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-studio/copilot-instructionsgit clone --depth 1 https://github.com/stacklok/toolhive-studioWhat 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 | $0.00976 | $0.00976 |
| Opus 5 | $0.00488 | $0.00488 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
toolhive-studio 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for Copilot
UI components
We will use @ui-kit.ai/components as the UI framework of choice.
An MCP server is provided that explains how to use specific components from @ui-kit.ai/components.
Before writing any UI code ALWAYS consult the MCP server to get a good understanding of how the library works.
Data fetching
Data fetching will be done with @tanstack/react-query & the browser fetch API
All data fetching will be centralized in src/common/hooks, e.g.:
src
+-- common
+-- hooks
+-- useGetMcpServers.ts
+-- useCreateMcpServer.ts
File naming conventions
- We always use kebab-case for all filenames, never camelCase or PascalCase
- We name components with the most generic term left to right, e.g.:
card-mcp-server-details.tsxfor a card component that displays an MCP servertable-mcp-servers.tsxfor a table component that displays a list of MCP serversselect-mcp-servers.tsxfor a select component that allows the user to select an MCP server
Testing
- We use
vitestfor testing - We use
@testing-library/reactfor testing React components - Tests are placed in the same folder as the component they are testing, in a directory called
__tests__, e.g.:
src
+-- common
+-- components
+-- __tests__
+-- component-a.test.tsx
+-- component-b.test.tsx
+-- component-a.ts
+-- component-b.ts
API Mocking
API responses are mocked using MSW with AutoAPIMock fixtures. See docs/mocks.md for full documentation and renderer/src/common/mocks/ for implementation.
- Fixtures are in
renderer/src/common/mocks/fixtures/and use named exports - Override responses in tests with
.override()or.overrideHandler() - Overrides reset automatically before each test
- Use
recordRequests()from@/common/mocks/nodeto assert on API calls
import { mockedGetApiV1BetaGroups } from '@mocks/fixtures/groups/get'
import { recordRequests } from '@/common/mocks/node'
import { HttpResponse } from 'msw'
// Override data (type-safe)
mockedGetApiV1BetaGroups.override(() => ({ groups: [] }))
// Return errors
mockedGetApiV1BetaGroups.overrideHandler(() =>
HttpResponse.json({ error: 'Server error' }, { status: 500 })
)
// Access default data
const defaultData = mockedGetApiV1BetaGroups.defaultValue
// Record and assert on requests
const rec = recordRequests()
// ... actions ...
expect(rec.recordedRequests).toContainEqual(
expect.objectContaining({ method: 'POST', pathname: '/api/v1beta/groups' })
)
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 · 109 lines · 976 tokens per session scan A 9a6f834b9a32
toolhive-studio copilot-instructions.md is an instructions file published in the GitHub repository stacklok/toolhive-studio (163 stars, last pushed 4d ago), licensed Apache-2.0. It adds 976 tokens to every session, about $0.0049 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 2026-08-30.
Other instructions, from other repositories
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
Embody AGENTS.md
Instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
.context copilot-instructions.md
Instructions for forefy/.context: This repo contains instruction files for using and conducting security reviews, do not confuse this copilot-instructions.md from other copilot-instructions files existing in this workspace.
assay CLAUDE.md
Instructions for Rul1an/assay, covering assay - ai agent context, what is assay?, workspace structure, key commands and cli entry points.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
tengu CLAUDE.md
Instructions for rfunix/tengu, covering claude.md — tengu mcp server, project overview, architecture, request flow and module map.