Update to CodeAgent Mobile

{
  "description": "Start a CodeAgent coding task from the user's request on one of their existing sessions, and report the session id so they can follow it.",
  "included_files": [],
  "name": "start-coding-task",
  "skill_md_contents": "---\nname: start-coding-task\ndescription: Start a CodeAgent coding task from the user's request on one of their existing sessions, and report the session id so they can follow it.\n---\n\n# Start a coding task\n\nUse this when the user asks to have an agent do coding work (\"fix…\", \"implement…\", \"add tests for…\", \"solve issue #…\").\n\n## Workflow\n1. Call `list_sessions`. If the user named a repository, project or host, pick the session whose `repository` or `title` matches. If none matches, or more than one could, **ask the user which session** — never guess.\n2. If the chosen session is `offline`, tell the user the host is offline; `start_task` will try to wake a codespace or CodeAgent Box, but a local CLI must be started by the user.\n3. If the user asked for a specific agent, call `list_agents` and pass its `id` as `agent_id`. If that agent is `managed` (uses credits), follow the `continue-with-codeagent-credits` skill first.\n4. Call `start_task` with a clear, self-contained `task` (include the issue number and any acceptance criteria the user gave). For a GitHub issue, describe it in the task text; the agent reads the repository itself.\n5. Reply in three lines: what was started, on which session (`title`, `session_id`), and that you will report progress on request. Example:\n   ```\n   Started Claude Code on org/app (session cmt…): \"Fix checkout validation\".\n   Status: running. Ask me \"what's the agent doing?\" for an update.\n   ```\n6. Never say the work is done. `start_task` only accepts the task; completion is only visible through `get_session` (status `idle` with new changes) or `get_diff`.\n"
}