GitHub adds custom agents to Copilot CLI workflows

GitHub announced on June 9, 2026 in a blog post that it is adding custom agents to Copilot CLI, enabling teams to encode stack context and standards into reusable CLI workflows. Per the post, a custom agent is defined using a Markdown file that describes the agent's behavior, available tools, standards, and outputs. The blog also states that remote control for Copilot sessions is now generally available on github.com and GitHub Mobile, and that GitHub is piloting an experimental general-purpose accessibility agent. The feature aims to turn one-off terminal prompts into repeatable, reviewable processes that live alongside existing developer tools.
What happened
GitHub announced on June 9, 2026 in a blog post on github.blog that it is introducing custom agents for Copilot CLI. The post describes a custom agent as a Copilot agent defined using a Markdown file that specifies how the agent should operate, which tools it can use, what standards it should follow, and what outputs it should produce. The post also says remote control for Copilot sessions is now generally available on github.com and GitHub Mobile and that GitHub is piloting an experimental general-purpose accessibility agent.
Technical details
The blog explains that custom agents let teams encode repository, tooling, and process context so the same agent behavior runs consistently wherever the agent is used. Examples in the post include coding agents that apply project-specific formatting rules and workflows that transform repeated terminal prompts into reviewable, repeatable tasks. The feature is presented as file-driven, with agents described in Markdown.
Editorial analysis
Programmable, reproducible agents match a broader trend toward making AI-driven developer assistance automatable and auditable. Teams adopting file-defined agents can reduce the need to re-explain context in ad hoc prompts and increase reproducibility of CLI-based automation. For practitioners: reusable agents lower the friction of operationalizing prompt-based workflows, but they also shift attention toward maintaining the agent definition and CI processes that validate agent outputs.
What to watch
Observers should track whether GitHub publishes examples, templates, or CI integration patterns for agent definitions and whether third-party tooling integrates with the Markdown-based agent format.
Scoring Rationale
This is a notable tooling update for developer productivity, making prompt-driven terminal work more reproducible. It is not a frontier-model release, but it materially affects workflows for engineers who use the CLI and Copilot.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems


