now

Composite top-level dashboard. Not a skill that runs - a UI surface that queries multiple endpoints to render the current system state in real time.

Lives at state/skills/now/resources/ui.openui. Served via the per-skill serve route when the user asks broad intent questions like "show me what's happening right now", "give me a system overview", "show me the status".

The dashboard IS the verb. There is nothing to invoke server-side; the chat renders the OpenUI Lang composition fetched from the skill's resource file.

Dashboard shape

The Now dashboard shows:

1. Agent activity - running agents, their status, how long they have been running
2. Recent skill runs - the last 10 skill evaluations with scores and timestamps
3. System KPIs - total agents, active dispatches, recent activity count
4. Skills summary - total skills available, recent skill count

Each panel is a Card with a Table or Stack of key metrics. The dashboard queries multiple endpoints:

• /agents - list of agents and their current status
• /recent - recent skill evaluations (evals.ndjson tail)
• /full-state - high-level summary of dispatch activity

All data is live; the dashboard refreshes by re-rendering when the user asks again.

No prose steps

The dashboard is purely a UI resource. It has no executable steps - the Steps section is deliberately omitted. The render happens client-side when the snappy-chat app mounts the shape.

now - loader

Per-turn rules for the live status dashboard. Full skill: state/skills/now/SKILL.md. Prose-only UI resource; no executable steps.

Critical Rules

1. No backend execution. "now" is a pure UI resource (OpenUI Lang). It does not run anything server-side.
2. Resource served via per-skill route. Broad-intent regex matches "what is happening now" / "system overview" and routes to /bundle/now/resources/ui.openui.
3. Live data binding: OpenUI Query() at render time. Resource file uses Query() calls to fetch from /agents, /recent, /full-state inline. Data fetched at render time, not pre-fetched.
4. All fields must render, even if empty. Agent list, recent evals, KPIs must exist even with 0 agents or stale data. Fallback to sensible defaults (empty arrays, 0 counts).
5. Three data endpoints: /agents (agent list + status), /recent (tail of evals.ndjson), /full-state (system-wide counts + summaries).

Commands

Dashboard Shape

Renders four panels:

1. Agent activity - running agents, status, elapsed time
2. Recent skill runs - last 10 evaluations with scores, timestamps
3. System KPIs - total agents, active dispatches, recent count
4. Skills summary - total skills available, recent skill count

Query Pattern

Resource uses OpenUI Query() for live binding:

agents = Query("get_agents", {}, {agents: []}, 10)
recent = Query("get_recent", {}, {evals: []}, 10)
kpis = Query("get_kpis", {}, {total_agents: 0, running_count: 0, recent_count: 0}, 30)

Custom backend routes (get_agents, get_recent, get_kpis) return JSON matching shapes above. Refresh by re-render.

Self-Test

• [ ] Understand "now" is pure UI, no backend execution?
• [ ] Know resource is served via /bundle/now/resources/ui.openui?
• [ ] Recognize Query() fetches live data at render time?
• [ ] Know endpoints: /agents, /recent, /full-state?
• [ ] Understand broad-intent regex routing for "what is happening now"?

<!-- kernel-ok: historical attribution for the PID-loader pattern. -->

Self-correcting loader (PID feedback)

This is the rule that makes loaders learn. Ported from snappy-kernel, where it demonstrably worked: the snappy-dom-cartographer skill mapped Skool admin UI once, every later ship-agent inherited the full map for free.

Before you finish, do two things:

1. Fix gaps (P - proportional). MANDATORY. If this loader didn't cover your case - if you had to read another file, run an undocumented command, work around a wrong selector, or discover a quirk - you MUST attempt an Edit to this AGENTS.md before you log.

• Default action: edit this file. Surgical. Add the missing line, table

row, or code example where it belongs. No restructuring.

• Only LOGGED is allowed when: the fix needs >10 lines, spans multiple

files, or requires a structural rewrite.

• "I didn't have time" / "it's minor" / "the next agent will figure it out"

are NOT valid reasons.

• The goal: the next agent never has to leave the loader.

2. Log the result.

echo "[$(date -u +%FT%TZ)] now: <what was missing or fixed> [FIXED|LOGGED] action_kind=<kind>" >> state/log/loader-feedback.log

Do not skip this. Every agent run must leave the system better than it found it. The loader is the setpoint; you are the sensor; the gap is the error signal; closing the gap is the correction.

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/now/resources/ui.openui. Read it before rendering or editing this skill's generated component surface.
• Treat this resource as a first-class artifact of the skill, not a generic chat response. Improve it when the skill's user-facing output needs to become richer.
• System resources compose OpenUI primitives and inherit SnappyChat tokens. Use ui_contract: branded in SKILL.md only for deliberate platform or client visuals.