Tools

AI configuration generators and developer utilities for autonomous agents.

Standardise design tokens, multi-agent instructions, tool connections, and site discovery for modern AI coding workflows.

Start with a conversation

Talk to us

Use Halden AI as a sales assistant to explore services, understand offerings, and choose the right next step before booking a meeting.

Book a Meeting

AI Generators

Developer & Agent Configuration Tools

Open-standard interactive config generators built by Halden Solutions to help engineering teams streamline AI agent workflows, standardize design tokens, and connect enterprise tools.

Output: DESIGN.mdDesign Systems & AI Rules

DESIGN.md Generator

Build a tokenized design system specification that AI coding agents can read, understand, and apply consistently across your codebase.

Design TokensDesign SystemsAI Coding RulesTailwind CSSCSS Variables

Key Capabilities

Interactive semantic color tokens editor with auto-palette generation
Typography, spacing scales, and corner radius token management
UI component token mapping for buttons, cards, inputs, and badges

Open & Generate DESIGN.md

Output: AGENTS.mdAgent Orchestration & Context

AGENTS.md Generator

Generate a universal AGENTS.md configuration file that provides unified repo context, guidelines, and execution boundaries to any AI coding agent.

Agent OrchestrationMulti-Agent SystemsCoding StandardsAI WorkflowsDeveloper Tooling

Key Capabilities

Pre-configured smart presets for Next.js, Vite, Vue, SvelteKit, Astro, Node API, and Python
Configurable setup & script commands (install, dev, build, lint, test, typecheck)
Granular code style rules (TypeScript, ESLint, Prettier, Tailwind, component architecture)

Open & Generate AGENTS.md

Output: mcp.jsonTool Calling & Agent Protocols

MCP Config Generator

Create Model Context Protocol (MCP) server configuration files to securely connect AI coding assistants to external tools, databases, APIs, and cloud resources.

Model Context ProtocolTool CallingAgent InfrastructureAPI IntegrationsCursorClaude Desktop

Key Capabilities

Multi-client support: Cursor (.cursor/mcp.json), Claude Desktop, VS Code (.vscode/mcp.json), Windsurf, and Generic
Target scope switching between project-specific and global configurations
Curated catalog of top MCP servers (Filesystem, GitHub, Postgres, Supabase, Slack, Linear, Sentry, Brave Search, Puppeteer, Memory)

Open & Generate mcp.json

Output: llms.txtAI SEO & Discoverability

llms.txt Generator

Create structured llms.txt and llms-full.txt files to guide AI search engines, LLMs, and agent web crawlers to your highest-value documentation.

AI SEOLLM OptimizationDocumentation IndexingWeb Standardsllmstxt.org

Key Capabilities

Visual section manager for organizing documentation, guides, APIs, and examples
Quick sitemap.xml parser that extracts and classifies URLs in your browser
Dual export: curated llms.txt manifest and concatenated llms-full.txt structure

Open & Generate llms.txt

Architecture

Why Standardise AI Agent Configs?

Modern engineering teams are shifting from ad-hoc prompting to declarative, repository-grounded agent architecture.

Deterministic Rules

Provide AI models with explicit design tokens and constraints in DESIGN.md to eliminate visual drift and UI hallucinations.

Multi-Agent Context

Use AGENTS.md to provide a single, universal source of project truth across Claude Code, Cursor, Copilot, and custom agents.

Safe Tool Access

Connect agents to private databases, APIs, and CLI tooling using standardized mcp.json specifications with least-privilege access.

AI Search Discovery

Publish llms.txt to guide LLMs and AI crawlers directly to your structured documentation, cutting token overhead.