copilot-cli

Integration instructions for connecting GitHub Copilot CLI, a command-line AI coding agent, to another program through the Agent Client Protocol.

In plain words
What is it for?
Use it to start Copilot CLI in standard input/output or network mode and handle its JSON-RPC messages, notifications, file paths, and line numbers.
Why use it?
It explains how two developer tools exchange requests and responses so an editor or controller can use Copilot CLI.

Agent

Install

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.

agentmods
npx agentmods add agents/marcinbunsch/overseer/copilot-cli
Clone the repo
git clone --depth 1 https://github.com/marcinbunsch/overseer
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02576
Opus 5 $0.00000 $0.01288
Sonnet 5 $0.00000 $0.00515
Haiku 4.5 $0.00000 $0.00258

Measured 2d ago against content hash 0e689ef78494, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-cli 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 2d 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.

docs/agents/copilot-cli.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot CLI Integration

This document describes the Agent Client Protocol (ACP) used by GitHub Copilot CLI and how to integrate it with Overseer.

Overview

GitHub Copilot CLI is a command-line AI coding agent that can be integrated into Overseer using the Agent Client Protocol (ACP) - an open standard for agent-editor communication. ACP uses JSON-RPC 2.0 over stdio, similar to how Codex is already integrated.

References:

Starting Copilot in ACP Mode

# stdio mode (recommended for IDE integration)
copilot --acp --stdio

# TCP mode (for remote/network access)
copilot --acp --port 3000

Protocol Basics

  • Transport: JSON-RPC 2.0 over stdio (NDJSON - newline-delimited JSON)
  • Encoding: UTF-8
  • Message types:
    • Methods: Request-response pairs (have id)
    • Notifications: One-way messages (no id)
  • File paths: Must be absolute
  • Line numbers: 1-based indexing

Message Flow

Client (Overseer)                    Agent (copilot --acp --stdio)
  |                                      |
  |-- initialize ----------------------->|
  |<-- result (capabilities) ------------|
  |                                      |
  |-- session/new ---------------------->|
  |<-- result (sessionId) ---------------|
  |                                      |
  |-- session/prompt ------------------->|
  |<-- session/update (streaming) -------|  (notifications)
  |<-- session/request_permission -------|  (approval request)
  |-- result (selected option) --------->|
  |<-- session/update (tool updates) ----|
  |<-- result (stopReason) --------------|

Initialization

Request: initialize

{
  "jsonrpc": "2.0",
  "method": "initialize",
  "id": 1,
  "params": {
    "protocolVersion": 1,
    "clientInfo": {
      "name": "overseer",
      "title": "Overseer",
      "version": "1.0.0"
    },
    "clientCapabilities": {
      "fs": {
        "readTextFile": true,
        "writeTextFile": true
      },
      "terminal": true
    }
  }
}

Read the full file on GitHub · 422 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.

  1. 2d ago First seen · 422 lines · 0 tokens per session scan A 0e689ef78494

Subscribe to this mod's changes

copilot-cli is an agent published in the GitHub repository marcinbunsch/overseer (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,576 tokens. 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens