toolhive-cloud-ui AGENTS.md

Project-specific instructions for coding assistants working on ToolHive Cloud UI, a Next.js web application that displays MCP servers in a user's infrastructure. It describes the project's technologies, guidelines, and required documents to read before changing code.

In plain words
What is it for?
Use it when working on the ToolHive Cloud UI repository, especially before editing its TypeScript, React, authentication, API, styling, or testing code.
Why use it?
It gives an assistant the context and rules needed to make changes that fit this particular codebase.

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/stacklok/toolhive-cloud-ui/agents-md
Clone the repo
git clone --depth 1 https://github.com/stacklok/toolhive-cloud-ui

Made for: Codex, OpenCode.

Per session 3,745 This file is loaded in full into every session.
When invoked 3,745 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 $0.03745 $0.03745
Opus 5 $0.01872 $0.01872
Sonnet 5 $0.00749 $0.00749
Haiku 4.5 $0.00375 $0.00375

Measured 2d ago against content hash ef3776839e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolhive-cloud-ui 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 2d 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 · 527 lines

How it starts

The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Guidelines - ToolHive Cloud UI

This document provides essential context for AI coding assistants (Claude, GitHub Copilot, Cursor, etc.) working on this codebase.

Quick Start

IMPORTANT: Before making any code changes, read:

  1. This file (AGENTS.md) - Project overview and key patterns
  2. CLAUDE.md - Detailed guidelines for AI assistants
  3. README.md - Setup and deployment instructions
  4. docs/mocks.md - MSW auto-mocker, fixtures, and dev server

Project Summary

ToolHive Cloud UI is a Next.js 16 application for visualizing MCP (Model Context Protocol) servers in user infrastructure.

Technology Stack

Category Technology
Framework Next.js 16 (App Router)
Language TypeScript (strict mode)
UI Library React 19 + React Compiler
Styling Tailwind CSS 4
Components shadcn/ui
Auth Better Auth (OIDC, stateless)
API Client hey-api + React Query
Testing Vitest + Testing Library
Linting Biome
Package Manager pnpm

Core Principles

  1. Server Components First - Use 'use client' only when necessary
  2. Generated API Client - Never write manual fetch logic, use hey-api functions in server actions
  3. Server Actions for API Calls - Client components fetch data via server actions, not direct API calls
  4. Async/Await Only - No .then() promise chains
  5. 🚫 NEVER USE any - STRICTLY FORBIDDEN. Use unknown with type guards or proper types
  6. Stateless Auth - JWT tokens, no server-side sessions

⚠️ Before Suggesting Code

IMPORTANT: This is a Next.js 16 App Router application. Before suggesting any code:

Read the full file on GitHub · 527 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. 2d ago First seen · 527 lines · 3,745 tokens per session scan A ef3776839e46

Subscribe to this mod's changes

toolhive-cloud-ui AGENTS.md is an instructions file published in the GitHub repository stacklok/toolhive-cloud-ui (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,745 tokens to every session, about $0.0187 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 2026-08-31.