@agent-native/core 0.137.2 → 0.137.4

package/corpus/templates/content/.agents/skills/frontend-design/SKILL.md

@@ -77,7 +77,10 @@ passed this requirement yet.
 
 ## Aesthetic Guidelines
 
-- **Typography**: Use the product's existing type system first. For net-new public pages, choose characterful but readable type and keep sizing appropriate to the surface.
+- **Typography**: Use the product's existing type system first. For SaaS and
+  operational apps, make a clear sans-serif hierarchy the default; reserve a
+  serif or editorial face for a deliberate content preview or brand moment,
+  not the whole application shell.
 - **Color and theme**: Use semantic tokens and CSS variables. Avoid one-note palettes and default purple/blue gradients unless the brand demands them.
 - **Motion**: Prefer purposeful transitions and small state changes. Use CSS transitions/keyframes unless the app already uses a motion library. Never `transition-all` — list the properties that actually change (e.g. `transition-[opacity,transform]`). Use the shared easing tokens defined in `packages/core/src/styles/agent-native.css` instead of hand-typing curves: `var(--ease-drawer)` (260ms, drawers/app chrome), `var(--ease-collapse)` (200ms, expand/collapse), `var(--ease-out-strong)` (snappy entrances) — in Tailwind, `ease-[var(--ease-collapse)]`. Enter/exit with ease-out, never `ease-in`. Overlays that zoom in must set the Radix origin var (e.g. `origin-[--radix-popover-content-transform-origin]`). Animate `transform`/`opacity`, not width/height/padding/box-shadow. Gate looping or large-movement animations with `motion-reduce:`. Command palettes and keyboard-triggered actions get no animation.
 - **Composition**: Match the workflow. Operational apps should be dense and scannable; marketing or portfolio pages can be more immersive.
@@ -115,6 +118,55 @@ passed this requirement yet.
 - Keep UI optimistic where possible: update cache and navigation immediately, then reconcile or roll back on mutation result.
 - Custom styles belong in Tailwind classes, component CSS, or the existing global CSS theme file; avoid inline styles.
 
+### Agent Surface And Page Boundaries
+
+- Treat the domain UI and the agent as two coordinated surfaces. The domain
+  page should make the repeatable job fast; the agent should handle judgment,
+  exploration, and actions that benefit from conversation.
+- Keep domain work on a named domain route such as `/automations`, `/block`, or
+  `/workflow`. Preserve the starter's full-page chat route (`/` or `/chat/*`)
+  when it exists; do not replace it with a domain form while leaving the shell
+  configured as if it were chat.
+- Use the persistent right `AgentSidebar` for contextual AI. A button that
+  sends work to `sendToAgentChat` must open or focus that sidebar and leave the
+  user on the current domain surface. Use full-page chat for chat-first work,
+  not as a hidden transport for a domain button.
+- Keep the left navigation domain-specific. A page called Automations,
+  Block time, or Create deck should not be nested under a generic Chat item;
+  Chat is its own destination and the right rail is the contextual assistant.
+- Never use sparkle, wand, magic, robot, or similar decorative AI icons. Use a
+  familiar message, assistant, or neutral action icon, and let the button copy
+  explain the intent. An icon-only control needs a tooltip and accessible name.
+- Give the persistent agent drawer a quiet but intentional boundary: a subtle
+  surface shift, divider, or both. The sidebar and domain page should not read
+  as one undifferentiated slab, and the treatment should remain calm when the
+  drawer opens or closes.
+- Treat an AI-labeled button as a contract. Buttons named Ask agent, Review
+  with agent, Refine, Generate with AI, or similar must call
+  `sendToAgentChat` with bounded context, `openSidebar: true`, and the intended
+  `submit` mode. A deterministic local action is useful, but label it local,
+  preview, or analyze rather than implying it invoked an agent.
+
+### Product Surface Review
+
+Before shipping a new app or a substantial redesign, review the first viewport
+as an operator would use it repeatedly:
+
+- Show one clear job title, the current state, and one primary next action.
+- Put optional inputs, provider choices, diagnostics, long explanations, and
+  secondary actions behind a disclosure, a later step, a menu, or the agent
+  sidebar. Do not put multiple unrelated forms side by side by default.
+- Prefer a short step flow or a focused page per domain job over one giant
+  dashboard. A route can have several states, but it should reveal one state
+  at a time and preserve the user's progress.
+- Remove generic hero copy, feature tours, repeated helper text, nested cards,
+  status-chip soup, and decorative AI treatment before adding more styling.
+- For review flows, stack the source/original first and the generated or safe
+  result second by default. Use side-by-side comparison only when the content
+  is short enough to scan without excessive horizontal reading.
+- Check the result at the target desktop width and a narrow width. If the first
+  viewport feels like documentation instead of a tool, subtract again.
+
 ## shadcn/ui Design Rules
 
 - Use built-in component variants first (`variant`, `size`) before overriding classes.

package/corpus/templates/crm/.agents/skills/agent-native-toolkit/SKILL.md

@@ -32,6 +32,39 @@ Move behavior into shared toolkit primitives when it is:
 Keep behavior app-local when the abstraction would hide important domain
 language or make a simple app-specific workflow harder to understand.
 
