Copilot Sdk logo

Copilot Sdk

Organization
skillmds
copilot-sdk

Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Overview

Publisherskillmds
Repositoryskillmd
Skill namecopilot-sdk
Stars
249
Forks
3
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by skillmds on GitHub. Read the source before you install it.

Installation

Install the Copilot Sdk AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/skillmds/skillmd/tree/main/plugins/agents-mcp/skills/copilot-sdk
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/skillmds/skillmd.git /tmp/skillmd
mkdir -p .claude/skills
cp -r /tmp/skillmd/plugins/agents-mcp/skills/copilot-sdk .claude/skills/copilot-sdk
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Copilot Sdk in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Copilot Sdk on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Copilot Sdk is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GitHub Copilot SDK

Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Prerequisites

  • GitHub Copilot CLI installed and authenticated (copilot --version to verify)
  • GitHub Copilot subscription (Individual, Business, or Enterprise) — not required for BYOK
  • Runtime: Node.js 18+ / Python 3.8+ / Go 1.21+ / .NET 8.0+

Installation

LanguagePackageInstall
Node.js@github/copilot-sdknpm install @github/copilot-sdk
Pythongithub-copilot-sdkpip install github-copilot-sdk
Gogithub.com/github/copilot-sdk/gogo get github.com/github/copilot-sdk/go
.NETGitHub.Copilot.SDKdotnet add package GitHub.Copilot.SDK

Core Pattern: Client → Session → Message

All SDK usage follows this pattern: create a client, create a session, send messages.

Node.js / TypeScript

typescript
import { CopilotClient } from "@github/copilot-sdk";

const client = new CopilotClient();
const session = await client.createSession({ model: "gpt-4.1" });

const response = await session.sendAndWait({ prompt: "What is 2 + 2?" });
console.log(response?.data.content);

await client.stop();

Python

python
import asyncio
from copilot import CopilotClient

async def main():
    client = CopilotClient()
    await client.start()
    session = await client.create_session({"model": "gpt-4.1"})
    response = await session.send_and_wait({"prompt": "What is 2 + 2?"})
    print(response.data.content)
    await client.stop()

asyncio.run(main())

Go

go
client := copilot.NewClient(nil)
if err := client.Start(ctx); err != nil { log.Fatal(err) }
defer client.Stop()

session, _ := client.CreateSession(ctx, &copilot.SessionConfig{Model: "gpt-4.1"})
response, _ := session.SendAndWait(ctx, copilot.MessageOptions{Prompt: "What is 2 + 2?"})
fmt.Println(*response.Data.Content)

.NET

csharp
await using var client = new CopilotClient();
await using var session = await client.CreateSessionAsync(new SessionConfig { Model = "gpt-4.1" });
var response = await session.SendAndWaitAsync(new MessageOptions { Prompt = "What is 2 + 2?" });
Console.WriteLine(response?.Data.Content);

Streaming Responses

Enable real-time output by setting streaming: true and subscribing to delta events.

typescript
const session = await client.createSession({ model: "gpt-4.1", streaming: true });

session.on("assistant.message_delta", (event) => {
    process.stdout.write(event.data.deltaContent);
});
session.on("session.idle", () => console.log());

await session.sendAndWait({ prompt: "Tell me a joke" });

Python equivalent:

python
from copilot.generated.session_events import SessionEventType

session = await client.create_session({"model": "gpt-4.1", "streaming": True})

def handle_event(event):
    if event.type == SessionEventType.ASSISTANT_MESSAGE_DELTA:
        sys.stdout.write(event.data.delta_content)
        sys.stdout.flush()

session.on(handle_event)
await session.send_and_wait({"prompt": "Tell me a joke"})

Event Subscription

MethodDescription
on(handler)Subscribe to all events; returns unsubscribe function
on(eventType, handler)Subscribe to specific event type (Node.js only)

Custom Tools

Define tools that Copilot can call to extend its capabilities.

