Copilot CLI issue proposes inline custom-agent calls and chaining
DenDrobiazko-Apryse · ghdev · 2026-07-21
A GitHub Copilot CLI issue proposes explicit inline custom-agent invocation and chaining inside prompts.
- Today, users can pick a custom agent before starting a task or rely on automatic delegation, but cannot clearly switch agents mid-prompt.
- The proposal adds syntax like $agent: architecture-review so a workflow can pass findings from one specialized agent to another while preserving context.
- The author argues this would make multi-agent workflows more deterministic, easier to document, and less dependent on the model guessing which agent to use.
More from coding & agent
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- Tokyo Agent Forge hackathon shipped production-ready AI agents in one day — DavidBennett__ · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- A VS Code extension adds Markdown-style highlighting to Alchemy string templates — samgoodwin89 · 2026-07-27
- Claude’s Stripe MCP connector is being called unusable after repeated disconnects — evielync · 2026-07-27