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/copilot-instructionsgit 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 | $0.02154 | $0.02154 |
| Opus 5 | $0.01077 | $0.01077 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
toolhive-cloud-ui copilot-instructions.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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions - ToolHive Cloud UI
Project Context
This is a Next.js 16 App Router application for visualizing MCP (Model Context Protocol) servers running in user infrastructure. It's an open-source project using TypeScript, React 19, Tailwind CSS 4, and Better Auth for OIDC authentication.
Core Architecture Principles
- Server Components by default - Use Client Components (
'use client') only when needed (event handlers, browser APIs, state hooks) - 🚫 NEVER USE
anyTYPE - STRICTLY FORBIDDEN. Useunknownwith type guards or proper types - Stateless authentication - JWT-based sessions, no server-side storage
- hey-api generated client - Never create manual fetch logic, always use generated hooks
- async/await over promises - No
.then()chains, use async/await for readability
⚠️ Next.js App Router - Validate Before Suggesting
This is Next.js 16 with App Router - Before suggesting code, verify against Next.js Documentation:
Common mistakes to flag:
- ❌ Pages Router patterns (getServerSideProps, getStaticProps, _app.js, _document.js)
- ❌ Custom routing logic (use file-system routing:
page.tsx,layout.tsx) - ❌ Missing
'use client'when using hooks, events, or browser APIs - ❌ Adding
'use client'to Server Components unnecessarily - ❌ Not understanding what Server Components can/cannot do
- ❌ Ignoring Next.js caching (
next: { revalidate, tags })
Key App Router concepts:
- File conventions:
page.tsx(route),layout.tsx(shared UI),loading.tsx(loading state),error.tsx(error boundary) - Server Components (default): No hooks, no events, can fetch data directly with async/await
- Client Components (
'use client'): Use when you need hooks, events, browser APIs - Server Actions (
'use server'): For mutations, better than API routes for simple cases - Caching: Use
revalidatePath(),revalidateTag()for on-demand cache updates
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 · 305 lines · 2,154 tokens per session scan A 4dd9c575f5dc
toolhive-cloud-ui copilot-instructions.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 2,154 tokens to every session, about $0.0108 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.