World

This is Mission Control. When the human opens their world, it should feel like booting an operating system — everything they care about, at a glance, with clear paths to action.

NOT a database dump. NOT a flat list. A living view of their world, grouped by what matters, showing relationships, surfacing what needs attention.

Load Sequence

1. Read the injected <WORLD_INDEX> — it's already in your session context from the SessionStart hook. Contains every walnut's type, goal, phase, rhythm, updated, people, links, tags, bundles, and parent relationships. Zero file reads needed. If <WORLD_INDEX> is not in context, fall back to reading .alive/_index.yaml directly.
2. If no index exists at all — generate it first (python3 "$ALIVE_PLUGIN_ROOT/scripts/generate-index.py" "$WORLD_ROOT"), then read the output. Fall back to manual scanning only on first-time setup before the index infrastructure exists.
3. Freshness check — read the generated: timestamp from the index. Display it in the dashboard header. If older than 10 minutes, show a warning. If older than 1 hour, suggest regeneration. This makes index staleness visible instead of invisible.
4. Build the tree from the index — parent/child relationships from parent: field
5. Lightweight fresh checks — one Bash call each, no subagents, no Explore agents:
   • Unsaved sessions with stash: already in the index as unsaved_with_stash:. If non-zero, surface in the Attention section. No bash loop needed.
   • Unrouted inputs: resolve the world root via the doctor JSON surface, then list the absolute path. Never use a relative ls 03_Inbox/ — it silently fails when the Bash tool's cwd isn't the world root. One-liner:

     WR=$(alive doctor --check=world-root --json | jq -r '.world_root') && [ -n "$WR" ] && ls "$WR/03_Inbox/" 2>/dev/null | grep -v '^\.' | grep -v '^Icon'
     

     Doctor's pinned-strategy result is the authoritative resolver — preferred over raw config-file reads, which mangle paths with internal whitespace. Just the filenames, no deep reads.
   • API context: only if context sources are listed in the session start injection (already in your context from the hook — do NOT re-read preferences.yaml).
6. Compute attention items from fresh checks + index staleness signals
7. Inbox triage (background) — if 03_Inbox/ has items, dispatch a background agent to triage them. Don't wait for it — render the dashboard immediately, the triage results arrive while the human reads.

Inbox Triage Agent

Dispatch with run_in_background: true when inbox has 1+ items. The agent:

1. Reads the subagent brief from the plugin templates (for ALIVE context)
2. Lists all files in 03_Inbox/ with ls -la
3. For each item, determines:
   • Type: transcript, email, document, screenshot, video, extraction directory, financial, unknown
   • Likely destination walnut: match against the world index (injected in the agent prompt) by keywords, people names, project names
   • Priority: urgent (contains decisions/deadlines), normal, low (reference material)
   • Age: how old is the file
4. Returns a structured triage report

When the background agent completes, surface the results:

╭─ 🐿️ inbox triaged (8 items)
│
│  Urgent
│   march-expenses.csv              → finance (transactions, needs review)
│   error-log-april-2.txt           → my-startup (build error from deploy)
│
│  Route
│   team-dinner-recap.mp4           → my-startup (event footage)
│   fathom-extraction/              → runs via /alive:mine-for-context
│   otter-extraction/               → runs via /alive:mine-for-context
│
│  Auto-route (low priority)
│   gmail/                          → capture via sync script
│   slack/                          → capture via sync script
│
│  ▸ Route all? Or review one at a time?
│  1. Route all suggested
│  2. Review each
│  3. Skip for now
╰─

The triage agent gets the world index in its prompt so it knows every walnut, person, and active bundle. It matches by name, keywords, and file type patterns. It does NOT move files — it suggests. The human confirms.

DO NOT read preferences.yaml — it's already injected at session start. DO NOT read individual walnut files (key.md, now.json, log.md) — the index has everything. DO NOT read .alive/_squirrels/*.yaml files — recent sessions are in the index under recent_sessions: and unsaved stash count is in unsaved_with_stash:. DO NOT spawn Explore agents or subagents for the dashboard — use the index and the one bash check above. The entire dashboard should render from data already in context plus 1 fast bash call (inputs listing).

State Detection

Before rendering, detect system state:

• Fresh install (no walnuts exist) → route to setup.md
• Previous system detected (v3/v4 _brain/ folders exist) → offer migration via /alive:create-walnut migrate mode
• Normal → render dashboard

Dashboard Layout

The dashboard has 4 sections. Each tells you something different.

Section 1: Right Now

What needs the human's attention TODAY. Not everything — just what's active and demanding.

╭─ 🐿️ your world
│
│  RIGHT NOW
│  ──────────────────────────────────────────────
│
│   1. my-startup              launching
│      Urgent: 1 · Active: 3
│      Last: 2 hours ago · 6 sessions this week
│
│   2. freelance-agency        legacy
│      Urgent: 3 · Active: 0
│      Last: 2 days ago
│      People: Jake Chen, Sarah Mills
│
│   3. social-content          building
│      Urgent: 0 · Active: 8
│      ⚠ 4 days past rhythm
│
╰─

Only show walnuts that are active or past their rhythm. Sort by most recently touched. Show:

• Phase
• Urgent + active task counts (from the index's task_counts payload, which mirrors _kernel/now.json unscoped_tasks.counts)
• Last activity (relative time)
• People involved (from _kernel/key.md — max 2-3 names)
• Warning if past rhythm

Section 2: Attention

Things that need your decision or action. Not walnuts — specific issues.

╭─ 🐿️ attention
│
│   → 3 unread emails from Orion (Gmail, 2 days)
│   → Unsaved session on nova-station (squirrel:a3f7, 6 stash items)
│   → 03_Inbox/ has 2 items older than 48 hours
│   → flux-engine quiet for 12 days (rhythm: weekly)
│   → 4 working files older than 30 days across 3 walnuts
│
╰─

Sources:

• Inputs buffer (HIGH PRIORITY) — anything in 03_Inbox/ older than 48 hours. These are unrouted context that could impact active walnuts TODAY. The squirrel should stress this to the human: "You have unrouted inputs. These might contain decisions, tasks, or context that affects your active work. Route them before diving into a walnut."
• API context (Gmail unread, Slack mentions, Calendar upcoming)
• Unsaved sessions with stash items (saves: 0)
• Stale walnuts (quiet/waiting)
• Stale working files

Inputs triage: The world skill should understand that inputs are a buffer — content arrives there and needs routing to its proper walnut. When surfacing inputs, the squirrel should scan the context.manifest.yaml frontmatter (if manifests exist) or the file names to understand what the content might relate to. Don't digest the full content — just flag it, estimate which walnuts it might affect, and urge the human to route it. Use alive:capture-context to process each input properly.

Section 3: Your World (the tree)

The full structure — grouped by ALIVE domain, with parent/child nesting visible.

╭─ 🐿️ your world
│
│  LIFE
│   identity           active     LinkedIn bio update
│   health             quiet      ADHD assessment follow-up
│   finance            quiet      ⚠ 10 days — subscriptions review
│   people/
│     jake-chen        updated 2 days ago
│     sarah-mills      updated 1 day ago
│     tom              updated 5 days ago
│
│  VENTURES
│   my-startup         launching  MVP demo + investor deck
│     └ mobile-app     building   React Nati