+## Agent Surface Contract
+
+The repeated app shell has two distinct navigation surfaces:
+
+- The left rail owns domain destinations, settings, and chat history when the
+  app has a full-page chat route. Do not label a domain workflow as `Chat` just
+  because the app was scaffolded from the chat template.
+- The right `AgentSidebar` owns contextual agent work. Domain buttons that call
+  `sendToAgentChat` should open it (`openSidebar: true`) so the user can see,
+  steer, and review the agent without losing the page they were using.
+- Keep `/` or `/chat/*` as the full-page chat surface when the starter provides
+  one. Put domain workflows on named routes and wire the shell's route checks,
+  navigation labels, and handoffs to those routes together.
+- Use familiar message or neutral action icons for agent affordances. Never use
+  sparkle, wand, magic, or robot icons as an AI label; the copy should carry the
+  meaning.
+- Give the right rail a quiet visual boundary with a subtle surface shift,
+  divider, or both. The domain page and AgentSidebar should not collapse into a
+  single undifferentiated background.
+- Any button labeled as agent work must use `sendToAgentChat` with bounded
+  context and `openSidebar: true`; local deterministic analysis should be
+  labeled as local, preview, or analyze. For original/generated review, stack
+  the source above the result by default and use side-by-side only for short,
+  highly scannable content.
+- Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
+  context. Match direct assistant-ui pins to the installed core/toolkit peer
+  graph, use Vite dedupe/aliases when linked dependencies can split contexts,
+  and verify an AI handoff produces no stale-index console error.
+
+Contextual agent UI is not a reason to expose every option at once. Start with
+the domain task's primary action, reveal review or configuration only when the
+current state needs it, and let the sidebar carry conversational depth.
+
 ## Discover Before Building
 
 Before creating an app-local version of repeated workspace or agent UI:

package/corpus/templates/crm/app/routes/settings.tsx

@@ -30,7 +30,7 @@ export function meta() {
 }
 
 /**
- * `/settings/<section>` deep links. `connections` is the shared workspace tab
+ * `/settings/<section>` deep links. `integrations` is the shared workspace tab
  * and `connection` is the CRM one, so the segment is matched exactly rather
  * than by substring.
  */
@@ -45,7 +45,7 @@ const SETTINGS_SECTIONS: readonly string[] = [
 
 function sectionFromPath(pathname: string): string {
   const section = pathname.split("/settings/")[1]?.split("/")[0] ?? "";
-  return SETTINGS_SECTIONS.includes(section) ? section : "general";
+  return SETTINGS_SECTIONS.includes(section) ? section : "integrations";
 }
 
 export default function SettingsRoute() {

package/corpus/templates/design/.agents/skills/agent-native-toolkit/SKILL.md

@@ -32,6 +32,39 @@ Move behavior into shared toolkit primitives when it is:
 Keep behavior app-local when the abstraction would hide important domain
 language or make a simple app-specific workflow harder to understand.
 
+## Agent Surface Contract
+
+The repeated app shell has two distinct navigation surfaces:
+
+- The left rail owns domain destinations, settings, and chat history when the
+  app has a full-page chat route. Do not label a domain workflow as `Chat` just
+  because the app was scaffolded from the chat template.
+- The right `AgentSidebar` owns contextual agent work. Domain buttons that call
+  `sendToAgentChat` should open it (`openSidebar: true`) so the user can see,
+  steer, and review the agent without losing the page they were using.
+- Keep `/` or `/chat/*` as the full-page chat surface when the starter provides
+  one. Put domain workflows on named routes and wire the shell's route checks,
+  navigation labels, and handoffs to those routes together.
+- Use familiar message or neutral action icons for agent affordances. Never use
+  sparkle, wand, magic, or robot icons as an AI label; the copy should carry the
+  meaning.
+- Give the right rail a quiet visual boundary with a subtle surface shift,
+  divider, or both. The domain page and AgentSidebar should not collapse into a
+  single undifferentiated background.
+- Any button labeled as agent work must use `sendToAgentChat` with bounded
+  context and `openSidebar: true`; local deterministic analysis should be
+  labeled as local, preview, or analyze. For original/generated review, stack
+  the source above the result by default and use side-by-side only for short,
+  highly scannable content.
+- Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
+  context. Match direct assistant-ui pins to the installed core/toolkit peer
+  graph, use Vite dedupe/aliases when linked dependencies can split contexts,
+  and verify an AI handoff produces no stale-index console error.
+
+Contextual agent UI is not a reason to expose every option at once. Start with
+the domain task's primary action, reveal review or configuration only when the
+current state needs it, and let the sidebar carry conversational depth.
+
 ## Discover Before Building
 
 Before creating an app-local version of repeated workspace or agent UI:

package/corpus/templates/design/.agents/skills/frontend-design/SKILL.md

@@ -77,7 +77,10 @@ passed this requirement yet.
 
 ## Aesthetic Guidelines
 
-- **Typography**: Use the product's existing type system first. For net-new public pages, choose characterful but readable type and keep sizing appropriate to the surface.
+- **Typography**: Use the product's existing type system first. For SaaS and
+  operational apps, make a clear sans-serif hierarchy the default; reserve a
+  serif or editorial face for a deliberate content preview or brand moment,
+  not the whole application shell.
 - **Color and theme**: Use semantic tokens and CSS variables. Avoid one-note palettes and default purple/blue gradients unless the brand demands them.
 - **Motion**: Prefer purposeful transitions and small state changes. Use CSS transitions/keyframes unless the app already uses a motion library. Never `transition-all` — list the properties that actually change (e.g. `transition-[opacity,transform]`). Use the shared easing tokens defined in `packages/core/src/styles/agent-native.css` instead of hand-typing curves: `var(--ease-drawer)` (260ms, drawers/app chrome), `var(--ease-collapse)` (200ms, expand/collapse), `var(--ease-out-strong)` (snappy entrances) — in Tailwind, `ease-[var(--ease-collapse)]`. Enter/exit with ease-out, never `ease-in`. Overlays that zoom in must set the Radix origin var (e.g. `origin-[--radix-popover-content-transform-origin]`). Animate `transform`/`opacity`, not width/height/padding/box-shadow. Gate looping or large-movement animations with `motion-reduce:`. Command palettes and keyboard-triggered actions get no animation.
 - **Composition**: Match the workflow. Operational apps should be dense and scannable; marketing or portfolio pages can be more immersive.
@@ -115,6 +118,55 @@ passed this requirement yet.
 - Keep UI optimistic where possible: update cache and navigation immediately, then reconcile or roll back on mutation result.
 - Custom styles belong in Tailwind classes, component CSS, or the existing global CSS theme file; avoid inline styles.
 
+### Agent Surface And Page Boundaries
+
+- Treat the domain UI and the agent as two coordinated surfaces. The domain
+  page should make the repeatable job fast; the agent should handle judgment,
+  exploration, and actions that benefit from conversation.
+- Keep domain work on a named domain route such as `/automations`, `/block`, or
+  `/workflow`. Preserve the starter's full-page chat route (`/` or `/chat/*`)
+  when it exists; do not replace it with a domain form while leaving the shell
+  configured as if it were chat.
+- Use the persistent right `AgentSidebar` for contextual AI. A button that
+  sends work to `sendToAgentChat` must open or focus that sidebar and leave the
+  user on the current domain surface. Use full-page chat for chat-first work,
+  not as a hidden transport for a domain button.
+- Keep the left navigation domain-specific. A page called Automations,
+  Block time, or Create deck should not be nested under a generic Chat item;
+  Chat is its own destination and the right rail is the contextual assistant.
+- Never use sparkle, wand, magic, robot, or similar decorative AI icons. Use a
+  familiar message, assistant, or neutral action icon, and let the button copy
+  explain the intent. An icon-only control needs a tooltip and accessible name.
+- Give the persistent agent drawer a quiet but intentional boundary: a subtle
+  surface shift, divider, or both. The sidebar and domain page should not read
+  as one undifferentiated slab, and the treatment should remain calm when the
+  drawer opens or closes.
+- Treat an AI-labeled button as a contract. Buttons named Ask agent, Review
+  with agent, Refine, Generate with AI, or similar must call
+  `sendToAgentChat` with bounded context, `openSidebar: true`, and the intended
+  `submit` mode. A deterministic local action is useful, but label it local,
+  preview, or analyze rather than implying it invoked an agent.
+
+### Product Surface Review
+
+Before shipping a new app or a substantial redesign, review the first viewport
+as an operator would use it repeatedly:
+
+- Show one clear job title, the current state, and one primary next action.
+- Put optional inputs, provider choices, diagnostics, long explanations, and
+  secondary actions behind a disclosure, a later step, a menu, or the agent
+  sidebar. Do not put multiple unrelated forms side by side by default.
+- Prefer a short step flow or a focused page per domain job over one giant
+  dashboard. A route can have several states, but it should reveal one state
+  at a time and preserve the user's progress.
+- Remove generic hero copy, feature tours, repeated helper text, nested cards,
+  status-chip soup, and decorative AI treatment before adding more styling.
+- For review flows, stack the source/original first and the generated or safe
+  result second by default. Use side-by-side comparison only when the content
+  is short enough to scan without excessive horizontal reading.
+- Check the result at the target desktop width and a narrow width. If the first
+  viewport feels like documentation instead of a tool, subtract again.
+
 ## shadcn/ui Design Rules
 
 - Use built-in component variants first (`variant`, `size`) before overriding classes.

package/corpus/templates/design/actions/import-figma-clipboard.ts

@@ -34,7 +34,7 @@ const AMBIGUOUS_GUIDANCE =
   'Couldn\'t confidently match this paste to specific Figma nodes, so nothing was imported from the API. Paste a frame LINK instead (copy the frame in Figma, then "Copy link to selection") for an exact node import — or continue with the clipboard preview below.';
 
 const KEY_MISSING_GUIDANCE =
-  "Connect your Figma access token (Settings > Connections > Figma access token) to import this paste as exact, editable Figma nodes.";
+  "Connect your Figma access token (Settings > Integrations > API keys) to import this paste as exact, editable Figma nodes.";
 const SELECTION_TRUNCATED_GUIDANCE =
   "Figma copied more than 100 selected nodes. Imported the first 100; split larger selections into smaller pastes so every layer is included.";
 

package/corpus/templates/dispatch/.agents/skills/agent-native-toolkit/SKILL.md

@@ -32,6 +32,39 @@ Move behavior into shared toolkit primitives when it is:
 Keep behavior app-local when the abstraction would hide important domain
 language or make a simple app-specific workflow harder to understand.
 
+## Agent Surface Contract
+
+The repeated app shell has two distinct navigation surfaces:
+
+- The left rail owns domain destinations, settings, and chat history when the
+  app has a full-page chat route. Do not label a domain workflow as `Chat` just
+  because the app was scaffolded from the chat template.
+- The right `AgentSidebar` owns contextual agent work. Domain buttons that call
+  `sendToAgentChat` should open it (`openSidebar: true`) so the user can see,
+  steer, and review the agent without losing the page they were using.
+- Keep `/` or `/chat/*` as the full-page chat surface when the starter provides
+  one. Put domain workflows on named routes and wire the shell's route checks,
+  navigation labels, and handoffs to those routes together.
+- Use familiar message or neutral action icons for agent affordances. Never use
+  sparkle, wand, magic, or robot icons as an AI label; the copy should carry the
+  meaning.
+- Give the right rail a quiet visual boundary with a subtle surface shift,
+  divider, or both. The domain page and AgentSidebar should not collapse into a
+  single undifferentiated background.
+- Any button labeled as agent work must use `sendToAgentChat` with bounded
+  context and `openSidebar: true`; local deterministic analysis should be
+  labeled as local, preview, or analyze. For original/generated review, stack
+  the source above the result by default and use side-by-side only for short,
+  highly scannable content.
+- Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
+  context. Match direct assistant-ui pins to the installed core/toolkit peer
+  graph, use Vite dedupe/aliases when linked dependencies can split contexts,
+  and verify an AI handoff produces no stale-index console error.
+
+Contextual agent UI is not a reason to expose every option at once. Start with
+the domain task's primary action, reveal review or configuration only when the
+current state needs it, and let the sidebar carry conversational depth.
+
 ## Discover Before Building
 
 Before creating an app-local version of repeated workspace or agent UI:

package/corpus/templates/dispatch/.agents/skills/frontend-design/SKILL.md

@@ -77,7 +77,10 @@ passed this requirement yet.
 
 ## Aesthetic Guidelines
 
-- **Typography**: Use the product's existing type system first. For net-new public pages, choose characterful but readable type and keep sizing appropriate to the surface.
+- **Typography**: Use the product's existing type system first. For SaaS and
+  operational apps, make a clear sans-serif hierarchy the default; reserve a
+  serif or editorial face for a deliberate content preview or brand moment,
+  not the whole application shell.
 - **Color and theme**: Use semantic tokens and CSS variables. Avoid one-note palettes and default purple/blue gradients unless the brand demands them.
 - **Motion**: Prefer purposeful transitions and small state changes. Use CSS transitions/keyframes unless the app already uses a motion library. Never `transition-all` — list the properties that actually change (e.g. `transition-[opacity,transform]`). Use the shared easing tokens defined in `packages/core/src/styles/agent-native.css` instead of hand-typing curves: `var(--ease-drawer)` (260ms, drawers/app chrome), `var(--ease-collapse)` (200ms, expand/collapse), `var(--ease-out-strong)` (snappy entrances) — in Tailwind, `ease-[var(--ease-collapse)]`. Enter/exit with ease-out, never `ease-in`. Overlays that zoom in must set the Radix origin var (e.g. `origin-[--radix-popover-content-transform-origin]`). Animate `transform`/`opacity`, not width/height/padding/box-shadow. Gate looping or large-movement animations with `motion-reduce:`. Command palettes and keyboard-triggered actions get no animation.
 - **Composition**: Match the workflow. Operational apps should be dense and scannable; marketing or portfolio pages can be more immersive.
@@ -115,6 +118,55 @@ passed this requirement yet.
 - Keep UI optimistic where possible: update cache and navigation immediately, then reconcile or roll back on mutation result.
 - Custom styles belong in Tailwind classes, component CSS, or the existing global CSS theme file; avoid inline styles.
 
