@design-intelligence/ghost 0.20.0 → 0.22.0

package/dist/init-payloads/median/median-tells.md

@@ -0,0 +1,117 @@
+---
+name: Median tells
+description: Flags the measured defaults of unsteered generation, the deterministic floor, and current model-signature tells — hover-lift, default accents, unprompted dark theme, gradient text, contrast, frequency tells, and per-model signatures.
+severity: high
+references:
+  - cliche.median > Hover-lift
+  - cliche.median > Indigo accent
+  - cliche.median > Dark theme
+  - cliche.median > Gradients
+  - cliche.median > Glassmorphism
+  - cliche.median > Side-stripe
+  - cliche.median > Cream surface
+  - cliche.median > Chat bubbles
+  - cliche.median > Stock copy
+  - cliche.median > Celebration
+  - cliche.median > Hero metric
+  - cliche.median > Eyebrow kicker
+---
+
+These flags target the measured convergence patterns of unsteered model
+generation, the deterministic floor the median node licenses, and tells
+specific to individual models. Each is mechanically detectable in a diff.
+Pruning a rule from `cliche.median` orphans its paired reference here —
+`ghost validate` warns; delete the flag and its reference together.
+
+Flag `transform` with `translateY` inside a `:hover` rule on cards,
+buttons, or list items, especially paired with a shadow increase. Hover
+confirmation in this fingerprint is color and background change, not lift.
+(`cliche.median > Hover-lift`)
+
+Flag accent values in the indigo/blue/purple default family (`#4f46e5`,
+`#6366f1`, `#2563eb`, `#3b82f6`, `#8b5cf6`, and close neighbors)
+unless the diff shows the user asked for them. They are model defaults, not
+palette members. (`cliche.median > Indigo accent`)
+
+Flag whole-page dark backgrounds when the ask did not request dark mode.
+Dark surfaces are a declared brand choice or an explicit theme, never an
+unprompted default. (`cliche.median > Dark theme`)
+
+Flag `linear-gradient` or `radial-gradient` as page or section
+backgrounds, and gradient-filled buttons. (`cliche.median > Gradients`)
+
+Flag `backdrop-filter: blur` used for glassmorphism cards.
+(`cliche.median > Glassmorphism`)
+
+Flag `background-clip: text` (with or without the `-webkit-` prefix)
+paired with a gradient. Emphasis comes from weight or size in a single
+solid color.
+
+Flag a thick colored border on one side of an element (`border-left` or a
+`border-l-*` utility at 2px or more in a non-neutral color) while the
+other sides stay thin. (`cliche.median > Side-stripe`)
+
+Flag warm off-white page backgrounds in the cream/sand/beige band, and token
+names like `--cream`, `--sand`, `--parchment`, `--linen` introduced
+by the diff. (`cliche.median > Cream surface`)
+
+Flag assistant messages rendered as bubbles with initials-circle avatars.
+(`cliche.median > Chat bubbles`)
+
+Flag emoji used as icons or imagery in interface chrome. Text labels carry
+meaning.
+
+Flag stock template copy in headings: "Simple, transparent pricing",
+"Welcome back", and interchangeable-with-a-competitor phrasing. Recommend
+copy that states what this product specifically does.
+(`cliche.median > Stock copy`)
+
+Flag exclamation-marked success copy, confetti language, and celebratory UI
+("You did it!", "Awesome!"). Confirmation is quiet and factual.
+(`cliche.median > Celebration`)
+
+Flag the hero-metric template — a big number, small label, and supporting
+stats as default proof — unless the metric shows real user data. Recommend
+evidence specific to the product, or nothing.
+(`cliche.median > Hero metric`)
+
+Deterministic floor — licensed by the median node, verified here, never
+steered in prose:
+
+Flag text/background pairs below WCAG AA contrast: 4.5:1 for body text,
+3:1 for large text (24px and up, or 18.7px bold and up). Check the worst
+stop when the background is a gradient.
+
+Flag animation or transition without a `prefers-reduced-motion: reduce`
+alternative — a crossfade or instant state change.
+
+Flag ad-hoc z-index values (`999`, `9999`, or any value outside a
+declared scale). Layering wants a semantic scale, not an arms race.
+
+Flag `cubic-bezier` easings whose control points overshoot the 0–1 range,
+and keyframe names matching bounce, elastic, wobble, or jiggle.
+
+Frequency tells — the crime is repetition, not the move (advisory):
+
+Flag three or more uppercase, tracked eyebrow kickers above section headings
+in one page. One named kicker is voice; a kicker on every section is model
+grammar. (`cliche.median > Eyebrow kicker`)
+
+Flag five or more em-dashes in body copy in one view.
+
+Flag three or more instances of the aphoristic rebuttal cadence ("Not X. Y."
+/ "Sentence. No qualifiers.") in one page's copy.
+
+Model-signature tells — skip any block whose model did not produce the diff
+(advisory):
+
+Codex: flag a 1px border paired with a box-shadow of 16px blur or more on
+the same element — pick a solid border or a tight shadow, not both. Flag
+border-radius of 32px or more on cards, sections, or inputs unless an
+answered shape dial (`signature.shape`) sanctions large radii — then it is
+fidelity, not a tell. Flag 1px linear-gradient grid or repeating-stripe
+backgrounds used as decoration.
+
+Gemini: flag `transform` (scale, rotate, translate) on `img` inside a
+`:hover` rule, including group-hover utilities targeting a child image.
+Animate the card's background, border, or shadow instead.

package/dist/init-payloads/skeleton/brand.md

@@ -0,0 +1,22 @@
+---
+description: "The brand on one page — always in context; what this brand is, how it feels, and what only it refuses."
+---
+
+This cover is unwritten. It is the one page always in an agent's context, so
+it carries only what cannot be retrieved by task: what this brand is about,
+in one paragraph, in the brand's own voice. The temperature its words and
+motion share. And the refusals only this brand makes — not generic don'ts
+(those live in each foundation's misuse list, and the model's cliches live
+in the cliche nodes), but the lines this brand alone draws.
+
+Until a human writes it, the working stance is: quiet, precise, content
+first, decoration never. Treat that as provisional and say so in your
+report.
+
+One test admits a sentence to this page: where would a violation show? In a
+single element, it belongs in that element's chapter. In a single view, it
+belongs in the composition foundation. Only across the whole body of work —
+temperature, density, restraint — it belongs here.
+
+The budget is one screen. When this page is real, delete every sentence of
+scaffolding above — including this one.

package/dist/init-payloads/skeleton/context.conversation.md

@@ -0,0 +1,24 @@
+---
+description: "AI conversation threads — assistant text on the page surface, compact user turns, collapsed tool calls, one structured prompt input. Read only for chat threads, agent consoles, and prompt composers."
+---
+
+In this context: AI conversation threads, agent consoles, review assistants,
+and prompt composers. Elsewhere, the defaults hold.
+
+Conversation UI is not chat cosplay. The assistant speaks on the page
+surface as plain text: no bubble, no border, no fill. Wrapping assistant
+messages in cards makes the system look defensive and wastes density —
+hierarchy comes from prose, spacing, and type.
+
+User turns are compact muted surfaces aligned right. They mark authorship
+without turning the thread into alternating balloons.
+
+Tool calls are operational evidence. Collapse them to a labeled one-line
+summary with status; expand only when the user asks, then show mono content
+inside the disclosed area.
+
+The prompt input is one bordered surface. The textarea stays empty of
+controls so writing remains the focus; attachments, model choice, and send
+live in a single row below it. There is one primary send action — stop and
+send are mutually exclusive states of the same action area, never two
+competing primaries.

package/dist/init-payloads/skeleton/foundation.color.md

@@ -0,0 +1,39 @@
+---
+description: "Color — the role system, status meanings, expression rules, and misuse; palette values are an open question. Read before choosing any color."
+---
+
+## Usage
+
+Color is assigned by role, not by taste. The roles are the source of truth;
+raw color values are implementation detail, never product language. If a
+container needs a color, it first needs a role: `background`, `foreground`,
+`card`, `popover`, `primary`, `secondary`, `muted`, `accent`, `border`,
+`input`, `ring`, and the status roles.
+
+The status roles — destructive, success, warning, info — exist only when
+meaning demands them. Destructive means destructive or error. Success means
+success. None of them are brand accents.
+
+One view does not perform a color palette. If a status color is present, the
+rest of the view stays on the base roles. Richness beyond this comes from a
+closed expression set (`--expression-*`), used at the volume the situation
+allows — a marketing page may turn it up; a settings form stays quiet.
+
+## Palette
+
+Open — ask the human; do not freehand. The fixed relationship: a quiet base
+spine is the default atmosphere in every medium, and a closed expression set
+supplies the rest, its volume set by situation, never by taste. The open
+question: what is this brand's base spine, and what are the named hues of
+its expression set — how many, and which? When the human answers, restate
+this section as the brand's current answer and record the values where your
+materials live. Until then, proceed with a quiet provisional spine and label
+it provisional.
+
+## Misuse
+
+- Status colors never moonlight as atmosphere, in any context.
+- Expression never touches what you click. Buttons, inputs, and links stay
+  on the base roles everywhere. A colored control is a different design
+  system.
+- No one-off hex values. If a color has no role, it has no place.

package/dist/init-payloads/skeleton/foundation.composition.md

@@ -0,0 +1,30 @@
+---
+description: "Composition — how a view is assembled: one focal point, one primary action, actions land last, separation escalates. Read before assembling any view."
+---
+
+## Usage
+
+Composition is the layer above layout: layout gives the stacks and gaps;
+composition decides what dominates, what recedes, and what comes last.
+
+Every view has exactly one focal point — one element at the largest scale.
+If two elements compete for primacy, demote or delete one; never resolve
+the tie by making both big.
+
+One primary action per view: the action the view exists to complete.
+Everything else steps down the control ladder (see the controls
+foundation). If two buttons both look primary, the composition failed.
+
+Actions land last. Calls to action render at the end of reading order —
+the user reads, then decides.
+
+Separation escalates: whitespace first, then a divider, then a container —
+in that order, never skipping a step.
+
+## Misuse
+
+- Never fake a focal point with decoration. Primacy comes from scale,
+  position, and space.
+- Never promote a second action to primary because something wants
+  emphasis; step the other one down instead.
+- Never separate with a container when whitespace would do.

package/dist/init-payloads/skeleton/foundation.controls.md

@@ -0,0 +1,29 @@
+---
+description: "Controls — the five-rung emphasis ladder, quiet fields, and misuse. Read for any view with actions or inputs."
+---
+
+## Usage
+
+The control emphasis ladder is exactly five rungs: primary, secondary,
+outline, ghost, link. Primary is for the action the screen exists to
+complete; everything else steps down the ladder. How many primaries a view
+may hold is a composition rule — see the composition foundation: one.
+
+Destructive is a meaning, not a rung. It is rare, it names the destructive
+act directly, and it is never borrowed for urgency, emphasis, or brand heat.
+
+Fields are quiet until active: hairline border, muted placeholder, clear
+label, and a focus ring when the user engages. The ring is guidance, not
+decoration. Errors state facts next to the field that caused them — never
+hidden in modals, toasts, or generic banners when the user needs to fix one
+input.
+
+Controls take the control radius; see the layout foundation for the two
+radius roles.
+
+## Misuse
+
+- Never two competing primary buttons.
+- Never destructive styling as attention-getting.
+- Never expression color on a control — what you click stays on the base
+  roles everywhere.

package/dist/init-payloads/skeleton/foundation.layout.md

@@ -0,0 +1,45 @@
+---
+description: "Layout — stacks with five gap steps, surface roles, three elevation tiers, the two radius roles, and misuse; radius values are an open question. Read before laying anything out."
+---
+
+## Usage
+
+All layout is stacks. Rhythm comes from relationships between siblings, not
+from isolated margins pasted onto whichever element was last touched. The
+gap steps are exactly five: `--gap-xs` through `--gap-xl`. Choose the gap
+that states the relationship; do not tune by single pixels to make a
+screenshot pass. The default is column, medium gap. Columns are for almost
+everything — forms, cards, modal bodies, settings, page sections. Rows are
+conditional: controls, metadata lines, paired label/value moments. If a row
+wraps awkwardly, it wanted to be a column.
+
+Surface is the only way an element gets a background, border, radius, or
+shadow. The vocabulary is closed: role, padding, radius, border, elevation.
+The default surface is flat — no border, no shadow. We do not outline
+everything to prove layout exists.
+
+The elevation tiers are exactly three: card, popover, modal. Elevation
+implies hierarchy — a card sits in flow, a popover floats above it, a modal
+interrupts the task. Pick the tier that matches the interaction.
+
+Borders are structural — inputs and overlays — not decorative frames around
+ordinary text. Use space, tone, and type hierarchy instead.
+
+## Radius
+
+Open — ask the human; do not freehand. The fixed relationship: controls and
+surfaces carry different radius roles, and the two never swap. Buttons and
+inputs take `--radius-control`; cards and containers take
+`--radius-surface`. One radius for what you click, one for what contains.
+The open question: how round is a control, and how round is a surface? When
+answered, restate this section as the brand's current answer. Until then,
+choose provisional values and label them.
+
+## Misuse
+
+- No ad-hoc margins between siblings — they hide the rhythm. Change the
+  stack gap or split the stack.
+- No custom shadows because a composition feels flat, and no modal gravity
+  on a routine card. Component shadows belong to the primitives that own
+  them.
+- Never one radius everywhere by reflex.

package/dist/init-payloads/skeleton/foundation.motion.md

@@ -0,0 +1,34 @@
+---
+description: "Motion — evidence of state change, three durations and one ease, nothing loops, and misuse; the ease's character is an open question shared with voice. Read for any transition or hover treatment."
+---
+
+## Usage
+
+Motion is evidence of a state change. It confirms hover, press, reveal,
+collapse, entrance, exit, and spatial movement. It does not entertain.
+
+The entire vocabulary is three duration roles and one ease. Fast is for
+hover and press. Normal is for reveals, fades, and small state changes. Slow
+is reserved for spatial transitions where the user needs to understand
+movement. Prefer opacity and small transforms.
+
+In editorial and marketing contexts, entrances may be staged — scroll
+reveals and section transitions are part of editorial rhythm, still built
+from the three durations and the one ease. In product UI the same staging is
+decoration.
+
+## Character
+
+Open — ask the human; do not freehand. Motion and voice share one
+temperature: however warm or cool the brand's words are, its movement
+matches. See the voice foundation for the other half of this answer. The
+open question here: what character does the one ease carry? When answered,
+restate this section. Until then, use a quiet standard ease and label it
+provisional.
+
+## Misuse
+
+- Nothing loops except explicit loading states. Decorative pulsing,
+  floating, glowing, and attention-seeking keyframes are off-language.
+- No novelty easings because a surface feels static.
+- If removing an animation does not reduce comprehension, it was decoration.

package/dist/init-payloads/skeleton/foundation.type.md

@@ -0,0 +1,44 @@
+---
+description: "Type — six text variants, seven tones, the one-voice rule, and misuse; the typeface is an open question. Read for any view that contains text."
+---
+
+## Usage
+
+Hierarchy is a closed vocabulary, not a size slider. Every piece of text
+picks from a named set; anything outside the set is a broken primitive, not
+a variant.
+
+The text variants are exactly six: display, headline, title, body, label,
+mono. Variant names are jobs. Display leads a rare editorial moment.
+Headline names a section. Title anchors a card, dialog, or compact region.
+Body carries reading. Label names structure — field labels, category tags,
+metadata, compact status. Mono carries code and machine detail.
+
+The tones are exactly seven: default, muted, inverse, success, warning,
+info, destructive. Tone is part of the message. Hierarchy starts with tone
+and weight before size — a secondary note usually wants muted body or label,
+not a smaller custom font. If prose needs emphasis, improve the sentence
+before adding a style.
+
+The heading scale is editorial: it exists for pages composed outside the
+text variants — heroes and editorial moments. Product UI never mixes the two
+vocabularies in one view. A modal title is not a poster.
+
+Balanced text is for headings and compact statements, never long body copy.
+
+## Typeface
+
+Open — ask the human; do not freehand. The fixed relationship: one typeface
+is the voice of the interface, everywhere, with a mono partner only for
+code, tool detail, and machine output. The open question: what typeface is
+this brand's voice, what mono partners it, and what rhythm does the
+editorial heading scale carry? When answered, restate this section as the
+brand's current answer. Until then, choose a quiet provisional pair and
+label it provisional.
+
+## Misuse
+
+- No faked hierarchy with arbitrary font sizes. Choose the variant that
+  matches the job.
+- Status tones appear only when the words carry that state meaning.
+- Never a second display face to make a view feel branded.

package/dist/init-payloads/skeleton/foundation.voice.md

@@ -0,0 +1,29 @@
+---
+description: "Voice and tone — copy states facts, no performed personality, and misuse; warmth is an open question shared with motion. Read for any copy."
+---
+
+## Usage
+
+Copy states what happened, what is possible, or what the user must decide.
+It does not perform personality. Confidence comes from precision, not
+enthusiasm.
+
+Voice and motion carry the same temperature: a brand whose copy is warm does
+not move coldly, and a brand whose copy is spare does not bounce. When you
+set one, check the other.
+
+## Warmth
+
+Open — ask the human; do not freehand. The open question: how warm or cool
+does this brand sound — and, by the shared temperature, how does it move?
+See the motion foundation for the other half. When answered, restate this
+section as the brand's current answer. Until then, write plainly and label
+the tone provisional.
+
+## Misuse
+
+- No exclamation points as a substitute for having something to say.
+- No apologizing for the interface ("Oops!"). State the fact and the next
+  step.
+- Never restate this section as answered when it was your own provisional
+  choice.

package/dist/init-payloads/skeleton/glossary.md

@@ -0,0 +1,39 @@
+---
+kinds:
+  - name: foundation
+  - name: context
+  - name: cliche
+---
+
+# foundation
+
+The core elements — color, type, controls, layout, motion, voice — plus
+composition, the rules for assembling them into a view. Each foundation
+node is a chapter: usage rules that hold no matter what the brand values
+turn out to be, the brand's open questions (unanswered in this starter,
+marked as decisions only a human can make), and the chapter's misuse list.
+Follow the usage rules as written. Never fill in an open value and present
+it as the brand's.
+
+# context
+
+Where the defaults bend: a context names a situation — an AI conversation
+thread, a data-dense console, a transactional email — and states only what
+inverts there. Read a context only when its situation matches the task.
+Rules from the wrong context are contamination, not guidance.
+
+# cliche
+
+The defaults a generative model falls back on when no brand is steering it.
+These are nobody's brand. Each entry pairs the tired move with the honest
+replacement. Gather before styling anything greenfield; enforced by paired
+checks at review.
+
+---
+
+The cover node (`brand.md`, declared in the manifest) is the one page always
+in context: what the brand is, its temperature, and the refusals only it
+makes. The ghost skill's `adapting-a-starter` recipe is the procedure for
+growing this skeleton into a real fingerprint: write the cover, answer each
+chapter's open question, prune the cliches your chapters absorb, then add
+materials and refs.

package/dist/init-payloads/vessel-light/anti-goal.median.md

@@ -0,0 +1,86 @@
+---
+description: "The model's median defaults this fingerprint refuses — gather for any greenfield visual surface or first-draft copy. Each rule is reject→replace; delete lines your brand legitimately violates."
+---
+
+This is the model's median, not your brand. Each rule is reject→replace.
+Delete every line your brand legitimately violates — `ghost validate` will
+warn on any check reference the deletion orphans — delete the paired flag too.
+
+These are not aesthetic opinions. Where a count is given, it is the measured
+convergence of 300 unsteered generations across three frontier models (the
+antimedian experiment): the defaults a model reaches for when nobody hands it
+a brand. An output showing several of these tells reads as generated,
+whatever else it does right. A deterministic floor rides alongside these
+rules in the paired check — mechanical tells like gradient-filled text,
+emoji as interface icons, em-dash pileups, and aphoristic cadence —
+verified at review, never steered in prose.
+
+### Hover-lift
+Reject hover-lift (`translateY` + growing shadow) as the default interaction
+→ confirm with color and background change at the fingerprint's fast
+duration. (measured: 341)
+
+### Indigo accent
+Reject the indigo/blue/purple default accent (`#4f46e5`, `#2563eb`,
+`#8b5cf6` family; purple/violet hue 260–310) → the fingerprint's declared
+palette; absent one, monochrome plus a single functional accent.
+
+### Dark theme
+Reject unprompted dark theme → the fingerprint's declared surface.
+Dark-to-look-cool and light-to-be-safe are the same retreat from a decision.
+(measured: 271)
+
+### Gradients
+Reject gradient page and section backgrounds and gradient-filled CTAs → flat
+surfaces in semantic roles.
+
+### Side-stripe
+Reject side-stripe borders (a thick colored border on one side of a rounded
+card) — the single most recognizable tell of AI-generated UI → a full
+hairline border, a 4–8% surface tint, or a leading glyph.
+
+### Cream surface
+Reject the cream/sand/beige default surface (warm off-white; token names
+like `--cream`, `--sand`, `--parchment` are the tell) → a true off-white,
+the brand's own hue, or a committed color; warmth via accent and type, not
+the ground.
+
+### Glassmorphism
+Reject glassmorphism (decorative backdrop blur) → flat surfaces with real
+borders and the fingerprint's elevation tiers.
+
+### Chat bubbles
+Reject chat bubbles with initials-circle avatars for assistant turns →
+assistant text plain on the page surface; user turns marked compactly.
+
+### Stock copy
+Reject stock template copy ("Simple, transparent pricing") → headings that
+state what this product specifically does.
+
+### Celebration
+Reject celebration copy and UI (exclamation success, confetti language) →
+quiet factual confirmation.
+
+### Nested cards
+Reject nested cards and everything-in-cards → one surface level per region;
+interior hierarchy from spacing and type; spacing and alignment group
+without card overhead.
+
+### Hero metric
+Reject the hero-metric template (big number + small label + supporting stats
+as default proof) → evidence specific to the product, or nothing. A
+prominent metric showing real user data is fine.
+
+### Every button primary
+Reject every button a primary button → one primary per view; the rest step
+down the fingerprint's emphasis ladder.
+
+### Eyebrow kicker
+Reject an eyebrow kicker on every section → at most one, where the register
+sanctions it; one named kicker is voice, every-section is AI grammar.
+
+### Decorative motion
+Reject decorative looping animation (pulse/float/shimmer) and uniform
+fade-and-rise on every scrolled section → motion as evidence of state
+change; loops only for genuine loading; decoration never compensates for
+weak structure — fix spacing, copy, and hierarchy first.

package/dist/init-payloads/vessel-light/anti-goal.tells.md

@@ -0,0 +1,38 @@
+---
+description: "Failure modes specific to this brand's own signature — gather alongside any signature node you pull."
+---
+
+These are the near-misses of Vessel's own signature: outputs that got close
+enough to cite the brand and still missed it. Each reject names its
+replacement. When a tell fires, the fix direction is always toward the
+token, the role, or deletion — never toward adding a compensating style on
+top of the miss.
+
+Reject rectangular buttons. A rectangular button is not a variant; it is a
+different design system → controls take `--radius-control`, the pill.
+
+Reject swapped radius roles: the surface radius on a control, the pill on a
+surface, or 20px cells in a data table → `--radius-control` on what you
+click, `--radius-surface` on what contains, small radius on data cells.
+
+Reject expression hues on interactive controls, an invented sixth hue, or a
+tinted gray posing as monochrome → the five named expression hues at their
+register's volume, and a true gray spine. An invented hue is not a bolder
+Vessel; it is a different brand.
+
+Reject custom shadows that sit near a tier → the exact tier — card, popover,
+or modal — chosen by interaction importance.
+
+Reject borrowing `--shadow-btn` for layout → component shadows belong to the
+primitives that own them; layout elevation comes from the three tiers.
+
+Reject editorial display type in product UI, and product type timidity in
+editorial → each register keeps its own vocabulary; a modal title is not a
+poster, and a hero at product scale reads as timid.
+
+Reject borders around assistant text → the assistant speaks as plain text on
+the page surface; use space, tone, and type hierarchy instead.
+
+Fidelity note: pills and fluid clamp display headings are medians Vessel
+deliberately shares — their presence is fidelity, not drift. Convergence is
+not the crime; surrendering the choice is.

package/dist/init-payloads/vessel-light/checks/conversation-grammar.md

@@ -0,0 +1,20 @@
+---
+name: Conversation grammar
+description: Flags conversation UI that breaks plain assistant text, prompt-input structure, primary-action discipline, or collapsed tool output.
+severity: high
+references:
+  - grammar.conversation
+  - grammar.surfaces
+---
+
+Apply this check to diffs that touch AI threads, agent consoles, prompt composers, chat messages, or tool-call rendering.
+
+Flag assistant messages wrapped in bordered, filled, elevated, or card-like surfaces. Assistant turns should sit as plain text on the page surface.
+
+Flag user messages that are not compact muted surfaces aligned to the right when the layout has a conversational thread.
+
+Flag controls placed inside the prompt-input textarea region. The textarea is for writing only; controls belong in the single row below it.
+
+Flag more than one primary button in the input row. Send, stop, retry, attach, model select, and tools must not compete as primary actions.
+
+Flag tool output shown expanded by default. The default state is a one-line labeled summary with status; mono detail appears after expansion.