copilot-cli

copilot-cli is a plugin for Claude Code from wkin-t/claude-copilot-plugin. Its manifest loads nothing; the 1 skill, 2 agents it bundles cost 720 tokens per session together, scanned A, original, MIT.

A plugin that sends coding tasks to GitHub Copilot CLI, a command-line tool for AI-assisted programming. It can use GPT-5 or Sonnet as separate task workers and reviewers.

In plain words
What is it for?
Use it to delegate coding tasks to Copilot CLI and request adversarial reviews that look for problems in the work.
Why use it?
It helps divide work between coding agents and adds a separate review pass to challenge the result. This can reduce the need to handle every task and check yourself in one session.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions subagents.

Good fit Use it to delegate coding tasks to Copilot CLI and request adversarial reviews that look for problems in the work.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add wkin-t/claude-copilot-plugin
/plugin install copilot-cli
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.

Clone the repo
git clone --depth 1 https://github.com/wkin-t/claude-copilot-plugin

Made for: Claude Code.

Wrote 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.

agentmods badge for copilot-cli

README.md
[![agentmods](https://agentmods.dev/badge/plugins/wkin-t/claude-copilot-plugin/copilot-cli/github.svg)](https://agentmods.dev/plugins/wkin-t/claude-copilot-plugin/copilot-cli)
Your own site
<a href="https://agentmods.dev/plugins/wkin-t/claude-copilot-plugin/copilot-cli"><img src="https://agentmods.dev/badge/plugins/wkin-t/claude-copilot-plugin/copilot-cli/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for copilot-cli

Your own site · 80×15
<a href="https://agentmods.dev/plugins/wkin-t/claude-copilot-plugin/copilot-cli"><img src="https://agentmods.dev/badge/plugins/wkin-t/claude-copilot-plugin/copilot-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 2 agents cost 720 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
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 2mo 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.

plugins/copilot-cli/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "copilot-cli",
  "version": "1.0.12",
  "description": "Dispatch tasks to GitHub Copilot CLI (GPT-5/Sonnet) as subagents — task delegation and adversarial review.",
  "author": {
    "name": "wkin-t",
    "url": "https://github.com/wkin-t"
  },
  "homepage": "https://github.com/wkin-t/claude-copilot-plugin",
  "repository": "https://github.com/wkin-t/claude-copilot-plugin",
  "license": "MIT",
  "keywords": [
    "copilot",
    "gpt-5",
    "subagent",
    "code-review",
    "delegation"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 2 agents travel with it, and installing the plugin installs all of them — 720 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 2mo ago First seen · 20 lines scan A 98b1b7944795

Subscribe to this mod's changes

copilot-cli is a plugin published in the GitHub repository wkin-t/claude-copilot-plugin (4 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.

Related

copilot-cli compared with plugins from other repositories

copilot-cli next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
copilot-cliwkin-t/claude-copilot-pluginPlugin46mo agoMITA—Claude Code
humanizerblader/humanizerPlugin68k2d agoMITA—Claude Code
claude-plugins-official marketplaceanthropics/claude-plugins-officialPlugin47ktodayApache-2.0A—Claude Code
nextjsvercel/next.jsPlugin143ktodayMITA—Claude Code
themes-examplegoogle-gemini/gemini-cliPlugin109ktodayApache-2.0A—Gemini CLI
knowledge-work-plugins marketplaceanthropics/knowledge-work-pluginsPlugin35ktodayApache-2.0A—Claude Code
code-modernizationanthropics/claude-plugins-officialPlugin47ktodayApache-2.0A—Claude Code