+### Agent Surface And Page Boundaries
+
+- Treat the domain UI and the agent as two coordinated surfaces. The domain
+  page should make the repeatable job fast; the agent should handle judgment,
+  exploration, and actions that benefit from conversation.
+- Keep domain work on a named domain route such as `/automations`, `/block`, or
+  `/workflow`. Preserve the starter's full-page chat route (`/` or `/chat/*`)
+  when it exists; do not replace it with a domain form while leaving the shell
+  configured as if it were chat.
+- Use the persistent right `AgentSidebar` for contextual AI. A button that
+  sends work to `sendToAgentChat` must open or focus that sidebar and leave the
+  user on the current domain surface. Use full-page chat for chat-first work,
+  not as a hidden transport for a domain button.
+- Keep the left navigation domain-specific. A page called Automations,
+  Block time, or Create deck should not be nested under a generic Chat item;
+  Chat is its own destination and the right rail is the contextual assistant.
+- Never use sparkle, wand, magic, robot, or similar decorative AI icons. Use a
+  familiar message, assistant, or neutral action icon, and let the button copy
+  explain the intent. An icon-only control needs a tooltip and accessible name.
+- Give the persistent agent drawer a quiet but intentional boundary: a subtle
+  surface shift, divider, or both. The sidebar and domain page should not read
+  as one undifferentiated slab, and the treatment should remain calm when the
+  drawer opens or closes.
+- Treat an AI-labeled button as a contract. Buttons named Ask agent, Review
+  with agent, Refine, Generate with AI, or similar must call
+  `sendToAgentChat` with bounded context, `openSidebar: true`, and the intended
+  `submit` mode. A deterministic local action is useful, but label it local,
+  preview, or analyze rather than implying it invoked an agent.
+
+### Product Surface Review
+
+Before shipping a new app or a substantial redesign, review the first viewport
+as an operator would use it repeatedly:
+
+- Show one clear job title, the current state, and one primary next action.
+- Put optional inputs, provider choices, diagnostics, long explanations, and
+  secondary actions behind a disclosure, a later step, a menu, or the agent
+  sidebar. Do not put multiple unrelated forms side by side by default.
+- Prefer a short step flow or a focused page per domain job over one giant
+  dashboard. A route can have several states, but it should reveal one state
+  at a time and preserve the user's progress.
+- Remove generic hero copy, feature tours, repeated helper text, nested cards,
+  status-chip soup, and decorative AI treatment before adding more styling.
+- For review flows, stack the source/original first and the generated or safe
+  result second by default. Use side-by-side comparison only when the content
+  is short enough to scan without excessive horizontal reading.
+- Check the result at the target desktop width and a narrow width. If the first
+  viewport feels like documentation instead of a tool, subtract again.
+
 ## shadcn/ui Design Rules
 
 - Use built-in component variants first (`variant`, `size`) before overriding classes.

package/corpus/templates/dispatch/changelog/2026-08-04-dispatch-keeps-connected-chats-out-of-local-history-by-defau.md

@@ -0,0 +1,6 @@
+---
+type: improved
+date: 2026-08-04
+---
+
+Dispatch keeps connected chats out of local history by default and lets you show all sources on demand.

package/corpus/templates/factory/.agents/skills/agent-native-toolkit/SKILL.md

@@ -32,6 +32,39 @@ Move behavior into shared toolkit primitives when it is:
 Keep behavior app-local when the abstraction would hide important domain
 language or make a simple app-specific workflow harder to understand.
 
+## Agent Surface Contract
+
+The repeated app shell has two distinct navigation surfaces:
+
+- The left rail owns domain destinations, settings, and chat history when the
+  app has a full-page chat route. Do not label a domain workflow as `Chat` just
+  because the app was scaffolded from the chat template.
+- The right `AgentSidebar` owns contextual agent work. Domain buttons that call
+  `sendToAgentChat` should open it (`openSidebar: true`) so the user can see,
+  steer, and review the agent without losing the page they were using.
+- Keep `/` or `/chat/*` as the full-page chat surface when the starter provides
+  one. Put domain workflows on named routes and wire the shell's route checks,
+  navigation labels, and handoffs to those routes together.
+- Use familiar message or neutral action icons for agent affordances. Never use
+  sparkle, wand, magic, or robot icons as an AI label; the copy should carry the
+  meaning.
+- Give the right rail a quiet visual boundary with a subtle surface shift,
+  divider, or both. The domain page and AgentSidebar should not collapse into a
+  single undifferentiated background.
+- Any button labeled as agent work must use `sendToAgentChat` with bounded
+  context and `openSidebar: true`; local deterministic analysis should be
+  labeled as local, preview, or analyze. For original/generated review, stack
+  the source above the result by default and use side-by-side only for short,
+  highly scannable content.
+- Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
+  context. Match direct assistant-ui pins to the installed core/toolkit peer
+  graph, use Vite dedupe/aliases when linked dependencies can split contexts,
+  and verify an AI handoff produces no stale-index console error.
+
+Contextual agent UI is not a reason to expose every option at once. Start with
+the domain task's primary action, reveal review or configuration only when the
+current state needs it, and let the sidebar carry conversational depth.
+
 ## Discover Before Building
 
 Before creating an app-local version of repeated workspace or agent UI:

package/corpus/templates/factory/.agents/skills/frontend-design/SKILL.md

@@ -77,7 +77,10 @@ passed this requirement yet.
 
