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.
npx agentmods add instructions/stacklok/toolhive-cloud-ui/claude-mdgit clone --depth 1 https://github.com/stacklok/toolhive-cloud-uiWhat 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 | $0.03539 | $0.03539 |
| Opus 5 | $0.01769 | $0.01769 |
| Sonnet 5 | $0.00708 | $0.00708 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade A, and why
toolhive-cloud-ui 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 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.
How it starts
The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude AI Assistant Guide - ToolHive Cloud UI
This document provides context and guidelines for Claude (and other AI assistants) working on the ToolHive Cloud UI codebase.
Project Overview
ToolHive Cloud UI is an open-source Next.js 16 application for visualizing and managing MCP (Model Context Protocol) servers running in user infrastructure. It provides a catalog interface with detailed server information, tool listings, and URL copy functionality.
Repository: https://github.com/stacklok/toolhive-cloud-ui
Backend API: https://github.com/stacklok/toolhive-registry-server
License: Apache 2.0 (Open Source)
Core Technology Stack
- Framework: Next.js 16.0.3 (App Router)
- React: 19.2.0 with React Compiler (babel-plugin-react-compiler)
- TypeScript: Strict mode enabled
- Styling: Tailwind CSS 4
- UI Components: shadcn/ui
- Authentication: Better Auth (OIDC, stateless JWT)
- API Client: hey-api (@hey-api/openapi-ts) with React Query
- Testing: Vitest + Testing Library
- Linting: Biome (replaces ESLint + Prettier)
- Package Manager: pnpm
⚠️ Critical: Validate Against Next.js Documentation
Before suggesting any code or architecture changes:
- Consult Next.js Documentation - Verify your approach is correct
- This is App Router, not Pages Router - Different conventions and patterns
- Validate Server vs Client boundaries - Understand what runs where
- Check built-in features - Next.js provides routing, caching, data fetching, etc.
- Don't reinvent the wheel - Use Next.js conventions and built-ins
Common mistakes AI assistants make with Next.js:
- ❌ Mixing Pages Router and App Router patterns
- ❌ Creating custom routing when file-system routing exists
- ❌ Not understanding Server Components (no hooks, no event handlers)
- ❌ Adding
'use client'everywhere or forgetting it when needed - ❌ Ignoring Next.js caching and revalidation mechanisms
- ❌ Using old data fetching patterns (getServerSideProps, getStaticProps)
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.
- 2d ago First seen · 368 lines · 3,539 tokens per session scan A 1b673e56d432
toolhive-cloud-ui CLAUDE.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 3,539 tokens to every session, about $0.0177 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.
Other instructions, from other repositories
mcpscore AGENTS.md
Instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).
pixabay-mcp-server CLAUDE.md
Claude Code instructions for hanoak/pixabay-mcp-server, covering claude.md, project overview, tech stack (decided — do not relitigate without discussion), architecture & folder conventions and coding standards.
mTarsier AGENTS.md
Instructions for mcp360/mTarsier, covering mtarsier — agent guide, project overview, key paths, architecture and frontend conventions.
mTarsier CLAUDE.md
Instructions for mcp360/mTarsier, covering mtarsier — claude code instructions and quick rules.
xc-mcp CLAUDE.md
Claude Code instructions for conorluddy/xc-mcp, covering claude.md, project overview, architecture (v4.0.0), v4.0 migration guide (breaking) and development commands.
mcpscore CLAUDE.md
Instructions for mcp-box/mcpscore, a project described as: Lighthouse for MCP — score any MCP server 0–100.