What is claude-mcp copilot-instructions.md?

Repository instructions for claude-mcp, a server that connects AI tools with the Claude Code command-line program. They describe its architecture, services, tools, and development rules.

Use them when changing the server setup, Claude process handling, task lifecycle, MCP tools, validation, or related tests.

They help an agent preserve the project’s expected behavior, including synchronous and asynchronous tasks, conversation continuity, cancellation, and test compatibility.

How zhendalf/claude-mcp configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to zhendalf/claude-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zhendalf/claude-mcp/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/zhendalf/claude-mcp

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zhendalf/claude-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/zhendalf/claude-mcp/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/zhendalf/claude-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zhendalf/claude-mcp/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zhendalf/claude-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zhendalf/claude-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,035 This file is loaded in full into every session.

When invoked 1,035 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01035	$0.01035
Opus 5.5	$0.00414	$0.00414
Sonnet 5.5	$0.00207	$0.00207
Haiku 4.5	$0.00103	$0.00103

Measured 2mo ago against content hash f63c6d4ef217, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-mcp 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 2mo 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.

.github/copilot-instructions.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI agent quickstart and rules for this repo

Purpose: This MCP server bridges AI tools to the Claude Code CLI with sync/async execution and conversation continuity via Response IDs. Keep behavior compatible with existing tests and CLI output expectations.

Architecture and responsibilities

Entrypoints: server.js → src/server/setup.js (creates McpServer, registers tools, stdio transport, signal cleanup).
Services:
- src/services/ClaudeService.js: Finds CLI (CLAUDE_CLI_NAME or ~/.claude/local/claude or PATH), builds args, runs sync (--output-format json) and async (--output-format stream-json --verbose), parses JSON; if stdout isn’t JSON, falls back to plain text and extracts Response ID: … from stderr.
- src/services/TaskService.js: Async task lifecycle (pending/running/completed/failed/cancelled), cancellation (kill process group), periodic cleanup, optional MCP notifications, macOS notifications via osascript + afplay, parent-process watchdog to auto-cancel.
Tools (MCP): src/tools/{start,resume,status,cancel}.js, wired via src/tools/index.js. Schemas with zod; handlers close over (claudeService, taskService).
Utils: src/utils/{validation,errors,logger}.js for workingDirectory checks, standardized text responses, and debug logging gated by MCP_CLAUDE_DEBUG.

Developer workflows

Tests (Vitest E2E): npm test. Tests spawn server.js over stdio and assert text content (not JSON RPC payloads directly).
Run server: npm start. Verbose logs: MCP_CLAUDE_DEBUG=true npm start.
One-time setup: run claude --dangerously-skip-permissions once to accept permissions.

Behavioral contracts (must match tests)

Sync response shape (start/resume): return MCP text content that ends with a line Response ID: <uuid>.
- Example: { content: [{ type: "text", text: ${result.result}\n\nResponse ID: ${result.session_id} }] }.
Async start/resume: return Task started successfully. Use status with task ID: <uuid> then track via status.
status output (text) must include: Task , Status, Elapsed, Working Directory, Created/Updated timestamps. If completed, include Result, Response ID, Cost, Duration. If failed, include Error.
resume requires previousResponseId (zod schema enforces). It uses the original conversation’s working directory; don’t allow overriding it on resume.

Read the full file on GitHub · 52 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.

2mo ago First seen · 52 lines · 1,035 tokens per session scan A f63c6d4ef217

Subscribe to this mod's changes

claude-mcp copilot-instructions.md is an instructions file published in the GitHub repository zhendalf/claude-mcp (13 stars, last pushed 1y ago), licensed MIT. It adds 1,035 tokens to every session, about $0.0041 per session on Opus 5.5. 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.

Backend and APIs

claude-mcp copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-mcp copilot-instructions.mdzhendalf/claude-mcp	Instructions file	13	1y ago	MIT	A	1,035	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-mcp: Instructions file for GitHub Copilot