copilot-sdk-v2

$npx mdskill add diegosouzapw/awesome-omni-skills/copilot-sdk-v2

Build applications that programmatically interact with GitHub Copilot using the SDK.

  • Solves the need to integrate GitHub Copilot into custom development workflows.
  • Leverages JSON-RPC to wrap the Copilot CLI and supports Node.js, Python, Go, and .NET.
  • Manages sessions, hooks, and tools while preserving upstream workflow and provenance.
  • Delivers results through streaming, MCP server integration, and custom tool outputs.
SKILL.md
.github/skills/copilot-sdk-v2View on GitHub ↗
---
name: copilot-sdk-v2
description: "GitHub Copilot SDK workflow skill. Use this skill when the user needs 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 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off."
version: "0.0.1"
category: ai-agents
tags: ["copilot-sdk-v2", "copilot-sdk", "build", "applications", "programmatically", "interact", "github", "copilot"]
complexity: advanced
risk: caution
tools: ["codex-cli", "claude-code", "cursor", "gemini-cli", "opencode"]
source: community
author: "sickn33"
date_added: "2026-04-16"
date_updated: "2026-04-25"
---

# GitHub Copilot SDK

## Overview

This public intake copy packages `plugins/antigravity-awesome-skills/skills/copilot-sdk` from `https://github.com/sickn33/antigravity-awesome-skills` into the native Omni Skills editorial shape without hiding its origin.

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses the `external_source` block in `metadata.json` plus `ORIGIN.md` as the provenance anchor for review.

# 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.

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Prerequisites, Core Pattern: Client → Session → Message, Streaming Responses, Custom Tools, Hooks, MCP Server Integration.

## When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

- This skill is applicable to execute the workflow or actions described in the overview.
- Use when the request clearly matches the imported source intent: 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....
- Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.
- Use when provenance needs to stay visible in the answer, PR, or review packet.
- Use when copied upstream references, examples, or scripts materially improve the answer.
- Use when the workflow should remain reviewable in the public intake repo before the private enhancer takes over.

## Operating Table

| Situation | Start here | Why it matters |
| --- | --- | --- |
| First-time use | `metadata.json` | Confirms repository, branch, commit, and imported path through the `external_source` block before touching the copied workflow |
| Provenance review | `ORIGIN.md` | Gives reviewers a plain-language audit trail for the imported source |
| Workflow execution | `SKILL.md` | Starts with the smallest copied file that materially changes execution |
| Supporting context | `SKILL.md` | Adds the next most relevant copied source file without loading the entire package |
| Handoff decision | `## Related Skills` | Helps the operator switch to a stronger native skill when the task drifts |

## Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

1. Language - Package - Install
2. Node.js - @github/copilot-sdk - npm install @github/copilot-sdk
3. Python - github-copilot-sdk - pip install github-copilot-sdk
4. Go - github.com/github/copilot-sdk/go - go get github.com/github/copilot-sdk/go
5. .NET - GitHub.Copilot.SDK - dotnet add package GitHub.Copilot.SDK
6. Confirm the user goal, the scope of the imported workflow, and whether this skill is still the right router for the task.
7. Read the overview and provenance files before loading any copied upstream support files.

### Imported Workflow Notes

#### Imported: Installation

| Language | Package | Install |
|----------|---------|---------|
| Node.js | `@github/copilot-sdk` | `npm install @github/copilot-sdk` |
| Python | `github-copilot-sdk` | `pip install github-copilot-sdk` |
| Go | `github.com/github/copilot-sdk/go` | `go get github.com/github/copilot-sdk/go` |
| .NET | `GitHub.Copilot.SDK` | `dotnet add package GitHub.Copilot.SDK` |

---

#### Imported: 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+

## Examples

### Example 1: Ask for the upstream workflow directly

```text
Use @copilot-sdk-v2 to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.
```

**Explanation:** This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

### Example 2: Ask for a provenance-grounded review

```text
Review @copilot-sdk-v2 against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.
```

**Explanation:** Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

### Example 3: Narrow the copied support files before execution

```text
Use @copilot-sdk-v2 for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.
```

**Explanation:** This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

### Example 4: Build a reviewer packet

```text
Review @copilot-sdk-v2 using the copied upstream files plus provenance, then summarize any gaps before merge.
```

**Explanation:** This is useful when the PR is waiting for human review and you want a repeatable audit packet.



## Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

- Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
- Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
- Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
- Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
- Treat generated examples as scaffolding; adapt them to the concrete task before execution.
- Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.



## Troubleshooting

### Problem: The operator skipped the imported context and answered too generically

**Symptoms:** The result ignores the upstream workflow in `plugins/antigravity-awesome-skills/skills/copilot-sdk`, fails to mention provenance, or does not use any copied source files at all.
**Solution:** Re-open `metadata.json`, `ORIGIN.md`, and the most relevant copied upstream files. Check the `external_source` block first, then restate the provenance before continuing.

### Problem: The imported workflow feels incomplete during review

**Symptoms:** Reviewers can see the generated `SKILL.md`, but they cannot quickly tell which references, examples, or scripts matter for the current task.
**Solution:** Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.

### Problem: The task drifted into a different specialization

**Symptoms:** The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better.
**Solution:** Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.



## Related Skills

- `@00-andruia-consultant` - Use when the work is better handled by that native specialization after this imported skill establishes context.
- `@00-andruia-consultant-v2` - Use when the work is better handled by that native specialization after this imported skill establishes context.
- `@10-andruia-skill-smith` - Use when the work is better handled by that native specialization after this imported skill establishes context.
- `@10-andruia-skill-smith-v2` - Use when the work is better handled by that native specialization after this imported skill establishes context.

## Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

| Resource family | What it gives the reviewer | Example path |
| --- | --- | --- |
| `references` | copied reference notes, guides, or background material from upstream | `references/n/a` |
| `examples` | worked examples or reusable prompts copied from upstream | `examples/n/a` |
| `scripts` | upstream helper scripts that change execution or validation | `scripts/n/a` |
| `agents` | routing or delegation notes that are genuinely part of the imported package | `agents/n/a` |
| `assets` | supporting assets or schemas copied from the source package | `assets/n/a` |



### Imported Reference Notes

#### Imported: References

- [GitHub Copilot SDK](https://github.com/github/copilot-sdk)
- [Copilot CLI Installation](https://docs.github.com/en/copilot/how-tos/set-up/install-copilot-cli)
- [MCP Protocol Specification](https://modelcontextprotocol.io)

#### Imported: 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);
```

---

#### Imported: 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

| Method | Description |
|--------|-------------|
| `on(handler)` | Subscribe to all events; returns unsubscribe function |
| `on(eventType, handler)` | Subscribe to specific event type (Node.js only) |

---

#### Imported: 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],
});
```

---

#### Imported: Hooks

Intercept and customize session behavior at key lifecycle points.

| Hook | Trigger | Use Case |
|------|---------|----------|
| `onPreToolUse` | Before tool executes | Permission control, argument modification |
| `onPostToolUse` | After tool executes | Result transformation, logging |
| `onUserPromptSubmitted` | User sends message | Prompt modification, filtering |
| `onSessionStart` | Session begins | Add context, configure session |
| `onSessionEnd` | Session ends | Cleanup, analytics |
| `onErrorOccurred` | Error happens | Custom 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

| Field | Type | Description |
|-------|------|-------------|
| `permissionDecision` | `"allow"` \| `"deny"` \| `"ask"` | Whether to allow the tool call |
| `permissionDecisionReason` | string | Explanation for deny/ask |
| `modifiedArgs` | object | Modified arguments to pass |
| `additionalContext` | string | Extra context for conversation |
| `suppressOutput` | boolean | Hide tool output from conversation |

---

#### Imported: 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

| Field | Type | Description |
|-------|------|-------------|
| `type` | `"local"` \| `"http"` | Server transport type |
| `command` | string | Executable path (local) |
| `args` | string[] | Command arguments (local) |
| `url` | string | Server URL (http) |
| `tools` | string[] | `["*"]` or specific tool names |
| `env` | object | Environment variables |
| `cwd` | string | Working directory (local) |
| `timeout` | number | Timeout in milliseconds |

---

#### Imported: 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,
    },
});
```

| Provider | Type | Notes |
|----------|------|-------|
| 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.

---

#### Imported: 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,
    },
});
```

---

#### Imported: 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.",
    }],
});
```

---

#### Imported: System Message

Control AI behavior and personality:

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

---

#### Imported: 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"],
});
```

---

#### Imported: 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" };
    },
});
```

---

#### Imported: 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" });
```

---

#### Imported: Client Configuration

| Option | Type | Description |
|--------|------|-------------|
| `cliPath` | string | Path to Copilot CLI executable |
| `cliUrl` | string | URL of external CLI server |
| `githubToken` | string | GitHub token for auth |
| `useLoggedInUser` | boolean | Use stored CLI credentials (default: true) |
| `logLevel` | string | `"none"` \| `"error"` \| `"warning"` \| `"info"` \| `"debug"` |
| `autoRestart` | boolean | Auto-restart CLI on crash (default: true) |
| `useStdio` | boolean | Use stdio transport (default: true) |

#### Imported: Session Configuration

| Option | Type | Description |
|--------|------|-------------|
| `model` | string | Model to use (e.g., `"gpt-4.1"`) |
| `sessionId` | string | Custom ID for resumable sessions |
| `streaming` | boolean | Enable streaming responses |
| `tools` | Tool[] | Custom tools |
| `mcpServers` | object | MCP server configurations |
| `hooks` | object | Session hooks |
| `provider` | object | BYOK provider config |
| `customAgents` | object[] | Custom agent definitions |
| `systemMessage` | object | System message override |
| `skillDirectories` | string[] | Directories to load skills from |
| `disabledSkills` | string[] | Skills to disable |
| `reasoningEffort` | string | Reasoning effort level |
| `availableTools` | string[] | Restrict available tools |
| `excludedTools` | string[] | Exclude specific tools |
| `infiniteSessions` | object | Auto-compaction config |
| `workingDirectory` | string | Working directory |

---

#### Imported: 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`

---

#### Imported: Key API Summary

| Language | Client | Session Create | Send | Stop |
|----------|--------|---------------|------|------|
| Node.js | `new CopilotClient()` | `client.createSession()` | `session.sendAndWait()` | `client.stop()` |
| Python | `CopilotClient()` | `client.create_session()` | `session.send_and_wait()` | `client.stop()` |
| Go | `copilot.NewClient(nil)` | `client.CreateSession()` | `session.SendAndWait()` | `client.Stop()` |
| .NET | `new CopilotClient()` | `client.CreateSessionAsync()` | `session.SendAndWaitAsync()` | `client.DisposeAsync()` |

#### Imported: 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.
More from diegosouzapw/awesome-omni-skills