clearotron 0.2.2 → 0.2.4

package/driver/publish/render.mjs

@@ -416,7 +416,7 @@ const useEvidence = (m) => [USE_EVIDENCE_LABEL[m?._status], USE_SOURCE_LABEL[m?.
 // EXACT EQUALITY, exactly as EVIDENCE_LABEL maps `_status`. The sentinel itself does not move: archived
 // runs carry the old value forever and a fourth spelling of it would have to be accepted everywhere.
 const USE_CHECK_NO_RESULT = 'perplexity_research — no result';
-const USE_CHECK_NO_RESULT_CITE = 'Marketplace search run — no result found.';
+const USE_CHECK_NO_RESULT_CITE = 'Nothing found in the marketplaces searched.';
 const USE_CHECK_NO_RESULT_SHORT = 'marketplace search — no result found';
 // — MATCHED ON NORMALISED PUNCTUATION, NOT ONE SPELLING. The constant itself does not
 // move (archived runs carry it forever, the validators name it), but the SEAT emitted a hyphen where
@@ -456,8 +456,8 @@ function meter(name, entry) {
 // (emitted by the report-card stage, parsed into card.meta.ord) and the driver already orders +
 // provenance-checks cards by it — so match on THAT exact, injective key. The old fuzzy owner/mark
 // containment collapsed distinct findings onto one card (`.find()` first-match): two findings sharing
-// a mark, or whose mark is a substring of another's ("aura" ⊂ "aurora"), all matched the first card,
-// rendering one card's prose under every finding (the PETCARY "02 On-field conflicts" duplication). The
+// a mark, or whose mark is a substring of another's ("nova" ⊂ "novadex"), all matched the first card,
+// rendering one card's prose under every finding (the "02 On-field conflicts" duplication). The
 // fuzzy match is kept ONLY as a fallback for legacy artifacts whose cards predate the `- ord:` line.
 function matchCard(finding, cards) {
   const list = cards || [];
@@ -852,7 +852,7 @@ function plainScopeNote(text) {
   if (!t) return '';
   return stripTelemetry(t).trim();   // trim: an all-telemetry note leaves only newlines, and '' is falsy
 }
-function scopeSection(ranBucket, coverage, coverageJudgment, methodologyText, contextNotes, fm = {}, hasRecordSet = false, hasCards = false) {
+function scopeSection(ranBucket, coverage, coverageJudgment, methodologyText, contextNotes, fm = {}, hasRecordSet = false, hasCards = false, hasIndexEntry = false) {
   const parts = [];
   // B3 (spec 2026-07-30 §4) — record provenance, stated ONCE, here, instead of a hedge stamped on
   // every card. This is the single home of what "fetched", "register-index entry" and "inferred"
@@ -868,7 +868,11 @@ function scopeSection(ranBucket, coverage, coverageJudgment, methodologyText, co
   // conditions: a copy is a thing that drifts, and over-including costs one explanatory paragraph in a
   // collapsed section while under-including costs a reader an unexplained label. The fetched-records
   // sentence stays conditional on hasRecordSet, so a run WITH a record set is byte-identical to B3.
-  if (hasRecordSet || hasCards) parts.push(`<p class="scoperead" style="margin:0 0 4px;font-weight:600">Record provenance</p><p class="provnote" style="margin:0 0 6px;font-size:13px">${hasRecordSet ? 'Registry identifiers on the finding cards are read from the official register records fetched this run. ' : ''}A registration shown as a register-index entry was seen in the register index; its full record was not pulled. An enforcer appetite marked “inferred” rests on reputation or profile signals rather than a fetched record.</p>`);
+  // THREE SENTENCES EXPLAINING ONE WORD, and the middle one printed on every report whether or not the
+  // page had a register-index entry on it — a definition of a label the reader could not see. It renders
+  // now only where such an entry does, and the remaining two say what "inferred" means in the words a
+  // reader would use for it rather than in the renderer's.
+  if (hasRecordSet || hasCards) parts.push(`<p class="scoperead" style="margin:0 0 4px;font-weight:600">Record provenance</p><p class="provnote" style="margin:0 0 6px;font-size:13px">${hasRecordSet ? 'Registration numbers on the cards were read from the register records. ' : ''}${hasIndexEntry ? 'A registration shown as a register-index entry was seen in the register index; its full record was not pulled. ' : ''}“Inferred” beside an owner’s likelihood to object means we judged it from what the owner sells and holds; we had no enforcement history to read.</p>`);
   // — this is the one part of §4 that does NOT fold. Same markup, same heading, same marker; it is
   // emitted beside the <details> instead of inside it, wrapped in the panel the only-you section already
   // uses so it reads as a region of the page rather than a stray heading.
@@ -896,7 +900,11 @@ function scopeSection(ranBucket, coverage, coverageJudgment, methodologyText, co
       + `<p class="covnone" style="margin:0 0 6px;font-size:13px">No coverage record was produced for this run. `
       + `This section normally lists what each search covered and what is still open; its absence here is a gap `
       + `in the record, not a finding that nothing is open. Ask us before relying on it.</p>`);
-  if (coverageJudgment && coverageJudgment.reason) parts.push(`<p class="cov-read" style="margin:8px 0 0;font-size:13px;color:var(--faint)"><b>Coverage read (internal):</b> ${esc(String(coverageJudgment.reason))}</p>`);
+  // THE INTERNAL COVERAGE READ IS NOT RENDERED. It concatenated the engine's own search-unit names into
+  // about a thousand characters of prose — and on the measured run it ended mid-word, because it is a
+  // machine's working note and nothing was reading it as a sentence. Every fact in it is already in the
+  // coverage cells directly above, in plain words. It stays in the run's artifacts and in the workbook,
+  // where the reader is someone who wants it.
   const meth = plainScopeNote(methodologyText);
   if (meth) parts.push(`<p class="scoperead" style="margin:10px 0 4px;font-weight:600">How this search was run</p><div class="methnote" style="font-size:13px">${renderProse(meth)}</div>`);
   const cn = contextNotesBlock(contextNotes);
@@ -1230,11 +1238,16 @@ function fullDetail(f, card, recordsByUri = new Map()) {
   //                 ("Download full audit (Excel)"), because that is the string the reader hunts for on
   //                 the page. NOT an inline .xlsx link: portal-report.mjs strips those, correctly — the
   //                 portal REPLACES them with its own download control (portal-ui Result.tsx).
-  //   placeholder — a register UI exists and we do not know its per-record address. Labelled as a
-  //                 placeholder so it reads as unfinished rather than as a citation a reader can check.
+  //   placeholder — a register UI exists and we do not know its per-record address. It CARRIES NO NOTE:
+  //                 the number stands on its own, because "(placeholder)" beside twenty-four
+  //                 registrations reads to a client as a broken report rather than as a missing link.
+  // THE PLACEHOLDER NOTE IS GONE. It printed " — no record link available yet (placeholder)" beside
+  // every registration a register UI has no per-record address for — twenty-four times on the measured
+  // page — and a client reads "placeholder" as a broken report. The number is the fact; when there is a
+  // link the number IS the link, and when there is not, the number still stands on its own. The
+  // workbook note stays: it tells a reader where the full record actually is.
   const NO_LINK_NOTE = {
     workbook: ' — full record in the audit workbook (“Download full audit (Excel)”)',
-    placeholder: ' — no record link available yet (placeholder)',
   };
   const regUri = (u, fb) => {
     const h = regHref(u);
@@ -1350,7 +1363,11 @@ function fullDetail(f, card, recordsByUri = new Map()) {
   // D7 — the code-owned "searched, nothing found" sentinel becomes client words HERE, by exact
   // equality against the one constant. Any other value is a source string and rides through untouched.
   const useSrc = isUseCheckNoResult(f.use_check?.source) ? USE_CHECK_NO_RESULT_CITE : f.use_check?.source;
-  const useChk = cite(useSrc, 'Use checked.', useStatus);
+  // NO EVIDENCE TAG ON AN EMPTY RESULT. The line read "Use checked. Marketplace search run — no result
+  // found. Evidence: inferred", and "inferred" beside "no result" reads as a contradiction: it qualifies
+  // how a FINDING was established, and there is no finding here. Nothing was found, and that is the
+  // whole of what the line has to say.
+  const useChk = cite(useSrc, 'Use checked.', isUseCheckNoResult(f.use_check?.source) ? null : useStatus);
   const ownR = cite(f.own_rights?.source, 'Own-portfolio sweep.', EVIDENCE_LABEL[f.own_rights?._status]);
   const proseFull = cardBlock(card, /^full detail/i);
   const proseFullShown = proseFull;   // one report: the full prose; portal-report strips serve-time chrome, never analysis
@@ -1627,7 +1644,67 @@ const COV_STATE = {
   'not-searched': { cls: 'todo', ic: '→', word: 'Not run this run' },
   note: { cls: 'info', ic: 'i', word: 'Note' },
 };
+/**
+ * ONE ROW PER GAP, where the driver's follow-up row and the model's own row are the same search.
+ *
+ * A run deferred the English word DOLPHIN and the page said so twice: once as the model wrote it — "the
+ * English word DOLPHIN as a dedicated exact search · Open item" — and once as the driver composes it
+ * from the envelope, "Follow-up / dolphin · Open item: dolphin — not completed this run — the search for
+ * it was planned and never reached the register…". The run's own reviewer flagged the duplicate and it
+ * shipped anyway, because the second row is composed HERE and the reviewer reads what the model wrote.
+ *
+ * RENDER-SIDE ONLY. Both rows stay in the record and in the workbook; this decides what the page draws.
+ * Dropping the driver's row from `coverage[]` would change what the run recorded, and this issue is
+ * presentation.
+ *
+ * IT ERRS TOWARD KEEPING BOTH. A surplus row is today's behaviour; a wrongly-suppressed one hides a gap
+ * from the reader, which is the failure worth avoiding. So the driver's row goes only when another row
+ * carries EVERY significant word of the directive it names — a near-match keeps both.
+ */
+const FOLLOW_UP_PREFIX = 'Follow-up / ';
+const COV_STOPWORDS = new Set(['the', 'a', 'an', 'as', 'for', 'of', 'in', 'on', 'and', 'or', 'to', 'is',
+  'was', 'it', 'its', 'this', 'that', 'with', 'by', 'at', 'be', 'been', 'run', 'search', 'searched']);
+const covWords = (t) => new Set(String(t || '').toLowerCase().match(/[a-z0-9]+/g)?.filter((w) => !COV_STOPWORDS.has(w)) ?? []);
+
+function dedupeFollowUps(coverage) {
+  const composed = (c) => String(c?.area || '').startsWith(FOLLOW_UP_PREFIX);
+  const written = coverage.filter((c) => !composed(c));
+  if (!written.length) return coverage;
+  return coverage.filter((c) => {
+    if (!composed(c)) return true;
+    // The directive is the note's opening clause — the same string the area was clipped from, unclipped.
+    const directive = covWords(String(c.note || '').split('—')[0]);
+    if (!directive.size) return true;
+    // A COMPLETED SEARCH NEVER STANDS IN FOR AN UNCOMPLETED ONE. This is the discriminator the first
+    // version lacked, and it hid a real gap from a client on a delivered page.
+    //
+    // The composed row exists to say a planned search never ran. Suppressing it requires another row
+    // saying THE SAME THING about the same search — so the row that suppresses must itself be open. A
+    // row reporting a search that RAN is reporting the opposite, and the two are not interchangeable
+    // however many words they share.
+    //
+    // Found on a real run, driven on the shipped renderer: a completed saturation probe into
+    // third-party dolphin-word rights suppressed the uncompleted exact-word register search for DOLPHIN,
+    // because both areas contain "dolphin". The client then read a coverage section that mentioned the
+    // word and disclosed nothing left undone, and the suppressed row was the page's only disclosure of
+    // it. That is exactly the failure this function's header calls the one worth avoiding, and the
+    // header was right while the code was not.
+    //
+    // WHAT THIS STILL CANNOT DO, said rather than implied: it is word containment, so two genuinely
+    // different OPEN searches sharing every word of a short directive would still collapse to one. The
+    // discriminator a reader would want is which search a row names, and the rows carry no identity to
+    // join on — that is why the issue's own wording is "name the same search" rather than a rule. The
+    // narrowing here is the strongest one the data supports, and it errs toward keeping both.
+    return !written.some((w) => {
+      if (COV_STATE[w?.state]?.cls === 'ok') return false;   // a searched-and-clean row reports the opposite
+      const theirs = covWords(w.area);
+      return [...directive].every((word) => theirs.has(word));
+    });
+  });
+}
+
 function coverageGrid(coverage) {
+  coverage = dedupeFollowUps(coverage);
   if (!coverage.length) return '';
   const cell = (c) => {
     const s = COV_STATE[c.state] || COV_STATE.note;
@@ -1753,7 +1830,7 @@ document.addEventListener('keydown',function(e){if(e.key==='Escape'){var pop=doc
 function markAssessmentBlock(ma) {
   if (ma == null) return '';
   const structured = typeof ma.distinctiveness === 'object' || typeof ma.connotation === 'object';
-  const SEC = `<div class="sec"><span class="num">✦</span><h2>The mark itself</h2><span class="note">standing read of the applicant's own mark — advisory, carries no rating</span></div>`;
+  const SEC = `<div class="sec"><span class="num">✦</span><h2>The mark itself</h2><span class="note">how strong the name is on its own</span></div>`;
   if (!structured) {
     const dist = String(ma?.distinctiveness ?? '').trim(), conn = String(ma?.connotation ?? '').trim();
     if (!dist && !conn) return '';
@@ -2130,7 +2207,7 @@ export function renderHtml(parsed, findings = [], coverage = [], opts = {}) {
   const clNotice = (clNoticeText && CASE_LAW_BY_ORD.size)
     ? `<div class="panel" style="padding:12px 16px;margin:0 0 12px"><p style="margin:0 0 4px;font-weight:700;font-size:13px">Session-wide notice</p><div style="font-size:13px">${renderProse(clNoticeText)}</div></div>`
     : '';
-  const CL_SEC = (n) => `<div class="sec" id="common-law"><span class="num">${n}</span><h2>Common-law &amp; marketplace</h2><span class="note">unregistered-use signals — not register rights</span></div>
+  const CL_SEC = (n) => `<div class="sec" id="common-law"><span class="num">${n}</span><h2>Common-law &amp; marketplace</h2><span class="note">who is using similar names, registered or not</span></div>
   ${clNotice}${clBody}`;
   const hasCL = Boolean(clBody || clNotice);
   let findingsSections, covNum;
@@ -2269,7 +2346,7 @@ ${opts.nav || ''}
   ${ruledOutSection(ruledOut, recordsByUri)}
 
   <!-- doc-52 §3 WHAT ONLY YOU CAN CLOSE — forward decisions, plain English, after the findings. -->
-  ${buckets.you ? `<div class="sec" id="only-you"><span class="num">✔</span><h2>What only you can close</h2><span class="note">forward decisions only you can make — each tied to a finding above</span></div>
+  ${buckets.you ? `<div class="sec" id="only-you"><span class="num">✔</span><h2>What only you can close</h2><span class="note">decisions that need you</span></div>
   <div class="panel actions"><div class="actgrp act-you">${renderProse(buckets.you.body)
     .replace(/\[Time-critical\]\s*/gi, '<span class="src cl" style="margin-right:6px">Time-critical</span> ')
     .replace(/\[Open question\]\s*/gi, '<span class="src" style="margin-right:6px">Open question</span> ')
@@ -2287,14 +2364,32 @@ ${opts.nav || ''}
 
   <!-- doc-52 §4 SCOPE & WHAT WE DIDN'T SEARCH — one collapsible section, last; replaces "Checks we ran"
        + "Methodology" + the coverage grid. Nothing here leads. -->
-  ${scopeSection(buckets.ran, coverage, opts.coverageJudgment, secs['Methodology'], DISPOSITION_MODE ? [] : contextNotes, fm, recordsByUri.size > 0, findings.length > 0)}
+  ${scopeSection(buckets.ran, coverage, opts.coverageJudgment, secs['Methodology'], DISPOSITION_MODE ? [] : contextNotes, fm, recordsByUri.size > 0, findings.length > 0,
+    // WHETHER A REGISTER-INDEX ENTRY IS ACTUALLY ON THIS PAGE, mirroring the registration render's own
+    // second disjunct rather than restating it loosely: a cited registration with no fetched body, which
+    // is the state that draws the "(register-index entry)" label. The provenance paragraph explains that
+    // label, so it renders where the label can and stays off every page where it cannot.
+    findings.some((f) => (f?.owner?.registrations ?? []).some((r) => r?.uri
+      && (recordsByUri.size > 0 || !(r.status || r.filed || r.expiry || (r.classes && r.classes.length))))))}
 
   ${askAiHtml}
 
   <footer>
     <span>${productName ? `${esc(productName)}. ` : ''}${FRAMEWORK
-        ? `Working draft for legal review. Risk bands (${esc(FRAMEWORK.title)}): <span class="mono">${esc(FRAMEWORK.bands.map(b => b.label).join(' / '))}</span> — the framework in force's own vocabulary, one word per finding on every surface. Internal notes are review-only and removed on export.`
-        : 'Working draft for legal review. Risk levels: <span class="mono">LOW / MANAGEABLE / MEDIUM / HIGH / VERY HIGH</span> (one vocabulary on every surface); the <span class="mono">Level A–E</span> · <span class="mono">Composite 1–5</span> codes beside them are the internal legal shorthand. Internal notes are review-only and removed on export.'}<br>Matter ${esc(fm.matter || '')}${fm.run ? ` · ${esc(fm.run)}` : ''}.${fm.rated_under ? `<br>Rated under: <span class="mono">${esc(fm.rated_under)}</span>.` : ''}${fm.run_under_project ? `<br>Run under project: <span class="mono">${esc(fm.run_under_project)}</span>.` : ''}</span>
+        // TWO SENTENCES, and that count is the ruled shape rather than a consequence of trimming.
+        //
+        // Two things left. The band note — "the framework in force's own vocabulary, one word per
+        // finding on every surface" — is a note about how the renderer works, printed on every report a
+        // client receives; the framework's NAME is on the "Rated under" line below, once, which is
+        // where a reader who wants it will look.
+        //
+        // AND "Working draft for legal review.", which is a separate decision and is recorded as one.
+        // A delivered clearance is not a draft, and a document that calls itself one on every page is
+        // describing its own status inaccurately to the person paying for it. Raised in review because
+        // the first version of this comment argued only the band note and left the reader to infer that
+        // the status line had gone along for the ride.
+        ? `Risk bands: <span class="mono">${esc(FRAMEWORK.bands.map(b => b.label).join(' / '))}</span>. Purple notes are for the reviewing lawyer and are removed on export.`
+        : 'Risk bands: <span class="mono">LOW / MANAGEABLE / MEDIUM / HIGH / VERY HIGH</span>. Purple notes are for the reviewing lawyer and are removed on export.'}<br>Matter ${esc(fm.matter || '')}${fm.run ? ` · ${esc(fm.run)}` : ''}.${fm.rated_under ? `<br>Rated under: <span class="mono">${esc(fm.rated_under)}</span>.` : ''}${fm.run_under_project ? `<br>Run under project: <span class="mono">${esc(fm.run_under_project)}</span>.` : ''}</span>
     ${logoLockup({ mark: 16 })}
   </footer>
 </div>

package/driver/reference-strip-signatures.mjs

@@ -30,6 +30,26 @@ export const SIGNATURES = [
     // the strip's residue always leaves whitespace after the hyphen.
     re: /\bpre-\s+[a-z]/,
   },
+  {
+    name: "a parenthesis opening on a comma",
+    // THE THIRD RESIDUE, and the floor could not see it for two years because the first two are
+    // WORD-level — a bare possessive, a dangling `pre-` — and this one is PUNCTUATION. It looks like
+    // ordinary code to a reader scanning for broken English, which is exactly why a census built from
+    // the shapes somebody had noticed reads like a census of the whole problem.
+    //
+    // Where the removed reference was the entire content of a parenthesis, nothing is left but `(,)`.
+    // Where it opened one, the sentence now begins on a comma: `(, 2026-08-21)`. Two ran off the end of
+    // their line.
+    //
+    // THE LOOKAHEAD IS THE WHOLE PRECISION AND IT IS DERIVED, NOT GUESSED. `(,` also occurs in code —
+    // inside a character class (`[(,=:…]`, `[;{\s(,]`) and in an alternation (`(,|$)`) — where those two
+    // characters are syntax rather than damage. Every code instance is followed by a regex metacharacter
+    // and no residue instance is, so the exclusion is `|`, `]` and `=` rather than a list of files that
+    // would go stale. Measured against the tree as it stood before the repair: 123 matches, which is the
+    // residue count the finding reported, and 0 after it. A signature that reproduces the number it was
+    // derived from is one that is reading the same thing.
+    re: /\(\s*,(?![|\]=])/,
+  },
 ];
 
 // THE RULE'S OWN DEFINITION IS THE ONLY EXEMPTION, and it is named rather than pattern-matched.

package/driver/search-policy.mjs

@@ -207,7 +207,7 @@ export const PRODUCT_POLICIES = {
       // 199 of those same 420 carry one. The driver now reads this row and can cut on that tier
       // (doubt-selection.mjs).
       //
-      //, owner-ruled 2026-08-23, product by product (reached this branch as an overwatch relay on
+      //, owner-ruled 2026-08-23, product by product (reached this branch on
       // that thread, not as a comment from the owner's own hand — the box has one `gh` identity).
       // It is the P2 column of that table's `placement-inquiry trace` row — the row whose typed key is
       // the placement tier. This stage's OWN row reads `bands 1+2 / band 1` on FINDING CLASS, which is
@@ -877,7 +877,7 @@ export const RECIPE_KEYS = [
  * The saved-search SCOPE block — where the machinery points, as against `base`/`components`, which
  * choose which machinery runs.
  *
- * This is what makes a saved search a saved SEARCH rather than a saved depth. "Zephyr Beverages knockouts — US
+ * This is what makes a saved search a saved SEARCH rather than a saved depth. "Drinks knockouts — US
  * focus" is a label over exactly this: base `knockout`, scope `{jurisdictions:["US"]}`. Without it a
  * saved search could only ever restate a level that is already one click away, which is why the recipe
  * store existed for weeks with nothing worth putting in it.
@@ -1066,7 +1066,7 @@ let recipeCache = null;
  * THE STORE IS NAMED, NEVER GUESSED. `CLEAROTRON_RECIPES_DIR` unset means this deployment has no saved
  * searches — not that it should use the ones bundled with the source.
  *
- * `driver/recipes/` ships synthetic demos for two FICTIONAL customers (aurora, zephyr) so the dev
+ * `driver/recipes/` ships synthetic demos for two test accounts so the dev
  * cockpit and the tests have something to render. It used to be the fallback when the env var was
  * unset, which is a foot-gun that only fires in production: the real deployment does not set the
  * variable, so switching saved searches on there would have surfaced invented customers inside the

package/driver/skills/blind-frame/SKILL.md

@@ -27,7 +27,7 @@ Decompose the mark into its element(s) and name the **dominant element** (the sp
 
 - **Drop** characters: shorten the element (VELTRIN → VELTRI). A dropped letter is the commonest missed-cluster cause — the shorter root is its own crowded field.
 - **Add** characters / **composite**: the element living inside a larger mark (DELPHI Diagnostics, Osler Delphi, Delphic). A composite that shares your dominant element is on the board.
-- **Phonetic / homophone**: sound-alikes (ZEPHYR / ZEFFYR / ZEPHUR).
+- **Phonetic / homophone**: sound-alikes (PHAROLIS / FAROLIS / PHAROLLIS). Carry the `ph`/`f` pair in particular: it sounds identical, files under a different letter, and survives no letter-distance measure — which is the whole reason this class is separate from the two above.
 - **Neighbour**: a one-keystroke real-word or famous-mark neighbour (CHROME on a NOVAPULSE clearance). A famous neighbour is carried for diligence even when off-field.
 
 For each, give the value, the direction, and one line of rationale.

package/driver/skills/knockout-assess/SKILL.md

@@ -119,6 +119,90 @@ Measured tone only — no "extremely difficult", "most dangerous", "massive", "e
 colour communicates urgency. No quantitative claims from research ("major streaming hit", never
 "294M streams"; "significant market presence", never revenue figures).
 
+## Plain language — the two-register rule
+
+The report goes to a lawyer who layers advice on top, and that lawyer's client reads the same page. The
+band, the summary, the basis line and the one-liners are the whole product for the second reader. They
+were the hardest lines on the page.
+
+**Everything a reader sees before opening a fold is written for the client's business owner.** Ordinary
+nouns, one idea per sentence, no sentence over 25 words, the conclusion first. On this product that is:
+`chunkSummary`, `basis`, `factors`, `counterFactors`, `mitigation`, every finding's `net`, every
+`registerReads[].read`, the `purpleNotes`, and `standardCaveats`.
+
+**Inside a fold the lawyer's vocabulary is allowed** where a plain word would lose precision — a
+finding's `basis`, the provenance, the long `assessment`. Even there, a term is explained the first time
+it appears on the page.
+
+The rule is the test, not the list. Ask of every noun: *does the reader already own this word?* These
+are worked examples of the one failure, not its boundary:
+
+| Instead of | Write |
+|---|---|
+| proprietor | owner |
+| subsisting | live |
+| senior | earlier, or came first |
+| specification | goods list |
+| DELPH-formative | names built on DELPH- |
+| prevail | win |
+| citable prior rights | earlier marks the office can raise against you |
+| vulnerable to a non-use attack | could be cancelled for not being used |
+| on the record as it stands | on what we found |
+| the marks-and-goods comparison | same name, same goods |
+| the confusion comparison meets on every limb | same name, same goods, same shops |
+| belt-and-braces classes | extra classes |
+| dispatch, instructed | the request, what was asked |
+| lane | class, or channel — whichever you mean |
+| chunk | never; say the batch, or these names |
+
+The target is the level of these, each the standard for its line:
+
+> **Basis.** "ORBIT is already the name of two satellite-tracking apps on the same app stores, and of an
+> established satellite-communications company. Any of them would likely win a dispute over this name
+> for this software. The word is a weak mark for these goods, which is why this is High and not Very
+> High."
+
+> **A finding's `net`.** "Same name, same goods, and their filing came first in every territory we
+> searched. We see no argument against it."
+
+> **The batch opener.** "One name screened: ORBIT, rated High."
+
+**Shortening by dropping the reason is not the fix.** The "why" stays, in plain words. A visible
+line that is short because it no longer says why is worse than the long one it replaced, and it
+passes every length rule on this page while telling the reader less.
+
+**Say it once.** A caveat, a limit or a finding belongs in one place. Four `standardCaveats` that each
+restate "this is not a clearance" are one caveat and three repetitions — and the report's scope block
+already carries that sentence in the renderer's own words, so a caveat repeating it is dropped before
+the reader sees it. Write the one thing the scope block does not say, or write none.
+
+**A note is verb-first, one line, and about one of two things.** Write each `purpleNotes` entry as an
+instruction to the reviewing lawyer, opening on the verb. Every note is about the REQUEST — what was
+asked, and whether it holds together — or about the NAME. The report prints the first kind at the top,
+above the conflicts, and the second under that name's cards, so a note that mixes the two lands in one
+place and reads oddly in it. Write two notes.
+
+A note about the request NAMES the request in the note — "the request", or "what we were asked". That is
+not a formality: the report sorts the two kinds by what the note talks about, so a request note that
+never mentions the request is filed under the name and prints in the wrong place.
+
+> "Check the request. The client is described as a beverages and supplements business, but we were asked
+> to screen satellite-tracking software in Class 9. We screened the software. If beverages is the real
+> business, this screen looked at the wrong market."
+
+> "Ask the client whether it already uses ORBIT. The request does not say, and the client's own earlier
+> use would change the picture."
+
+A note about the name opens on what the lawyer should do about the name:
+
+> "Pull EG Tech's full goods list at clearance. It is the record most likely to change the picture in
+> either direction."
+
+> "Search Classes 42 and 38 in their own right. Both carry live ORBIT filings, not spillover from
+> Class 9."
+
+A note that restates a finding already on the page is not a note. Cut it.
+
 ## The per-mark opening read (`assessment`)
 
 Each mark's report is delivered on its own, and `assessment` is the first thing its reader meets —

package/driver/skills/matter-frame/SKILL.md

@@ -75,11 +75,11 @@ You do not write a file. Hand the frame back by calling `record_matter_frame`; t
 
 ### Scope jurisdictions — search wide, cite narrow (instructed scope honored; worldwide / brand-signalled scope leans wide + discloses)
 
-Two scopes live here, and the doctrine is **narrow at citation, never silently at search**: the **search scope** (where the register sweep looks) must be wide enough to catch the conflict; the **citation scope** (what the report flags and ranks) is where rights legally matter. The failure to avoid is the PETCARY miss — *silently* pinning a globally-signalling brand to one country, so the real EU/UK/US conflict is never even searched. Derive both from THIS matter; a customer profile selects the **risk framework** only — it never sets territory.
+Two scopes live here, and the doctrine is **narrow at citation, never silently at search**: the **search scope** (where the register sweep looks) must be wide enough to catch the conflict; the **citation scope** (what the report flags and ranks) is where rights legally matter. The failure to avoid is the pinned-scope miss — *silently* pinning a globally-signalling brand to one country, so the real EU/UK/US conflict is never even searched. Derive both from THIS matter; a customer profile selects the **risk framework** only — it never sets territory.
 
 - **Instructed scope is honored (narrow or wide).** When the client names territories — a list, or "X only" — that is the scope for BOTH search and citation; do not override a client who genuinely wants a narrow scope (a sweep of a country with no instructed interest and no reach is wasted). The profile's `defaultJurisdictions`, when present, is the *customer's own standing instruction* — treat it like an instructed set.
-- **Worldwide, or the brand's own signals point broader → the SEARCH widens (it never silently narrows).** When the instruction is worldwide, OR the brand signals broader use — a global gTLD (a `.io`/`.com` launch), an investor / expansion announcement, stated target markets, a genuinely global customer base — the **search set includes the major markets (US / EU / UK / CN / JP) plus the signalled markets**. Decide which to actually cite and rank at **selection** (where rights matter), and **disclose** any material market you could not fully cover (a `coverage-limited` row — never a silent clean). The one move forbidden: quietly pinning an unpinned, globally-signalling brand to a single country (the PETCARY miss). **The cost guard stays:** an abstract *"the sector tends to be global"* is **not, by itself, the widener** — the widener is a CONCRETE signal (a worldwide instruction, or the brand's own global footprint), so a deliberately local matter stays local.
-- **Genuinely unpinned, no global signal → reason the likely scope, LABEL it inferred, and DISCLOSE it.** Read the product / customer base / channels and scope to where the brand plausibly operates; never silently default to the requester's home country (that is the PETCARY mechanism). Where reach is plausibly broad, lean wide; where clearly local, scope local — either way set `Scope basis: inferred` and record a one-line `Scope assumption:` so a narrowing is visible and the coverage gate can clamp + disclose it.
+- **Worldwide, or the brand's own signals point broader → the SEARCH widens (it never silently narrows).** When the instruction is worldwide, OR the brand signals broader use — a global gTLD (a `.io`/`.com` launch), an investor / expansion announcement, stated target markets, a genuinely global customer base — the **search set includes the major markets (US / EU / UK / CN / JP) plus the signalled markets**. Decide which to actually cite and rank at **selection** (where rights matter), and **disclose** any material market you could not fully cover (a `coverage-limited` row — never a silent clean). The one move forbidden: quietly pinning an unpinned, globally-signalling brand to a single country (the pinned-scope miss). **The cost guard stays:** an abstract *"the sector tends to be global"* is **not, by itself, the widener** — the widener is a CONCRETE signal (a worldwide instruction, or the brand's own global footprint), so a deliberately local matter stays local.
+- **Genuinely unpinned, no global signal → reason the likely scope, LABEL it inferred, and DISCLOSE it.** Read the product / customer base / channels and scope to where the brand plausibly operates; never silently default to the requester's home country (that is the pinned-scope mechanism). Where reach is plausibly broad, lean wide; where clearly local, scope local — either way set `Scope basis: inferred` and record a one-line `Scope assumption:` so a narrowing is visible and the coverage gate can clamp + disclose it.
 - **In scope by reach.** A territory also counts when a right is **legally effective in an instructed territory by any route** — filed there; an international (Madrid) registration **designating** it; a regional/supranational right covering it (an EUTM covers every EU member; an instructed EU member is covered by an EUTM); a treaty / priority effect. Tag such a territory `in-scope-by-reach` and name the route. Reason the route from the right — never assume it.
 - **Excluded.** Territories you considered and set aside — neither instructed, nor brand-signalled, nor a major on a worldwide matter — name each, the reason, and a **reopen trigger** (a right or signal pointing there surfaces). A hit effective ONLY outside the scope set is out of *citation* scope (drop it from findings); but a market the brand actually signals belongs in the SEARCH set, not here.
 - **Primary vs only.** If the instruction names territories of "primary" / "first" interest WITHOUT "only", treat the named ones as the citation core but **let the search lean wide** to the majors / brand-signalled markets (the "primary" wording signals more may matter), and **record the assumption** — a one-line `Scope assumption: <text>`. (A single clarifying question is acceptable instead; the recorded default never blocks the run.)
@@ -88,7 +88,7 @@ Two scopes live here, and the doctrine is **narrow at citation, never silently a
 
