code assistants when working with code in this repository.

Project Overview

Kaiden is an Electron-based desktop application built with Svelte that provides AI-powered container and Kubernetes management capabilities. It integrates with multiple AI providers (Gemini, OpenAI-compatible services, OpenShift AI). The application also implements the Model Context Protocol (MCP) for AI agent integration.

Core Architecture

Multi-Process Electron Application

Kaiden follows the standard Electron architecture with three main processes:

Main Process (packages/main): Node.js backend handling system integration, extension loading, container/Kubernetes operations, and business logic
Renderer Process (packages/renderer): Svelte-based UI running in the browser context
Preload Scripts (packages/preload and packages/preload-webview): Bridge layer for secure IPC communication between main and renderer

Plugin System and Dependency Injection

The core plugin system is implemented in packages/main/src/plugin/index.ts using Inversify for dependency injection. Key components include:

PluginSystem class: Orchestrates extension loading, configuration registry, and all core services
Extension Loader (ExtensionLoader): Manages extension lifecycle (loading, starting, stopping, uninstalling)
Container: Inversify DI container binding all major registries and managers as singletons

All major services are registered as singletons in the DI container during initialization:

ProviderRegistry: Manages inference, container, and Kubernetes providers
ContainerProviderRegistry: Handles Docker/Podman container operations
KubernetesClient: Kubernetes cluster management
MCPManager and MCPRegistry: Model Context Protocol integration
ConfigurationRegistry: Settings and configuration management

Extensions

Extensions are located in the extensions/ directory and follow a standard structure:

Read the full file on GitHub · 343 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.

1mo ago Changed · +54 lines · +1,192 tokens per session 5890094eec7c
1mo ago Changed · -13 lines · -113 tokens per session 0bce7f388f6b
1mo ago Changed · +2 lines · +45 tokens per session 37c7be348aeb
1mo ago Changed · -4 lines · -53 tokens per session 57ad4f406cc0
1mo ago Changed · +12 lines · +140 tokens per session 735a00177293
2mo ago First seen · 292 lines · 2,514 tokens per session scan A 6dc20faaf6a8

Subscribe to this mod's changes

kaiden AGENTS.md is an instructions file published in the GitHub repository openkaiden/kaiden (117 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,725 tokens to every session, about $0.0149 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

kaiden AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kaiden AGENTS.mdopenkaiden/kaiden	Instructions file	117	yesterday	Apache-2.0	A	3,725	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

kaiden: Instructions file for Codex