Heldinhow/copilot-cli-subagents
copilot-cli-subagents/SKILL.md
Use GitHub Copilot CLI with /fleet for parallel subagent execution and custom agent workflows.
$ install --global
skillsauthnpx skillsauth add Heldinhow/awesome-opencode-dev-skills copilot-cli-subagentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 7:26 AM117.8s2 files scanned
SKILL.md
- name:
- copilot-cli-subagents
- description:
- Use GitHub Copilot CLI with /fleet for parallel subagent execution and custom agent workflows.
Copilot CLI Subagents
Overview
GitHub Copilot CLI enables parallel task execution through subagents, allowing multiple independent tasks to run simultaneously. This skill should be invoked when executing multiple independent tasks that can run in parallel, leveraging /fleet for coordinated multi-agent execution.
Core Principles
- Plan Mode: Use Shift+Tab for complex task planning
- Fleet Execution: Use /fleet to execute multiple subagents
- Task Monitoring: Track progress with /tasks command
- Result Integration: Combine outputs from multiple agents
Preparation Checklist
- [ ] Install GitHub Copilot CLI extension
- [ ] Understand /fleet command capabilities
- [ ] Plan task breakdown for parallel execution
- [ ] Set up custom agents if needed
Step-by-Step Process
- Plan: Enter plan mode with Shift+Tab
- Define: Break down implementation into subtasks
- Execute: Run with /fleet command
- Monitor: Track with /tasks command
- Review: Examine outputs from each agent
- Integrate: Combine results into unified solution
Do's and Don'ts
- ✅ Do use /fleet for independent parallel tasks
- ✅ Do monitor task completion
- ✅ Do verify integration of results
- ❌ Don't use for sequential dependent tasks
- ❌ Don't ignore API costs with multiple agents
- ❌ Don't skip result verification
Anti-Patterns
- Sequential Fleet: Trying to use fleet for dependent tasks
- No Monitoring: Not tracking fleet execution progress
- Result Ignorance: Accepting outputs without verification
- Over-Fleet: Spawning too many concurrent agents
Related Skills
Heldinhow/websocket-real-time
tools
VerifiedTrustedCommunity
Implement WebSocket communication for real-time bidirectional client-server communication.
2SKILL.mdUpdated Apr 24, 2026
Heldinhow/webhook-handler
development
VerifiedTrustedCommunity
Implement webhook handlers for processing incoming events from external services.
2SKILL.mdUpdated Apr 24, 2026
Heldinhow/webapp-testing
development
VerifiedTrustedCommunity
Test web applications using Playwright for end-to-end browser testing.
2SKILL.mdUpdated Apr 24, 2026
Heldinhow/web-artifacts-builder
development
VerifiedTrustedCommunity
Build production-quality HTML artifacts using React, Tailwind CSS, and shadcn/ui.
2SKILL.mdUpdated Apr 24, 2026