Copilot plugin for Claude Code
Use GitHub Copilot (GPT-5.4) from inside Claude Code for code reviews, adversarial reviews, or to delegate tasks.
This plugin is for Claude Code users who have a GitHub Copilot subscription and want GPT-5.4 as a second brain for code review and task delegation.
Each slash command costs at most 1 Copilot premium request. Status, result, cancel, and setup cost 0.
What You Get
/copilot:review for a native Copilot code review/copilot:adversarial-review for a steerable challenge review with structured findings/copilot:rescue, /copilot:status, /copilot:result, and /copilot:cancel to delegate work and manage background jobs/copilot:ask for quick one-shot questions/copilot:task for delegating agentic tasks (foreground or background)/copilot:plan for generating structured implementation plans/copilot:review-plan and /copilot:adversarial-plan-review for reviewing plans
Requirements
- GitHub Copilot subscription with access to the Copilot CLI
- Node.js 18.18 or later
Install
Add the marketplace in Claude Code:
/plugin marketplace add mvpasarel/gh-copilot-plugin-cc
Install the plugin:
/plugin install copilot@mvpasarel-copilot
Reload plugins:
/reload-plugins
Then run:
/copilot:setup
/copilot:setup will tell you whether the Copilot CLI is installed and authenticated.
If Copilot CLI is not installed, follow the GitHub Copilot CLI docs to install it.
If Copilot is installed but not logged in yet, run:
!copilot login
After install, you should see:
- the slash commands listed below
- the
copilot:copilot-rescue subagent in /agents
One simple first run is:
/copilot:review --background
/copilot:status
/copilot:result
Update
claude plugin update copilot@mvpasarel-copilot
Then restart Claude Code to apply.
Usage
/copilot:setup
Checks whether the Copilot CLI is installed and authenticated.
You can also use /copilot:setup to manage the optional review gate.
Enabling review gate
/copilot:setup --enable-review-gate
/copilot:setup --disable-review-gate
When the review gate is enabled, the plugin uses a Stop hook to run a targeted Copilot review based on Claude's response. If that review finds issues, the stop is blocked so Claude can address them first.
[!WARNING]
The review gate costs 1 premium request per stop and can create a long-running Claude/Copilot loop. Only enable it when you plan to actively monitor the session.
/copilot:review
Runs a native Copilot review on your current work. Copilot's built-in review agent automatically detects uncommitted changes, staged changes, and recent commits.
[!NOTE]
Code review especially for multi-file changes might take a while. It's generally recommended to run it in the background.
Use it when you want:
- a review of your current uncommitted changes
- a review of your branch compared to a base branch like
main
Use --base <ref> for branch review. It also supports --wait and --background. It is not steerable and does not take custom focus text. Use /copilot:adversarial-review when you want to challenge a specific decision or risk area.
Examples:
/copilot:review
/copilot:review --base main
/copilot:review --background
This command is read-only and will not perform any changes. When run in the background you can use /copilot:status to check on the progress and /copilot:cancel to cancel the ongoing task.
/copilot:adversarial-review
Runs a steerable review that questions the chosen implementation and design.
It can be used to pressure-test assumptions, tradeoffs, failure modes, and whether a different approach would have been safer or simpler.
It uses the same review target selection as /copilot:review, including --base <ref> for branch review.
It also supports --wait and --background. Unlike /copilot:review, it can take extra focus text after the flags.
Use it when you want:
- a review before shipping that challenges the direction, not just the code details
- review focused on design choices, tradeoffs, hidden assumptions, and alternative approaches
- pressure-testing around specific risk areas like auth, data loss, rollback, race conditions, or reliability
Examples:
/copilot:adversarial-review
/copilot:adversarial-review --base main challenge whether this was the right caching and retry design
/copilot:adversarial-review --background look for race conditions and question the chosen approach
This command is read-only. It does not fix code.
/copilot:rescue
