Griffin Lickfeldt’s Post

This is a pretty big step for how we work with agents. GitHub Copilot CLI is no longer just local. You still run the session on your machine, but you can now control it remotely from GitHub web or even your phone. That convenience matters a lot once you move to longer running agent flows: -> you don’t have to stay at your desk -> you can review plans and approve steps on the go -> you can jump in only when needed for decisions or escalations It fits really well with human-in-the-loop workflows, where the agent keeps going, but you stay in control at key moments. Feels like a small feature, but it unlocks a much more practical way to run agentic development. Worth a read 👇 https://lnkd.in/dfTh3ZEg #AgenticAI #Copilot #SoftwareDevelopment #DevTools #DeveloperExperience

I've compiled a practical overview of 20 powerful yet underutilized GitHub Copilot CLI commands and features that can transform Copilot from a helpful assistant into a highly capable autonomous coding agent. This overview covers: - Efficient session management - Non-interactive execution - Advanced model switching - Tool permissions - Persistent custom instructions - Intelligent code reviews - GitHub integration - Parallel agent workflows These techniques can significantly boost development speed and consistency. #GitHubCopilot #AICoding #DeveloperProductivity #SoftwareEngineering #CLI #Microsoft

GitHub Copilot CLI… without a GitHub Copilot subscription? With recent restrictions around GitHub Copilot's new personal subscriptions sign-up, I wanted to see if I could still use the CLI experience with open models. Turns out—you can. I set up Copilot CLI using Open LLMs (BYOK approach), and it opens up a lot of possibilities: • Run models locally (depending on your hardware) • Use hosted models via OpenRouter • Control cost and performance • Customize how AI interacts with your workflows I also went deeper into: Context window management in CLI Model selection (weights, quantization, parameters) LM Studio configuration for running open source models And for a practical demo 👇 I built a skill that converts a wireframe into HTML/React code using the CLI. This setup is surprisingly powerful if you want flexibility beyond standard GH Copilot usage. 🎥 Watch here: https://lnkd.in/eHGM3b97 Let me know in the comments if you would like a copy of the wireframe to HTML code skill. #AI #Copilot #LLM #OpenSource #DeveloperTools #SoftwareEngineering

✨ Have you ever had an idea that you want to code but don't know how!! On Antisyphon this week: GitHub Copilot training with Carrie Roberts! She broke down how Copilot is transforming the idea of “knowing how to code” and showed practical ways to use it to build, debug, and refactor — all from your browser. 💡 If you couldn’t make it live, you can still watch the full session! Just search for the class on YouTube or LinkedIn and enjoy the replay at your own pace. #LearningTogether #GitHubCopilot #AIForDevelopers #TechCommunity #Upskilling #FutureOfWork

Want tips on using GitHub Copilot CLI ? I built a "Tip of the Day" for GitHub Copilot CLI — powered by /chronicle, it learns from how I actually use it 🚀 I use Copilot CLI daily for team investigations, GitHub searches, and workplace lookups. But I kept forgetting about features that would save me time. So I automated it. Now every morning, a personalized tip appears in my terminal — generated by Copilot's /chronicle command, based on my real session history. Here's how it works: - 🔍 /chronicle analyzes my past Copilot sessions — what tools I used, what I asked, what patterns I follow - 🎯 It generates a tip tailored to my workflow — features I haven't tried, better ways to do things I already do - 🔄 A zsh precmd hook displays the tip the first time I interact with any terminal each day — even ones left open overnight - ⏰ A macOS LaunchAgent pre-generates the tip at 7am so it's instant The whole setup is just two files: 1. daily-tip.sh — the zsh hook that calls /chronicle and caches the result 2. A LaunchAgent plist for pre-generation (optional) Add one line to your ~/.zshrc: [[ -f "$HOME/.copilot/daily-tip.sh" ]] && source "$HOME/.copilot/daily-tip.sh" That's it. No Python scripts, no static tip lists, no maintenance. /chronicle does the heavy lifting — it knows your history and gets smarter as your usage evolves. Grab the code: https://lnkd.in/e7CM4Wjz I built all of this using Copilot CLI itself. 😎 #GitHubCopilot #CopilotCLI #DeveloperProductivity #AI #DevTools

The Github Copilot CLI updates for BYOK open up a lot of great opportunities for Mission teams to use these kinds of tools to really level up development. Here's a great primer on what the Github Copilot CLI is and how it works. https://lnkd.in/g7QTPjt6

𝗕𝗲𝗳𝗼𝗿𝗲 𝗔𝗰𝗰𝗲𝗽𝘁𝗶𝗻𝗴 𝗔𝗻 𝗘𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲 𝗖𝗼𝗽𝗶𝗹𝗼𝘁 𝗦𝗲𝗮𝘁 GitHub paused new sign-ups for Copilot Pro and Pro+ plans. If you have a personal paid plan, read this before you accept a company seat. GitHub cancels your personal plan when you accept an enterprise seat. This process is automatic. You get a refund for unused time. This cancellation is permanent. You will not be able to sign up for a Pro plan again. If you lose your job or the seat, you move to Copilot Free. Copilot Free has limits: - 50 premium requests per month. - 50 IDE chat messages per month. - No Copilot CLI. Enterprise seats are better while you have them. Accept the seat if you have stable work. Know the risk first. Source: https://lnkd.in/gdUGnYza Optional learning community: https://t.me/GyaanSetuAi

GitHub pauses new sign-ups for GitHub Copilot Pro, Pro+, and Student plans, tightens limits for individual plans, and removes Opus models from Pro plan. https://lnkd.in/d8WN4UzA

#GitHub #copilot users - be aware that changes to licensing are coming. 🆕 New signups are paused 🆕 tighter limits on Pro plans. 🆕 Opus models removed from Pro https://lnkd.in/diNPAuzE

That's a pity. Since the limits in #Claude Pro are already limiting, now there will be tighter limits in #GitHub #Copilot too. I think "fun projects" will get fewer.