Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,8 @@ The following options are available:

Write agent settings and companion skill files at the project or user scope. Interactive setup prompts for a scope; non-interactive setup defaults to `project`.

Skills and MCP configuration follow the selected scope. The [telemetry hooks](/reference/cli/microsoft-collected-cli-telemetry/#ai-agent-skill-usage) are always written to user-level configuration (`~/.copilot/hooks` and `~/.claude/settings.json`), even with `--scope project`, so they apply in every repository where that client runs. Set `ASPIRE_CLI_TELEMETRY_OPTOUT=true` to opt out.
Comment thread
ellahathaway marked this conversation as resolved.
Resolved

- **`--skills <skills>`**

Comma-separated choices: `aspire`, `playwright-cli`, or `dotnet-inspect`. The `dotnet-inspect` skill requires a C# AppHost in the workspace. Use `all` for every applicable choice or `none` to skip them. Defaults to `aspire`, which applies all enabled skill sources. MCP setup is separate.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ Aspire CLI telemetry is collected when using the CLI to run commands. Telemetry

When you run `aspire agent init`, Aspire installs Aspire's AI skills and a `PostToolUse` hook into each detected agent client's user-level configuration (for example, GitHub Copilot CLI and Claude Code). The hook lets Aspire understand which of its AI skills and tools are actually used so the team can invest in the most valuable ones.

The hook is always installed at user scope, even when you run `aspire agent init --scope project`. Because user-level configuration applies to every repository, the hook runs wherever that client runs, but it reports usage events only for Aspire's own skills, MCP tools, or skill reference files.

After each agent tool use, the hook checks if an **Aspire** skill, Aspire MCP tool, or Aspire skill reference file was involved. If so, the hook inspects the event and forwards a low-cardinality usage event to the hidden `aspire agent telemetry` command. The command records the event through the same CLI telemetry pipeline. Tool uses that don't involve Aspire skills or tools are ignored. See [AI agent skill usage data](#ai-agent-skill-usage-data) for exactly what's recorded.

## How to opt-out
Expand Down
Loading