@design-intelligence/ghost 0.22.1 → 0.24.0

package/dist/skill-bundle/SKILL.md

@@ -1,34 +1,33 @@
 ---
 name: ghost
-description: Author, validate, consume, and review against a repo-local Ghost fingerprint — the medium-agnostic articulation of a product's brand. Use when the user wants to set up a .ghost fingerprint, write or update brand-truth nodes, gather brand context before generation, or assemble a review packet from Ghost checks.
+description: Author, validate, consume, and review against a repo-local ghost package — the medium-agnostic articulation of a product's brand. Use when the user wants to set up a .ghost package, write or update guidance nodes, gather brand context before generation, or assemble a review packet from ghost checks.
 license: Apache-2.0
 metadata:
   homepage: https://github.com/block/ghost
   cli: ghost
 ---
 
-# Ghost — Brand Fingerprints
+# ghost — Brand Guidance Packages
 
-A Ghost fingerprint is the medium-agnostic articulation of a brand: its truths,
-its stance, its conditions, and optional pointers to the concrete materials those
-truths govern. One brand truth is stated once, at the altitude it is actually
-true, and an agent reads the relevant truths before building.
+A ghost package is the medium-agnostic articulation of a brand: its guidance,
+its stance, its conditions, and optional pointers to the concrete materials that
+guidance governs. Each brand decision is stated once, at the broadest level where
+it applies, and an agent reads the relevant guidance before building.
 
 ```text
 .ghost/
   manifest.yml        # schema + id (the package anchor)
   glossary.md         # the author's kind vocabulary
   materials/          # bundled materials; reserved, never nodes
-  <kind>.<slug>.md    # a brand truth of a declared kind
-  <slug>.md           # a brand truth without a kind
+  <kind>.<slug>.md    # guidance of a declared kind
+  <slug>.md           # guidance without a kind
   checks/             # optional review assertions; never nodes
 ```
 
 ## The model in one breath
 
-- A **node** is a markdown file: `description`, optional `materials`, and a prose
-  brand truth.
-- `materials` is one list of locators for the concrete stuff the truth is about:
+- A **node** is a markdown file: `description`, optional `materials`, and prose brand guidance.
+- `materials` is one list of locators for the concrete stuff the guidance is about:
   repo-relative paths/globs or absolute HTTPS URLs. `materials/` is reserved for
   bundled materials; reference living implementations where they already live.
   Guidance stays in prose.
@@ -55,28 +54,35 @@ true, and an agent reads the relevant truths before building.
 ghost init          # scaffold .ghost/ with the steering starter
 ghost checks init   # opt in to review assertions
 ghost validate      # artifact shape + node/material/check validation
-ghost gather <ask>  # emit the fingerprint menu for this task
-ghost pull <ids>    # read selected node bodies and materials
+ghost gather <ask>  # emit Available guidance for this task
+ghost pull <ids>    # pull selected node bodies and materials
 ghost review        # assemble diff + matched material-backed nodes + checks
 ghost export        # package .ghost/ as a portable brand artifact
 ghost pulse         # summarize local gather/pull events while tuning
 ```
 
-`gather` does no selection. It emits the menu and you read the ask against it,
-then pull the truths you judge relevant. Its header includes a coverage line —
-total nodes and nodes carrying concrete material — so an all-prose
-fingerprint is visible before generation.
+`gather` does no selection. It emits the complete, unfiltered, unranked menu
+from the ghost package. You read the ask against descriptions, then
+pull every applicable node and skip inapplicable nodes. Topic overlap alone is
+not applicability. Its header includes a coverage line: total nodes and nodes
+carrying concrete material. `gather` labels materials, substantial fenced
+examples, and Skeletons separately, so an all-prose package is visible
+before generation.
 
 Prefer `ghost pull` over reading files directly: it emits the same prose,
 inlines small local materials by default, turns binary materials into
-inspect-pointers, orders the packet for steering (cover when selected, concrete nodes,
-prose rules), extracts Skeletons dead last, and appends structured
-events to `.ghost/.events` for local tuning.
+inspect-pointers, orders the packet for steering (cover when selected,
+concrete nodes, prose rules), extracts Skeletons dead last, and appends
+structured events to `.ghost/.events` for local tuning.
 
 `review` does no grading. It assembles an advisory packet: touched files,
 matched material-backed nodes, offered checks, probe
 evidence, coverage gaps, and the diff. The host agent renders findings.
 
+For visual work, do not stop at generation. Continue through material inspection,
+compact briefing, rendered verification, bounded repair, and grounded review in
+this same host-agent session.
+
 ## CLI verbs
 
 | Verb | Purpose |
@@ -84,7 +90,7 @@ evidence, coverage gaps, and the diff. The host agent renders findings.
 | `ghost init` | Scaffold `.ghost/` with the skeleton starter: manifest, glossary, a `brand.md` cover, foundation chapters, context nodes, and the cliche floor. `--template minimal` writes a smaller cover-led starter. `--with checks` also adds the checks directory. |
 | `ghost checks init` | Scaffold `.ghost/checks/` with an example review assertion. |
 | `ghost validate [file-or-dir]` | Validate manifest, nodes, material locators, check references, and glossary kind prefixes. |
-| `ghost gather [ask…] [--format json]` | Emit the node menu for selection plus coverage line; log exposed ids. |
+| `ghost gather [ask…] [--format json]` | Emit the complete guidance menu plus coverage line; log exposed ids. |
 | `ghost pull <id> [<id>…]` | Emit selected nodes' full bodies and materials in steering order; log selected/missed ids. |
 | `ghost review [--diff <path|->] [--base <ref>] [--format json] [--no-probes]` | Emit an advisory review packet for a diff (requires `.ghost/checks/`). |
 | `ghost export [--out <path>] [--no-checks] [--strict] [--format json]` | Package `.ghost/` as a portable brand artifact and report which material locators will not travel. |
@@ -101,7 +107,7 @@ from the node body and emits the fences at the end under a begin-from-this banne
 If a pulled Skeleton matches the task, start the artifact from it verbatim, then
 fill with task facts.
 
-## Receiving a fingerprint
+## Receiving a ghost package
 
 Unpack the exported archive, run `ghost validate --package <dir>`, then run
 `ghost skill install` in the receiving workspace. From there, gather and pull
@@ -109,27 +115,29 @@ against the unpacked package with `--package <dir>`.
 
 ## Workflows
 
-- Author or update the fingerprint: follow [references/capture.md](references/capture.md).
+- Author or update the package: follow [references/capture.md](references/capture.md).
+- Distill supplied artifacts into new or existing guidance: follow [references/distill.md](references/distill.md).
 - Author material-backed nodes: follow [references/blocks.md](references/blocks.md).
 - Choose which concrete code tiers the package carries: follow [references/concrete-tiers.md](references/concrete-tiers.md).
 - Choose the right human-agent authoring workflow: follow [references/authoring-scenarios.md](references/authoring-scenarios.md).
 - Adapt a starter (a body or the skeleton) to your brand: follow [references/adapting-a-starter.md](references/adapting-a-starter.md).
-- Gather applicable truths for a task: follow [references/recall.md](references/recall.md).
+- Gather applicable guidance for a task: follow [references/recall.md](references/recall.md).
+- Make a visual artifact end to end: follow [references/making.md](references/making.md).
 - Shape a pre-generation brief: follow [references/brief.md](references/brief.md).
 - Probe readiness before generating: follow [references/self-check.md](references/self-check.md).
 - Audit steering coverage: follow [references/steering-audit.md](references/steering-audit.md).
 - Understand the package shape: see [references/schema.md](references/schema.md).
 
-Fingerprint authoring is **elicitation, not scanning**. The raw material is what
+ghost package authoring is **elicitation, not scanning**. The raw material is what
 the human brings and points at: words, images, links, exemplar products, brand
 docs, copy they love or hate. Repo code can supply material locators and local
-conventions, but durable brand truth should be curated by the human.
+conventions, but durable brand guidance should be curated by the human.
 
-## When the fingerprint is silent
+## When the package is silent
 
-A silent fingerprint does not require stopping. Proceed from nearby product
+A silent package does not require stopping. Proceed from nearby product
 surfaces, local conventions, and ordinary reasoning when safe, and label that
-reasoning as provisional and non-Ghost-backed — unless the fingerprint itself
+reasoning as provisional and non-ghost-backed unless the package itself
 declares a stricter silence posture (check the cover), which overrides
 this default. Ask a human before high-risk, irreversible, privacy, security,
 legal, or brand-defining choices.
@@ -137,7 +145,7 @@ legal, or brand-defining choices.
 ## Never
 
 - Never invent hierarchy, inheritance, or cross-node edges.
-- Never file a truth by destination (`for-emails.md`); state its condition in prose.
+- Never file a node by destination (`for-emails.md`); state its condition in prose.
 - Never put guidance in `materials`; it belongs in the node body.
 - Never gather checks as generation context.
-- Never claim provisional or local-convention reasoning as Ghost-backed.
+- Never claim provisional or local-convention reasoning as ghost-backed.

package/dist/skill-bundle/references/adapting-a-starter.md

@@ -1,17 +1,17 @@
 ---
 name: adapting-a-starter
-description: Transplant a starter fingerprint — a body like vessel-light or the naked skeleton — into your own brand, one procedure from manifest id to regenerated refs.
+description: Transplant a starter ghost package — a body like vessel-light or the naked skeleton — into your own brand, one procedure from manifest id to regenerated refs.
 handoffs:
   - label: Validate the adapted package
     command: ghost validate --format json
-    prompt: Does the adapted fingerprint validate, and did any pruned rule orphan a check reference?
+    prompt: Does the adapted package validate, and did any pruned rule orphan a check reference?
 ---
 
-# Recipe: Adapt A Starter Fingerprint
+# Recipe: Adapt A Starter Package
 
 **Goal:** turn an installed starter — a full body (`ghost init --body
 vessel-light`) or the naked skeleton (`ghost init`) — into *your* brand's
-fingerprint without shipping a self-contradicting package.
+brand guidance without shipping a self-contradicting package.
 
 The naked skeleton is factored by what must happen during adaptation:
 
@@ -26,7 +26,7 @@ The naked skeleton is factored by what must happen during adaptation:
 
 Do the steps **in order and in one sitting** where possible. A half-adapted
 package is worse than an unadapted one: stale refs steer harder than any prose
-you rewrote, so stopping before refs and checks are current ships a fingerprint
+you rewrote, so stopping before refs and checks are current ships a package
 that contradicts itself.
 
 ## The procedure
@@ -64,7 +64,7 @@ that contradicts itself.
    stale ref loses. Rebuild each ref against the new values and chapter answers,
    keep any annotation headers current, and make each ref demonstrate its closed
    sets completely. If the starter shipped no refs, generate them now — a
-   fingerprint with no exemplars steers at half strength.
+   package with no exemplars steers at half strength.
 8. **Rewrite checks and near-miss nodes.** For each answered foundation chapter,
    name the failure mode one step away from the answer and its replacement. Put
    pre-generation guidance in nodes and review assertions in `checks/`; never
@@ -81,11 +81,11 @@ Work does not block on adaptation. Before the procedure runs (or midway through
 it), cite starter content honestly:
 
 - Cover scaffolding and unanswered foundation sections: **provisional** — never
-  plain brand truth.
-- Foundation usage rules: **Ghost-backed starter structure** until the human
+  plain brand guidance.
+- Foundation usage rules: **ghost-backed starter structure** until the human
   answers the open sections and edits the misuse lists.
-- Surviving median rules: **owner-backed after init** — Ghost stamps this
-  measured model truth into every initialized package; you own the pruning and
+- Surviving median rules: **owner-backed after init** — ghost stamps this
+  measured model behavior into every initialized package; you own the pruning and
   any adaptation thereafter.
 - Context nodes: **conditional** — read only when their situation matches, and
   revisit them after the foundation answers change.
@@ -94,7 +94,7 @@ it), cite starter content honestly:
 
 ## Never
 
-- Never leave cover scaffolding in a real fingerprint.
+- Never leave cover scaffolding in a real ghost package.
 - Never present your provisional value as the brand's answer.
 - Never leave stale refs alongside new values — regenerate or delete; a stale
   exemplar outweighs rewritten prose.

package/dist/skill-bundle/references/authoring-scenarios.md

@@ -1,19 +1,19 @@
 ---
 name: authoring-scenarios
-description: Choose the right human-agent workflow for authoring Ghost brand fingerprints.
+description: Choose the right human-agent workflow for authoring ghost packages.
 handoffs:
-  - label: Validate the fingerprint
+  - label: Validate the package
     command: ghost validate --format json
-    prompt: Classify this fingerprint's authoring scenario and confirm the package validates.
+    prompt: Classify this package's authoring scenario and confirm the package validates.
 ---
 
-# Recipe: Collaborative Fingerprint Authoring
+# Recipe: Collaborative Package Authoring
 
-**Goal:** help a human and agent co-author durable brand truths through
+**Goal:** help a human and agent co-author durable brand guidance through
 conversation — without laundering what a codebase happens to do into what the
 brand means.
 
-The fingerprint is medium-agnostic and is not derived from a repo. Its raw
+The ghost package is medium-agnostic and is not derived from a repo. Its raw
 material is **elicitation**: what the human says, shows, and points at — words,
 screenshots, links, exemplar products, marketing copy, a competitor they define
 themselves against. Agent synthesis is draft work until the human curates it
@@ -22,15 +22,15 @@ and ordinary Git review accepts it.
 Repo-bound reality — components, tokens, paths, building blocks — can be
 recorded as `materials` on the node whose prose explains their purpose. When a
 conversation surfaces "we have a component for that," treat it as material to
-locate and interpret, not as brand truth by itself.
+locate and interpret, not as brand guidance on its own.
 
 ## 1. Start With One Repeated Decision
 
-Do not try to fingerprint the whole brand at once. Ask the human for the one
+Do not try to capture the whole brand at once. Ask the human for the one
 decision whose feedback keeps repeating — the checkout always flagged for
 trust, the voice always re-toned, the empty state always rewritten — and
-capture that one truth as a node first. One high-confidence truth beats an
-empty catalog; the fingerprint grows as the next repeated decision shows up.
+capture that one decision as a node first. One well-grounded node beats an
+empty catalog; the package grows as the next repeated decision shows up.
 
 The scenario below tunes the authoring *posture* for that first node; it is not
 a gate to clear before writing anything.
@@ -38,19 +38,22 @@ a gate to clear before writing anything.
 | Scenario | Default authoring posture |
 | --- | --- |
 | Net new brand | Stance-first. Elicit feel, audience, and early anti-goals before anything else exists to point at. |
-| Established brand, first fingerprint | Artifact-rich interview. The human can show a lot — shipped surfaces, brand docs, campaigns. Elicit which of it is *intentional*. |
+| Established brand, first ghost package | Artifact-rich interview. The human can show a lot — shipped surfaces, brand docs, campaigns. Elicit which of it is *intentional*. |
 | Strong opinions, weak articulation | Example-led. The human knows it when they see it: work from exemplars and counter-exemplars ("this feels like us, this never would") toward the stance underneath. |
-| Brand doc or design-language deck exists | Distillation. The document is testimony, not truth: pull the claims that actually steer decisions, drop the aspirational filler, and have the human ratify each survivor. |
+| Brand doc or design-language deck exists | Distillation. Treat the document as evidence: pull the claims that actually steer decisions, drop the aspirational filler, and have the human ratify each survivor. |
 | Rebrand, redesign, migration | Transition-led. Capture current, target, and what must not be lost in between. |
-| Fork, white label, tenant variant | Shared base + local divergence. Keep common truths broad; scope divergence with conditions. |
+| Fork, white label, tenant variant | Shared base + local divergence. Keep shared guidance broad; scope divergence with conditions. |
 | Monorepo or product suite | One contract per package. |
 
+When supplied artifacts are the starting point or must be reconciled with an
+existing package, follow [distill.md](distill.md).
+
 If more than one applies, start with the broad scenario, then narrow.
 
 ## 2. Interview The Human
 
 The interview is the engine. Ask only high-leverage questions that change the
-fingerprint:
+guidance:
 
 - What should this brand feel like, and what should it never become? (The
   "never become" answers are anti-goal nodes — capture them with the same care
@@ -63,7 +66,7 @@ fingerprint:
 - What keeps getting flagged in review, re-toned, or rewritten?
 - Where do trust, density, pacing, accessibility, recovery, or disclosure
   matter most?
-- Which truths are universal, and which only hold under a specific situation?
+- Which guidance is universal, and which guidance holds only under a specific situation?
 
 Capture human-authored or human-approved answers as nodes. Do not treat
 unapproved notes as canonical.
@@ -73,7 +76,7 @@ unapproved notes as canonical.
 Ask for artifacts and read them closely: screenshots, links, exemplar products,
 brand docs, marketing copy, past campaigns, a rejected design and why it was
 rejected. Treat every artifact as *testimony* — evidence of a stance the human
-holds — never as truth by itself. A pattern that appears everywhere may be
+holds — never as guidance by itself. A pattern that appears everywhere may be
 legacy; a pattern that appears once may be the brand at its best. The human
 says which.
 
@@ -85,15 +88,15 @@ and enforced in review, not repeated as the model's main example.
 
 ## 4. Draft The Nodes
 
-Write the smallest useful set of nodes, each a purpose-coherent prose truth with
+Write the smallest useful set of nodes, each carrying purpose-coherent prose guidance with
 a one-line `description`, named `<kind>.<slug>.md` (or a bare slug when no kind is present). Ask three questions of each node body: why (the stance), with what
 (the materials), and how it is assembled (the patterns). These are drafting
 prompts, not fields.
 
-Draft only what the human said or showed. State universal truths plainly; give
-narrower truths a **condition** in the prose — the situation they apply in,
+Draft only what the human said or showed. State universal guidance plainly; give
+narrower guidance a **condition** in the prose — the situation they apply in,
 never a destination. Label uncertain reasoning as provisional. Prefer a few
-high-confidence truths over a broad catalog. Hold draft prose to the node prose
+focused guidance over a broad catalog. Hold draft prose to the node prose
 stances in [capture.md](capture.md) and score each node against its drafting
 gate before presenting drafts for curation.
 
@@ -103,7 +106,7 @@ Before treating draft content as durable, ask the human to classify important
 claims:
 
 - keep as canonical
-- soften into guidance
+- soften the guidance
 - reject as accidental or legacy
 - move to scratch notes
 - restate at a broader or narrower altitude (add or drop a condition)
@@ -115,10 +118,10 @@ Two authoring decisions replace any notion of hierarchy:
 - **Kind** — declare the kind vocabulary in `glossary.md` and name each node
   `<kind>.<slug>.md` so its normative weight is clear. The glossary defines what
   each kind means and how strongly it binds. Kinds are your choice;
-  Ghost ships no fixed vocabulary.
-- **Altitude** — state a truth at the level it is actually true. Universal → state
+  ghost ships no fixed vocabulary.
+- **Altitude** — state guidance at the level where it applies. Universal → state
   it plainly. Narrower → name the situation that activates it, in the prose. Never
-  file a truth by destination (`for-emails.md`); the model reads the condition and
+  file a node by destination (`for-emails.md`); the model reads the condition and
   decides when it applies.
 
 ## 7. Validate And Ratify
@@ -137,7 +140,7 @@ edits are drafts; checked-in nodes are canonical.
 The shapes below teach what steering prose looks like when it works. The
 examples use **Morrow Ledger**, a fictional bookkeeping product — teaching
 fiction for this recipe only, never content for a real corpus. Each shape is a
-pattern to imitate with the human's real truths.
+pattern to imitate with the human's real guidance.
 
 - **Stance as forced choices.** Not adjectives — decisions under pressure:
   "Clarity beats momentum: write '3 invoices are 14+ days late', not 'Cash
@@ -160,25 +163,25 @@ pattern to imitate with the human's real truths.
   teaches its accidents as brand.
 - **Material inventory.** `materials` locates; prose explains meaning:
   "`src/styles/tokens.css` should define the ink, ledger, amber, and paper
-  colors." Never duplicate API docs unless the API itself is the brand truth.
+  colors." Never duplicate API docs unless the API itself is the brand guidance.
 - **Decision trace.** A worked tradeoff with the reversal condition: "We chose
   visible evidence over shorter surfaces… Reverses when the evidence would
   expose sensitive third-party details — then show the count only." Models
   imitate reasoning as well as outputs.
 
 State the silence posture on the manifest-declared cover, which `gather`
-inlines for every task: when the fingerprint is silent, proceed provisionally
+inlines for every task: when the package is silent, proceed provisionally
 from local conventions only when safe, and ask before brand-defining,
 irreversible, legal, privacy-sensitive, or high-risk choices.
 
 ## Never
 
-- Never derive brand truth from repo code alone; what the codebase repeats may
+- Never derive brand guidance from repo code alone; what the codebase repeats may
   be legacy, not stance. Use repo paths as `materials` only after the prose
-  truth has been curated.
+  guidance has been curated.
 - Never draft a node the human neither said nor showed; that is invention
   wearing the brand's clothes.
 - Never treat a brand doc, an artifact, or repetition frequency as brand
   authority; the human ratifies what is intentional.
 - Never invent a hierarchy, inheritance, or edges — the package is flat.
-- Never file a truth by destination; state its condition in the prose.
+- Never file a node by destination; state its condition in the prose.

package/dist/skill-bundle/references/blocks.md

@@ -1,21 +1,21 @@
 ---
 name: blocks
-description: Author block and material nodes so an agent can match a fingerprint's stance to concrete building blocks.
+description: Author block and material nodes so an agent can match a ghost package's stance to concrete building blocks.
 handoffs:
   - label: List the node menu
     command: ghost gather
-    prompt: What materials does this fingerprint document, and what is absent?
+    prompt: What materials does this package document, and what is absent?
 ---
 
 # Recipe: Author Block And Material Nodes
 
 **Goal:** when you are documenting the **materials** a brand draws from — its
 building blocks, assets, and reusable pieces — write that prose so an agent can
-translate the fingerprint's stance into concrete building blocks without the
-fingerprint ever naming a component.
+translate the package's stance into concrete building blocks without the
+guidance ever naming a component.
 
 This is opinionated method, not new schema. **"Block node" is shorthand in this
-recipe, not a Ghost concept**: it means any node whose truth is a reusable
+recipe, not a ghost concept**: it means any node whose guidance is a reusable
 building block, whatever kind the author's glossary declares for it (`block`,
 `asset`, `pattern`, …). A block node is a node like any other: a markdown file
 with a `description` and a prose body, named `<kind>.<slug>.md` (or a bare
@@ -25,12 +25,11 @@ whatever keeps each node purpose-coherent.
 
 ## Where it sits
 
-A fingerprint declares stance. Block and material nodes ground that stance in
-concrete materials — they are what makes a node **concrete** in gather, pull
-ordering, and review matching. A realizing agent **reads** them and matches
-against them. Strip every block node and the fingerprint is still valid — it
-just gives the agent less to draw on, and prose-only steering is weak steering.
-The agent does the matching.
+A ghost package declares stance. Block and material nodes ground that stance in
+concrete material: materials, substantial fenced examples, or Skeletons. A
+realizing agent **reads** them and matches against them. Strip every block node
+and the package is still valid — it just gives the agent less to draw on,
+and prose-only steering is weak steering. The agent does the matching.
 
 ## Concreteness is the grounding dial
 
@@ -51,7 +50,7 @@ Neither is correct. A concrete block node is a deliberate trade, not a leak.
   the absence of a body is the signal that training priors are acceptable here.
   When a primitive is itself brand-distinctive (a button whose shape, weight, or
   focus treatment is a recognizable brand move), its *divergence from the
-  generic form* is a truth worth a body: state what differs and why, not the
+  generic form* is a decision worth a node: state what differs and why, not the
   full API.
 - **Anything that encodes a user moment** (confirmation, plan, task, tool,
   reasoning, sources…) earns **one short prose body**. This is what the method is
@@ -85,15 +84,15 @@ when (use X instead) / never*:
 
 Keep props, markup, and API reference out; the body documents purpose, and the
 implementation beneath it is swappable. Explicit values are the exception when
-the value itself is the brand truth — an exact color, a specific corner radius —
+the value itself is the brand guidance — an exact color, a specific corner radius —
 not a swappable implementation detail.
 
 ## How a match runs
 
-The agent reads the fingerprint's stance, `gather`s the menu, ranks candidate
-block nodes by description, separates near-neighbors on *not when* and
-*never*, and assembles. The realizing surface authors the chosen blocks in its
-medium. The fingerprint never named a component; the agent bridged via documented
+The agent reads the package's stance, `gather`s the menu, pulls block nodes
+whose descriptions apply, separates near-neighbors on *not when* and *never*,
+and assembles. The realizing surface authors the chosen blocks in its medium.
+The guidance never named a component; the agent bridged via documented
 purpose.
 
 ## Curation rule
@@ -156,7 +155,7 @@ divergence from the generic form would earn a short body.)
 ## Materials: bundle brand-owned materials, reference implementations
 
 Use the rule of thumb literally. Bundle brand-owned materials: brand-owned artifacts that
-should travel with the fingerprint and survive export or refactors — tokens.css,
+should travel with the package and survive export or refactors — tokens.css,
 motion.json, logo.svg, type materials. Reference implementations: living app
 code, components, stories, or tests whose home is still the product repo. The
 `materials` list locates both; the prose says what the material proves.
@@ -174,7 +173,7 @@ prop APIs re-imports implementation opinion and creates a mirror to maintain.
   of a body is the signal. A brand-distinctive primitive earns a body for its
   divergence, never for its API.
 - Never put props, markup, or API reference in a block body; explicit
-  values belong only when the value itself is the brand truth.
-- Never let the fingerprint reference the realizing surface; blocks are read,
+  values belong only when the value itself is the brand guidance.
+- Never let the package reference the realizing surface; blocks are read,
   not addressed.
 - Never split two blocks that answer the same first question; that is one node.

package/dist/skill-bundle/references/brief.md

@@ -1,20 +1,22 @@
 ---
 name: brief
-description: Build a compact pre-generation packet from pulled Ghost truths.
+description: Build a compact pre-generation packet from pulled ghost guidance.
 ---
 
-# Recipe: Brief Work From Ghost Fingerprint
+# Recipe: Brief Work From ghost Package
 
 A brief is an ephemeral steering packet for the generating pass. It is not a new
 schema and is never written back into `.ghost/`.
 
 1. Run `ghost gather <ask> --format json` and select against descriptions.
-2. The cover is already in context. Pull a small set from the menu: **3–5 nodes
-   is normal; 10 is a bad selection** unless the task is unusually broad.
-3. Prefer concrete nodes: `materials`, substantial fenced examples, or a
-   `## Skeleton`. If there is **no concrete material for this surface**, the
-   readiness ceiling is **Yellow**.
-4. Keep provisional reasoning visibly separate from Ghost-backed claims.
+2. The cover is already in context and outside selection. Pull every applicable
+   node with `ghost pull <id> [<id>…]`; skip nodes whose stated situation does
+   not apply. Topic overlap alone is not applicability.
+3. Note gather payload labels where present: `materials`, substantial fenced
+   examples, or a `## Skeleton`. If there is no concrete material for this
+   surface, the readiness ceiling is **Yellow**.
+4. If no node applies, name the package's silence, follow the cover silence
+   posture, and keep provisional reasoning separate from ghost-backed claims.
 
 ## The packet: five sections only
 
@@ -34,14 +36,14 @@ Return this shape:
 - matching pulled Skeleton, or "none pulled"
 
 ## Silent / provisional
-- what Ghost does not cover and what local evidence carries
+- what ghost does not cover and what local evidence carries
 ```
 
 Rules:
 
 - Do not add sections for every kind. Sections dilute instruction weight.
-- Treat `ghost pull` ordering as signal: stance first, concrete material next,
-  prose rules, Skeletons dead last.
+- Treat `ghost pull` ordering as packet structure: stance first, concrete-material
+  nodes next, prose rules, Skeletons dead last.
 - If a pulled Skeleton matches the surface, begin the artifact from it verbatim
   before filling.
 - Anti-goals are review-critical: state the positive replacement, not just the