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/ilyaev/mcp-chat-ui/copilot-instructionsgit clone --depth 1 https://github.com/ilyaev/mcp-chat-uiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/ilyaev/mcp-chat-ui/copilot-instructions)<a href="https://agentmods.dev/instructions/ilyaev/mcp-chat-ui/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ilyaev/mcp-chat-ui/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01131 | $0.01131 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
mcp-chat-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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for MCP Chat UI
Project Overview
This is a multi-component TypeScript/React project for a chat UI that integrates with agents and tools via WebSocket. The architecture is split between a client-side React app (in client/) and server-side logic (in src/server/). Redux is used for state management, and Vite is the build tool.
Key Components & Data Flow
- Client App (
client/src/): Main React UI, organized by feature (chat, chart, common, ui).- Chat: Managed by Redux slice (
store/slices/chatSessionSlice.ts). Handles chat items, agent/tool responses, and session state. - WebSocket Integration:
lib/ws_client.tsmanages connection, message dispatch, and tool/agent result handling. Tool calls and chart data are handled as special message types. - UI Patterns: Uses Radix UI, TailwindCSS, and custom components in
components/ui/.
- Chat: Managed by Redux slice (
- Server (
src/server/): Handles WebSocket connections, authentication, and agent/tool orchestration. - Agents & Tools: Defined in
src/agents/andsrc/tools/. Agents process chat prompts; tools (e.g., chart generator) respond to tool calls.
Developer Workflows
- Build:
npm run build(runs TypeScript build and Vite build) - Dev Server:
npm run dev(starts Vite dev server) - Lint:
npm run lint(ESLint) - Preview:
npm run preview(Vite preview) - Hot Reload: Supported via Vite and React Fast Refresh
- Redux State: Use slices in
store/slices/and actions for chat/agent/tool state updates
Conventions & Patterns
- Path Aliases: Use
@/forclient/src/imports (seetsconfig.jsonandvite.config.ts) - Chat/Tool/Chart Handling: Chat items and tool/chart responses are managed as objects in Redux state. Tool calls and chart data are handled as special message types in WebSocket client and Redux slice.
- Error Handling: WebSocket errors are appended to chat responses and update state.
- Session Management: Each WebSocket client has a unique session ID; session state is managed in Redux.
- UI Composition: Use Radix UI and custom components for consistent design. See
components/ui/for reusable UI elements.
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.
- 4d ago First seen · 96 lines · 1,131 tokens per session scan A ca5aeccffb80
mcp-chat-ui copilot-instructions.md is an instructions file published in the GitHub repository ilyaev/mcp-chat-ui (10 stars, last pushed 1y ago), licensed MIT. It adds 1,131 tokens to every session, about $0.0057 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
recharts AGENTS.md
AGENTS.md instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.
ui-components AGENTS.md
AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
react-svg AGENTS.md
AGENTS.md instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.
Paperlab AGENTS.md
AGENTS.md instructions for NourMtir0722/Paperlab, covering paperlab — for coding agents, integrating paperlab into a project, stage mode — paper as architecture, content types and lighting is data, not an enum.