 ## Aesthetic Guidelines
 
-- **Typography**: Use the product's existing type system first. For net-new public pages, choose characterful but readable type and keep sizing appropriate to the surface.
+- **Typography**: Use the product's existing type system first. For SaaS and
+  operational apps, make a clear sans-serif hierarchy the default; reserve a
+  serif or editorial face for a deliberate content preview or brand moment,
+  not the whole application shell.
 - **Color and theme**: Use semantic tokens and CSS variables. Avoid one-note palettes and default purple/blue gradients unless the brand demands them.
 - **Motion**: Prefer purposeful transitions and small state changes. Use CSS transitions/keyframes unless the app already uses a motion library. Never `transition-all` — list the properties that actually change (e.g. `transition-[opacity,transform]`). Use the shared easing tokens defined in `packages/core/src/styles/agent-native.css` instead of hand-typing curves: `var(--ease-drawer)` (260ms, drawers/app chrome), `var(--ease-collapse)` (200ms, expand/collapse), `var(--ease-out-strong)` (snappy entrances) — in Tailwind, `ease-[var(--ease-collapse)]`. Enter/exit with ease-out, never `ease-in`. Overlays that zoom in must set the Radix origin var (e.g. `origin-[--radix-popover-content-transform-origin]`). Animate `transform`/`opacity`, not width/height/padding/box-shadow. Gate looping or large-movement animations with `motion-reduce:`. Command palettes and keyboard-triggered actions get no animation.
 - **Composition**: Match the workflow. Operational apps should be dense and scannable; marketing or portfolio pages can be more immersive.
@@ -115,6 +118,55 @@ passed this requirement yet.
 - Keep UI optimistic where possible: update cache and navigation immediately, then reconcile or roll back on mutation result.
 - Custom styles belong in Tailwind classes, component CSS, or the existing global CSS theme file; avoid inline styles.
 
+### Agent Surface And Page Boundaries
+
+- Treat the domain UI and the agent as two coordinated surfaces. The domain
+  page should make the repeatable job fast; the agent should handle judgment,
+  exploration, and actions that benefit from conversation.
+- Keep domain work on a named domain route such as `/automations`, `/block`, or
+  `/workflow`. Preserve the starter's full-page chat route (`/` or `/chat/*`)
+  when it exists; do not replace it with a domain form while leaving the shell
+  configured as if it were chat.
+- Use the persistent right `AgentSidebar` for contextual AI. A button that
+  sends work to `sendToAgentChat` must open or focus that sidebar and leave the
+  user on the current domain surface. Use full-page chat for chat-first work,
+  not as a hidden transport for a domain button.
+- Keep the left navigation domain-specific. A page called Automations,
+  Block time, or Create deck should not be nested under a generic Chat item;
+  Chat is its own destination and the right rail is the contextual assistant.
+- Never use sparkle, wand, magic, robot, or similar decorative AI icons. Use a
+  familiar message, assistant, or neutral action icon, and let the button copy
+  explain the intent. An icon-only control needs a tooltip and accessible name.
+- Give the persistent agent drawer a quiet but intentional boundary: a subtle
+  surface shift, divider, or both. The sidebar and domain page should not read
+  as one undifferentiated slab, and the treatment should remain calm when the
+  drawer opens or closes.
+- Treat an AI-labeled button as a contract. Buttons named Ask agent, Review
+  with agent, Refine, Generate with AI, or similar must call
+  `sendToAgentChat` with bounded context, `openSidebar: true`, and the intended
+  `submit` mode. A deterministic local action is useful, but label it local,
+  preview, or analyze rather than implying it invoked an agent.
+
+### Product Surface Review
+
+Before shipping a new app or a substantial redesign, review the first viewport
+as an operator would use it repeatedly:
+
+- Show one clear job title, the current state, and one primary next action.
+- Put optional inputs, provider choices, diagnostics, long explanations, and
+  secondary actions behind a disclosure, a later step, a menu, or the agent
+  sidebar. Do not put multiple unrelated forms side by side by default.
+- Prefer a short step flow or a focused page per domain job over one giant
+  dashboard. A route can have several states, but it should reveal one state
+  at a time and preserve the user's progress.
+- Remove generic hero copy, feature tours, repeated helper text, nested cards,
+  status-chip soup, and decorative AI treatment before adding more styling.
+- For review flows, stack the source/original first and the generated or safe
+  result second by default. Use side-by-side comparison only when the content
+  is short enough to scan without excessive horizontal reading.
+- Check the result at the target desktop width and a narrow width. If the first
+  viewport feels like documentation instead of a tool, subtract again.
+
 ## shadcn/ui Design Rules
 
 - Use built-in component variants first (`variant`, `size`) before overriding classes.

package/corpus/templates/factory/README.md

@@ -35,7 +35,7 @@ finds that existing organization and seeds its organization-owned automations.
 If Dispatch synced the vault into a different organization, set
 `AGENT_VAULT_ORG_ID` to that existing org id instead of creating a new org.
 
