Copilot · GitHub · GitHub Blog
From one-off prompts to workflows: How to apply custom agents in GitHub Copilot CLI
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Developers work across many surfaces like the CLI, IDE, and GitHub.
Key facts
- Jacklyn Lee is a Content Writer at GitHub and a former technical writer with a love for good storytelling
- Developers work across many surfaces like the CLI, IDE, and GitHub
- They also let fast, execution-heavy tasks start in the CLI, carry context into the IDE, and land on GitHub as reviewable, shippable work
- After working with their partners like JFrog, Dynatrace, Octopus Deploy, arm, and others, they offer several off-the-shelf agents to help you
Summary
However, like any environment, the CLI can still accumulate friction: re-running the same commands, re-explaining context, or translating logs for your team into something they can act on. But what if your terminal didn’t run commands, it understood your stack, your tools, and your team’s standards? With custom agents in the CLI, you can turn repeated tasks and patterns into consistent, reviewable workflows that fit naturally alongside your other tools, further tailoring GitHub Copilot CLI with expertise for specific development tasks. A custom agent is a Copilot agent that can be defined using a Markdown file.