work-idealisted

# work-idea Workflow for producing a detailed brief on one Ideate idea, then navigating into its session. The unit of work is the **idea**. Sessions are one facet of an idea, alongside the backlog (tasks queued or mid-flight), resources (linked artifacts), and recent activity. The brief covers the whole idea, not just whatever session happens to be running. ## Inputs The user supplies an identifier for the target. Resolve in this order: 1. Session UUID (matches `^[0-9a-f-]{36}$`) — resolve to its owning idea via the `sessions.running` / `sessions.dormant` UUIDs on each `list_ideas` row. 2. Idea slug (exact match). 3. Idea name (case-insensitive substring). 4. Fuzzy keyword from the user's phrasing (e.g. "the boilerplate idea", "the search migration", "JWKS"). If the input matches zero ideas or more than one, stop and ask the user to disambiguate. Do not guess. ## Steps 1. **Batched workspace fetch.** Call `ideate:list_ideas` with `include_output_lines: 120`. The result carries every non-archived idea's `summary`, `backlog` counts + in-progress titles, `sessions.running` + `sessions.dormant` lists, `last_activity_at`, AND the most-recent running session's last 120 lines of screen — enough context to recover detailed state on the resolved idea. Resolve the user's input against the returned rows using the order above. 2. **(Optional) cross-references.** If the user's phrasing carries a URL (PR link, doc URL), call `ideate:match_resource_