-Connect Slack in Dispatch or in Settings -> Connections. Factory resolves
+Connect Slack in Dispatch or in Settings -> Integrations. Factory resolves
 Slack, GitHub, Sentry, and Builder credentials from the shared workspace vault
 and only uses matching deployment env vars as a last-resort fallback. All apps
 that read shared `app_secrets` rows must use the same

package/corpus/templates/forms/.agents/skills/agent-native-toolkit/SKILL.md

@@ -32,6 +32,39 @@ Move behavior into shared toolkit primitives when it is:
 Keep behavior app-local when the abstraction would hide important domain
 language or make a simple app-specific workflow harder to understand.
 
+## Agent Surface Contract
+
+The repeated app shell has two distinct navigation surfaces:
+
+- The left rail owns domain destinations, settings, and chat history when the
+  app has a full-page chat route. Do not label a domain workflow as `Chat` just
+  because the app was scaffolded from the chat template.
+- The right `AgentSidebar` owns contextual agent work. Domain buttons that call
+  `sendToAgentChat` should open it (`openSidebar: true`) so the user can see,
+  steer, and review the agent without losing the page they were using.
+- Keep `/` or `/chat/*` as the full-page chat surface when the starter provides
+  one. Put domain workflows on named routes and wire the shell's route checks,
+  navigation labels, and handoffs to those routes together.
+- Use familiar message or neutral action icons for agent affordances. Never use
+  sparkle, wand, magic, or robot icons as an AI label; the copy should carry the
+  meaning.
+- Give the right rail a quiet visual boundary with a subtle surface shift,
+  divider, or both. The domain page and AgentSidebar should not collapse into a
+  single undifferentiated background.
+- Any button labeled as agent work must use `sendToAgentChat` with bounded
+  context and `openSidebar: true`; local deterministic analysis should be
+  labeled as local, preview, or analyze. For original/generated review, stack
+  the source above the result by default and use side-by-side only for short,
+  highly scannable content.
+- Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
+  context. Match direct assistant-ui pins to the installed core/toolkit peer
+  graph, use Vite dedupe/aliases when linked dependencies can split contexts,
+  and verify an AI handoff produces no stale-index console error.
+
+Contextual agent UI is not a reason to expose every option at once. Start with
+the domain task's primary action, reveal review or configuration only when the
+current state needs it, and let the sidebar carry conversational depth.
+
 ## Discover Before Building
 
 Before creating an app-local version of repeated workspace or agent UI:

package/corpus/templates/forms/.agents/skills/frontend-design/SKILL.md

@@ -77,7 +77,10 @@ passed this requirement yet.
 
 ## Aesthetic Guidelines
 
-- **Typography**: Use the product's existing type system first. For net-new public pages, choose characterful but readable type and keep sizing appropriate to the surface.
+- **Typography**: Use the product's existing type system first. For SaaS and
+  operational apps, make a clear sans-serif hierarchy the default; reserve a
+  serif or editorial face for a deliberate content preview or brand moment,
+  not the whole application shell.
 - **Color and theme**: Use semantic tokens and CSS variables. Avoid one-note palettes and default purple/blue gradients unless the brand demands them.
 - **Motion**: Prefer purposeful transitions and small state changes. Use CSS transitions/keyframes unless the app already uses a motion library. Never `transition-all` — list the properties that actually change (e.g. `transition-[opacity,transform]`). Use the shared easing tokens defined in `packages/core/src/styles/agent-native.css` instead of hand-typing curves: `var(--ease-drawer)` (260ms, drawers/app chrome), `var(--ease-collapse)` (200ms, expand/collapse), `var(--ease-out-strong)` (snappy entrances) — in Tailwind, `ease-[var(--ease-collapse)]`. Enter/exit with ease-out, never `ease-in`. Overlays that zoom in must set the Radix origin var (e.g. `origin-[--radix-popover-content-transform-origin]`). Animate `transform`/`opacity`, not width/height/padding/box-shadow. Gate looping or large-movement animations with `motion-reduce:`. Command palettes and keyboard-triggered actions get no animation.
 - **Composition**: Match the workflow. Operational apps should be dense and scannable; marketing or portfolio pages can be more immersive.
@@ -115,6 +118,55 @@ passed this requirement yet.
 - Keep UI optimistic where possible: update cache and navigation immediately, then reconcile or roll back on mutation result.
 - Custom styles belong in Tailwind classes, component CSS, or the existing global CSS theme file; avoid inline styles.
 
+### Agent Surface And Page Boundaries
+
+- Treat the domain UI and the agent as two coordinated surfaces. The domain
+  page should make the repeatable job fast; the agent should handle judgment,
+  exploration, and actions that benefit from conversation.
+- Keep domain work on a named domain route such as `/automations`, `/block`, or
+  `/workflow`. Preserve the starter's full-page chat route (`/` or `/chat/*`)
+  when it exists; do not replace it with a domain form while leaving the shell
+  configured as if it were chat.
+- Use the persistent right `AgentSidebar` for contextual AI. A button that
+  sends work to `sendToAgentChat` must open or focus that sidebar and leave the
+  user on the current domain surface. Use full-page chat for chat-first work,
+  not as a hidden transport for a domain button.
+- Keep the left navigation domain-specific. A page called Automations,
+  Block time, or Create deck should not be nested under a generic Chat item;
+  Chat is its own destination and the right rail is the contextual assistant.
+- Never use sparkle, wand, magic, robot, or similar decorative AI icons. Use a
+  familiar message, assistant, or neutral action icon, and let the button copy
+  explain the intent. An icon-only control needs a tooltip and accessible name.
+- Give the persistent agent drawer a quiet but intentional boundary: a subtle
+  surface shift, divider, or both. The sidebar and domain page should not read
+  as one undifferentiated slab, and the treatment should remain calm when the
+  drawer opens or closes.
+- Treat an AI-labeled button as a contract. Buttons named Ask agent, Review
+  with agent, Refine, Generate with AI, or similar must call
+  `sendToAgentChat` with bounded context, `openSidebar: true`, and the intended
+  `submit` mode. A deterministic local action is useful, but label it local,
+  preview, or analyze rather than implying it invoked an agent.
+
+### Product Surface Review
+
+Before shipping a new app or a substantial redesign, review the first viewport
+as an operator would use it repeatedly:
+
+- Show one clear job title, the current state, and one primary next action.
+- Put optional inputs, provider choices, diagnostics, long explanations, and
+  secondary actions behind a disclosure, a later step, a menu, or the agent
+  sidebar. Do not put multiple unrelated forms side by side by default.
+- Prefer a short step flow or a focused page per domain job over one giant
+  dashboard. A route can have several states, but it should reveal one state
+  at a time and preserve the user's progress.
+- Remove generic hero copy, feature tours, repeated helper text, nested cards,
+  status-chip soup, and decorative AI treatment before adding more styling.
+- For review flows, stack the source/original first and the generated or safe
+  result second by default. Use side-by-side comparison only when the content
+  is short enough to scan without excessive horizontal reading.
+- Check the result at the target desktop width and a narrow width. If the first
+  viewport feels like documentation instead of a tool, subtract again.
+
 ## shadcn/ui Design Rules
 
 - Use built-in component variants first (`variant`, `size`) before overriding classes.

package/corpus/templates/macros/.agents/skills/agent-native-toolkit/SKILL.md

@@ -32,6 +32,39 @@ Move behavior into shared toolkit primitives when it is:
 Keep behavior app-local when the abstraction would hide important domain
 language or make a simple app-specific workflow harder to understand.
 
+## Agent Surface Contract
+
+The repeated app shell has two distinct navigation surfaces:
+
+- The left rail owns domain destinations, settings, and chat history when the
+  app has a full-page chat route. Do not label a domain workflow as `Chat` just
+  because the app was scaffolded from the chat template.
+- The right `AgentSidebar` owns contextual agent work. Domain buttons that call
+  `sendToAgentChat` should open it (`openSidebar: true`) so the user can see,
+  steer, and review the agent without losing the page they were using.
+- Keep `/` or `/chat/*` as the full-page chat surface when the starter provides
+  one. Put domain workflows on named routes and wire the shell's route checks,
+  navigation labels, and handoffs to those routes together.
+- Use familiar message or neutral action icons for agent affordances. Never use
+  sparkle, wand, magic, or robot icons as an AI label; the copy should carry the
+  meaning.
+- Give the right rail a quiet visual boundary with a subtle surface shift,
+  divider, or both. The domain page and AgentSidebar should not collapse into a
+  single undifferentiated background.
+- Any button labeled as agent work must use `sendToAgentChat` with bounded
+  context and `openSidebar: true`; local deterministic analysis should be
+  labeled as local, preview, or analyze. For original/generated review, stack
+  the source above the result by default and use side-by-side only for short,
+  highly scannable content.
+- Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
+  context. Match direct assistant-ui pins to the installed core/toolkit peer
+  graph, use Vite dedupe/aliases when linked dependencies can split contexts,
+  and verify an AI handoff produces no stale-index console error.
+
+Contextual agent UI is not a reason to expose every option at once. Start with
+the domain task's primary action, reveal review or configuration only when the
+current state needs it, and let the sidebar carry conversational depth.
+
 ## Discover Before Building
 
 Before creating an app-local version of repeated workspace or agent UI: