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 skills/shyamsridhar123/agentsmith-cli/copilot-sdknpx skills add shyamsridhar123/agentsmith-cli --skill copilot-sdkgit clone --depth 1 https://github.com/shyamsridhar123/agentsmith-cliWrote 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/skills/shyamsridhar123/agentsmith-cli/copilot-sdk)<a href="https://agentmods.dev/skills/shyamsridhar123/agentsmith-cli/copilot-sdk"><img src="https://agentmods.dev/badge/skills/shyamsridhar123/agentsmith-cli/copilot-sdk.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 | $0.00078 | $0.02117 |
| Opus 5 | $0.00039 | $0.01059 |
| Sonnet 5 | $0.00016 | $0.00423 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
copilot-sdk 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 5d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot SDK
Build AI-powered applications that leverage Copilot's agentic workflows. The SDK exposes the same engine behind Copilot CLI—a production-tested agent runtime you can invoke programmatically.
Status: Technical Preview
When to Use This Skill
- Creating applications that need programmatic access to GitHub Copilot
- Building custom AI agents with tool integration
- Developing CLI tools or backends powered by Copilot
- Integrating Copilot capabilities into existing applications
Prerequisites
- GitHub Copilot Subscription - Required for SDK usage
- Copilot CLI - Must be installed and in PATH (installation guide)
Installation
| Language | Package | Command |
|---|---|---|
| TypeScript/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 |
Architecture
Your Application → SDK Client → JSON-RPC → Copilot CLI (server mode)
Quick Start Examples
TypeScript
import { CopilotClient } from "@github/copilot-sdk";
const client = new CopilotClient();
await client.start();
const session = await client.createSession({ model: "gpt-5" });
session.on((event) => {
if (event.type === "assistant.message") {
console.log(event.data.content);
} else if (event.type === "session.idle") {
// Session finished processing
}
});
await session.send({ prompt: "What is 2+2?" });
await session.destroy();
await client.stop();
Python
from copilot import CopilotClient
client = CopilotClient()
await client.start()
session = await client.create_session({"model": "gpt-5"})
def on_event(event):
if event["type"] == "assistant.message":
print(event["data"]["content"])
session.on(on_event)
await session.send({"prompt": "What is 2+2?"})
await session.destroy()
await client.stop()
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.
- 5d ago First seen · 343 lines · 78 tokens per session scan A 318b5e09fe88
copilot-sdk is a skill published in the GitHub repository shyamsridhar123/agentsmith-cli (16 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 2,117 once invoked, about $0.0004 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 skills, from other repositories
oda-copilot-customization
Apply, review, improve, or maintain a repository's Copilot customization with the Ownership-Driven AI Customization Architecture and the latest official GitHub Copilot docs. Use when shaping or auditing a repository's customization map, governance files, supporting docs, and safeguards for drift, health, weak…
oda-task-tracking
Operate ODA GitHub Issues and the ODA Board consistently. Use when creating, updating, listing, moving, or reclassifying tracked work in GitHub for this repository.
impact-review
Assess likely downstream impact, decide what should be reconciled now versus carried forward explicitly, and keep the repository coherent without sweeping every related surface.
debug-behavior
Investigate inconsistent or incorrect behavior with a structured workflow.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…