Use lk agent for console, dev, and start

[bcherry]

What

Points the starter's local run instructions at the LiveKit CLI, and trims the README and AGENTS.md:

• README
  • CLI install moves to the top of Dev setup as a three-line list, with a link to the update instructions. The floor is now 2.18.8, the first version with lk agent debugger.
  • "Run the agent" shows lk agent console, lk agent dev, and lk agent debugger, then the direct node src/main.ts start for production. That's what the Dockerfile runs via pnpm start.
  • The feature list says what each piece does for you and links the docs for how. That covers Fish Audio as an expressive, cost-effective default, expressive mode, and adaptive interruption handling, which the starter enables but the list never mentioned.
  • "Using coding agents" shows lk docs search followed by lk docs get-page, since search only returns excerpts, and points to the bundled AGENTS.md and LiveKit Agents skill.
  • "Testing and debugging" points to the debugger for turn-by-turn checks, and adds Agent Console and lk agent logs.
  • Manual setup includes the git clone it was missing, and uses --write --destination rather than short flags.
• package.json — the dev script runs lk agent dev. start is unchanged.
• taskfile.yaml — the post-init hint prints lk agent dev.
• AGENTS.md
  • Drops guidance a coding agent can work out on its own: the project-layout paragraph, the run-command walkthrough, the lk docs command list, and the MCP transport details.
  • Adds a section on the bundled skill, with a fallback path for tools that don't load skills on their own.
  • Makes scenarios the tests and lk agent debugger the loop for checking each change, instead of the unit testing framework. The debugging checklist starts from reproducing the problem in the debugger, and points to Agent Console for speech issues the text-only debugger can't show.
  • Widens the feedback prompt from docs gaps to any LiveKit problem, keeping the to-do-list timing.
• Copy pass against the docs style guide: sentence-case headings, no "we", no hyphens standing in for dashes, bulleted rather than numbered lists where order doesn't matter, and less filler. Links to the testing, observability, and workflows pages point at their current paths.

Why

lk agent console and lk agent dev are the documented way to run an agent locally, and the Python starter already moved to them (livekit-examples/agent-starter-python#103). The CLI install instructions were buried in "Using coding agents", below the first commands that need them. lk agent debugger gives a coding agent a cheap way to check its own changes, so the starter should tell it to.

Notes for reviewers

• "Cost-effective" is based on LiveKit Inference pricing: Fish Audio S2.1 Pro is $15 per 1M characters, the lowest paid TTS tier, against $50 for Cartesia and $150–300 for ElevenLabs.
• AGENTS.md now matches the Python starter's after the review round there (Trim the README and AGENTS.md, and cover skills and debugging agent-starter-python#105), apart from tooling and the Node.js feature-parity note. The "LiveKit documentation" block is likely mirrored in other starters, which will now differ.
• src/agent.test.ts is still in the repo; only the docs stopped pointing to it.
• Every docs.livekit.io link in both files returns 200 without a redirect. prettier --check is clean.

🤖 Generated with Claude Code

https://claude.ai/code/session_01U7yszNU7t5aCHJsKLmU4hv