A setup tool for using GitHub Copilot in a project. It adds workspace guidance and connects Copilot to the project's MCP server, a way for tools to share information with the assistant.

Use it to configure Copilot in VS Code, JetBrains IDEs, or the terminal for a Marko project. It creates Copilot instructions, MCP registration, and shared agent guidelines.

It saves you from configuring these project files by hand and keeps Marko's guidance available to Copilot Chat. Your own edits outside the managed section remain when setup runs again.

copilot — Agent by marko-php

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/marko-php/marko/copilot

Clone the repo

git clone --depth 1 https://github.com/marko-php/marko

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 762 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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.00762
Opus 5	$0.00010	$0.00381
Sonnet 5	$0.00004	$0.00152
Haiku 4.5	$0.00002	$0.00076

Measured 2d ago against content hash 7fa85eade309, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot 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.

packages/docs-markdown/docs/ai-assisted-development/agents/copilot.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot is available in VS Code, JetBrains IDEs, and the terminal via the gh copilot extension. devai:install configures it with workspace instructions and MCP server registration.

Prerequisites

GitHub Copilot subscription active on your GitHub account
VS Code with the GitHub Copilot extension, or a JetBrains IDE with the Copilot plugin
marko/devai installed (see Installation)

What devai:install writes

Running marko devai:install with Copilot detected produces the following files:

.github/copilot-instructions.md    # Workspace-level guidelines for Copilot Chat
.vscode/mcp.json                   # MCP server registration (marko mcp:serve)
AGENTS.md                          # Shared guidelines file (devai-managed marker block)

Copilot does not implement LSP registration and no skills are distributed for Copilot.

copilot-instructions.md

The .github/copilot-instructions.md file is read by Copilot Chat for every workspace session. The installer writes merged Marko guidelines inside a  marker block, so your own edits outside the markers survive re-runs (see Editing generated files):

Module structure and naming conventions
Available MCP tools
Project-specific guidelines from every installed package's resources/ai/guidelines.md

MCP registration

The .vscode/mcp.json file registers marko mcp:serve as an MCP server using the servers key (not mcpServers). Each entry includes a type field for the transport. Copilot Chat's agent mode can call tools like find_event_observers and validate_module when answering questions about your project.

AGENTS.md

devai:install writes the shared AGENTS.md guidelines inside a  marker block: created if absent, and on later runs only the marked region is refreshed, so content you add outside the markers is preserved. Remove the markers to take full ownership — devai then leaves the file alone. See Editing generated files.

Read the full file on GitHub · 58 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.

2d ago First seen · 58 lines · 19 tokens per session scan A 7fa85eade309

Subscribe to this mod's changes

copilot is an agent published in the GitHub repository marko-php/marko (393 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 762 once invoked, about $0.0001 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.

Languages Writing and docs php php-framework php8

copilot

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Prerequisites

What devai:install writes

copilot-instructions.md

MCP registration

AGENTS.md

What this file has done since we first saw it

Other agents, from other repositories

fixture-reviewer

module-docs-sync

tdd-coach

quick-syntax

index

changelog-keeper