Node.js

typescript
import { CopilotClient, defineTool } from "@github/copilot-sdk";

const getWeather = defineTool("get_weather", {
    description: "Get the current weather for a city",
    parameters: {
        type: "object",
        properties: { city: { type: "string", description: "The city name" } },
        required: ["city"],
    },
    handler: async ({ city }) => ({ city, temperature: "72°F", condition: "sunny" }),
});

const session = await client.createSession({
    model: "gpt-4.1",
    tools: [getWeather],
});

Python

python
from copilot.tools import define_tool
from pydantic import BaseModel, Field

class GetWeatherParams(BaseModel):
    city: str = Field(description="The city name")

@define_tool(description="Get the current weather for a city")
async def get_weather(params: GetWeatherParams) -> dict:
    return {"city": params.city, "temperature": "72°F", "condition": "sunny"}

session = await client.create_session({"model": "gpt-4.1", "tools": [get_weather]})

Go

go
type WeatherParams struct {
    City string `json:"city" jsonschema:"The city name"`
}

getWeather := copilot.DefineTool("get_weather", "Get weather for a city",
    func(params WeatherParams, inv copilot.ToolInvocation) (WeatherResult, error) {
        return WeatherResult{City: params.City, Temperature: "72°F"}, nil
    },
)

session, _ := client.CreateSession(ctx, &copilot.SessionConfig{
    Model: "gpt-4.1",
    Tools: []copilot.Tool{getWeather},
})

.NET

csharp
var getWeather = AIFunctionFactory.Create(
    ([Description("The city name")] string city) => new { city, temperature = "72°F" },
    "get_weather", "Get the current weather for a city");

await using var session = await client.CreateSessionAsync(new SessionConfig {
    Model = "gpt-4.1", Tools = [getWeather],
});

Hooks

Intercept and customize session behavior at key lifecycle points.

HookTriggerUse Case
onPreToolUseBefore tool executesPermission control, argument modification
onPostToolUseAfter tool executesResult transformation, logging
onUserPromptSubmittedUser sends messagePrompt modification, filtering
onSessionStartSession beginsAdd context, configure session
onSessionEndSession endsCleanup, analytics
onErrorOccurredError happensCustom error handling, retry logic

Example: Tool Permission Control

typescript
const session = await client.createSession({
    hooks: {
        onPreToolUse: async (input) => {
            if (["shell", "bash"].includes(input.toolName)) {
                return { permissionDecision: "deny", permissionDecisionReason: "Shell access not permitted" };
            }
            return { permissionDecision: "allow" };
        },
    },
});

Pre-Tool Use Output

FieldTypeDescription
permissionDecision"allow" | "deny" | "ask"Whether to allow the tool call
permissionDecisionReasonstringExplanation for deny/ask
modifiedArgsobjectModified arguments to pass
additionalContextstringExtra context for conversation
suppressOutputbooleanHide tool output from conversation

MCP Server Integration

Connect to MCP servers for pre-built tool capabilities.

Remote HTTP Server

typescript
const session = await client.createSession({
    mcpServers: {
        github: { type: "http", url: "https://api.githubcopilot.com/mcp/" },
    },
});

Local Stdio Server

typescript
const session = await client.createSession({
    mcpServers: {
        filesystem: {
            type: "local",
            command: "npx",
            args: ["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"],
            tools: ["*"],
        },
    },
});

MCP Config Fields

FieldTypeDescription
type"local" | "http"Server transport type
commandstringExecutable path (local)
argsstring[]Command arguments (local)
urlstringServer URL (http)
toolsstring[]["*"] or specific tool names
envobjectEnvironment variables
cwdstringWorking directory (local)
timeoutnumberTimeout in milliseconds

Authentication

Methods (Priority Order)

  1. Explicit token — githubToken in constructor
  2. Environment variables — COPILOT_GITHUB_TOKEN → GH_TOKEN → GITHUB_TOKEN
  3. Stored OAuth — From copilot auth login
  4. GitHub CLI — gh auth credentials

Programmatic Token

typescript
const client = new CopilotClient({ githubToken: process.env.GITHUB_TOKEN });

BYOK (Bring Your Own Key)

Use your own API keys — no Copilot subscription required.

typescript
const session = await client.createSession({
    model: "gpt-5.2-codex",
    provider: {
        type: "openai",
        baseUrl: "https://your-resource.openai.azure.com/openai/v1/",
        wireApi: "responses",
        apiKey: process.env.FOUNDRY_API_KEY,
    },
});
ProviderTypeNotes
OpenAI"openai"OpenAI API and compatible endpoints
Azure OpenAI"azure"Native Azure endpoints (don't include /openai/v1)
Azure AI Foundry"openai"OpenAI-compatible Foundry endpoints
Anthropic"anthropic"Claude models
Ollama"openai"Local models, no API key needed

Wire API: Use "responses" for GPT-5 series, "completions" (default) for others.


Session Persistence

Resume sessions across restarts by providing your own session ID.

typescript
// Create with explicit ID
const session = await client.createSession({
    sessionId: "user-123-task-456",
    model: "gpt-4.1",
});

// Resume later
const resumed = await client.resumeSession("user-123-task-456");
await resumed.sendAndWait({ prompt: "What did we discuss?" });

Session management:

typescript
const sessions = await client.listSessions();          // List all
await client.deleteSession("user-123-task-456");       // Delete
await session.destroy();                                // Destroy active

BYOK sessions: Must re-provide provider config on resume (keys are not persisted).

Infinite Sessions

For long-running workflows that may exceed context limits:

typescript
const session = await client.createSession({
    infiniteSessions: {
        enabled: true,
        backgroundCompactionThreshold: 0.80,
        bufferExhaustionThreshold: 0.95,
    },
});

Custom Agents

Define specialized AI personas:

typescript
const session = await client.createSession({
    customAgents: [{
        name: "pr-reviewer",
        displayName: "PR Reviewer",
        description: "Reviews pull requests for best practices",
        prompt: "You are an expert code reviewer. Focus on security, performance, and maintainability.",
    }],
});

System Message

Control AI behavior and personality:

typescript
const session = await client.createSession({
    systemMessage: { content: "You are a helpful assistant. Always be concise." },
});

Skills Integration

Load skill directories to extend Copilot's capabilities:

typescript
const session = await client.createSession({
    skillDirectories: ["./skills/code-review", "./skills/documentation"],
    disabledSkills: ["experimental-feature"],
});

Permission & Input Handlers

Handle tool permissions and user input requests programmatically:

typescript
const session = await client.createSession({
    onPermissionRequest: async (request) => {
        // Auto-approve git commands only
        if (request.kind === "shell") {
            return { approved: request.command.startsWith("git") };
        }
        return { approved: true };
    },
    onUserInputRequest: async (request) => {
        // Handle ask_user tool calls
        return { response: "yes" };
    },
});

External CLI Server

Connect to a separately running CLI instead of auto-managing the process:

bash
copilot --headless --port 4321
typescript
const client = new CopilotClient({ cliUrl: "localhost:4321" });

Client Configuration

OptionTypeDescription
cliPathstringPath to Copilot CLI executable
cliUrlstringURL of external CLI server
githubTokenstringGitHub token for auth
useLoggedInUserbooleanUse stored CLI credentials (default: true)
logLevelstring"none" | "error" | "warning" | "info" | "debug"
autoRestartbooleanAuto-restart CLI on crash (default: true)
useStdiobooleanUse stdio transport (default: true)

Session Configuration

OptionTypeDescription
modelstringModel to use (e.g., "gpt-4.1")
sessionIdstringCustom ID for resumable sessions
streamingbooleanEnable streaming responses
toolsTool[]Custom tools
mcpServersobjectMCP server configurations
hooksobjectSession hooks
providerobjectBYOK provider config
customAgentsobject[]Custom agent definitions
systemMessageobjectSystem message override
skillDirectoriesstring[]Directories to load skills from
disabledSkillsstring[]Skills to disable
reasoningEffortstringReasoning effort level
availableToolsstring[]Restrict available tools
excludedToolsstring[]Exclude specific tools
infiniteSessionsobjectAuto-compaction config
workingDirectorystringWorking directory

Debugging

Enable debug logging to troubleshoot issues:

typescript
const client = new CopilotClient({ logLevel: "debug" });

Common issues:

  • CLI not found → Install CLI or set cliPath
  • Not authenticated → Run copilot auth login or provide githubToken
  • Session not found → Don't use session after destroy()
  • Connection refused → Check CLI process, enable autoRestart

Key API Summary

LanguageClientSession CreateSendStop
Node.jsnew CopilotClient()client.createSession()session.sendAndWait()client.stop()
PythonCopilotClient()client.create_session()session.send_and_wait()client.stop()
Gocopilot.NewClient(nil)client.CreateSession()session.SendAndWait()client.Stop()
.NETnew CopilotClient()client.CreateSessionAsync()session.SendAndWaitAsync()client.DisposeAsync()

References

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Frequently asked questions

What does the Copilot Sdk AI skill do?

Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Why use Copilot Sdk on TypingMind?

Because you install it once and use it with any model. Copilot Sdk is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Copilot Sdk in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/skillmds/skillmd/tree/main/plugins/agents-mcp/skills/copilot-sdk. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Copilot Sdk?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Copilot Sdk?

As many as you like. As long as a model supports skills, you can use Copilot Sdk with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Copilot Sdk AI skill free?

Yes. It is published on GitHub by skillmds under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