 *Worked illustrations:*
 *— Instructed "Switzerland and the EU, only" → search CH + the EUTM/EU layer (+ any Madrid designation reaching them); majors beyond (CN/JP/US/UK) are out of scope — an honored narrow instruction (`Scope basis: instructed`).*
-*— A brand on a `.io` domain with an investor deck naming a US/EU launch and no explicit territory list → lean wide: search US/EU/UK/CN/JP + the named launch markets; cite where rights matter; disclose any gap (`Scope basis: inferred`). This is the PETCARY fix — do not pin it to CH.*
+*— A brand on a `.io` domain with an investor deck naming a US/EU launch and no explicit territory list → lean wide: search US/EU/UK/CN/JP + the named launch markets; cite where rights matter; disclose any gap (`Scope basis: inferred`). This is the pinned-scope fix — do not pin it to CH.*
 *— A local artisan, national-only product, no global signal → scope the home market, `Scope basis: inferred`, `Scope assumption:` recorded — narrow but disclosed, never silent.*
 
 ### Off-field sectors
@@ -111,7 +111,7 @@ Two scopes live here, and the doctrine is **narrow at citation, never silently a
 ### Sector-convergence flags
 - Sectors off-field today where commercial trajectories may bring them adjacent
 - Brief reason
-- Example: "Aurora Interactive's broader AI / cloud AI narrative could theoretically bring vector-DBs adjacent to game-dev tooling, but Aurora dev kit is specifically game-tooling not LLM-tooling; convergence path exists but weak"
+- Example: "Foxglade Interactive's broader AI / cloud AI narrative could theoretically bring vector-DBs adjacent to game-dev tooling, but Foxglade dev kit is specifically game-tooling not LLM-tooling; convergence path exists but weak"
 
 ### Machine lines the task message dictates
 
@@ -132,7 +132,7 @@ driver's fixed query shapes:
 
 ## Reasoning posture
 
-- When in doubt about an **off-field / adjacency** decision, INCLUDE rather than exclude — matter-frame should not silently filter a *field*; downstream review (`placement-inquiry`) can deprioritise later with reasoning. **Jurisdiction scope follows its own rule (see *Scope jurisdictions*): search wide, cite narrow.** An instructed-narrow scope is honored; a worldwide or brand-signalled scope widens the SEARCH to the majors + signalled markets; an inferred scope is labelled and disclosed. Do not silently pin a globally-signalling brand to one country (the PETCARY miss), and do not widen a deliberately-local matter on abstract "the sector is global" reasoning (a wasted sweep).
+- When in doubt about an **off-field / adjacency** decision, INCLUDE rather than exclude — matter-frame should not silently filter a *field*; downstream review (`placement-inquiry`) can deprioritise later with reasoning. **Jurisdiction scope follows its own rule (see *Scope jurisdictions*): search wide, cite narrow.** An instructed-narrow scope is honored; a worldwide or brand-signalled scope widens the SEARCH to the majors + signalled markets; an inferred scope is labelled and disclosed. Do not silently pin a globally-signalling brand to one country (the pinned-scope miss), and do not widen a deliberately-local matter on abstract "the sector is global" reasoning (a wasted sweep).
 - Be concrete about WHY for each item. A senior lawyer reading matter-context.md should be able to disagree with specific items and see exactly where your reasoning broke — not just see a conclusion.
 - If you find yourself rating something as in-lane that a senior lawyer would obviously drop, surface the tension rather than smoothing it.
 

package/driver/skills/matter-frame/watchlist-reference.md

@@ -47,6 +47,6 @@ watchlists come from in any case, and is why this file was never authority.
 
 ## Cross-sector
 
-- **Aurora Interactive** — `major_brand_owners`. Broad AURORA / NEBULA / VANGUARD families;
-  on an Aurora Interactive-adjacent matter watch the relevant family token and name
+- **Foxglade Interactive** — `major_brand_owners`. Broad FOXGLADE / NEBULA / VANGUARD families;
+  on a Foxglade Interactive-adjacent matter watch the relevant family token and name
   ecosystem partners with their partnership context rather than as bare conflicts.

package/driver/skills/prelim-common-law/SKILL.md

@@ -173,7 +173,7 @@ For game-title rows, the `developer_of_record` and `publisher_of_record` columns
 | Finding | Source / Platform | URL | Notes |
 |---|---|---|---|
 | Sony "Pulse Elevate" portfolio | Sony products | https://... | Sony uses "Elevate" in audio products; flagged for prelim-register cross-check |
-| Aurora "Borealis" console "Raise Your Play" tagline (prior usage) | Aurora Interactive marketing | https://... | Client's own prior use — note as supportive |
+| Foxglade "Borealis" console "Raise Your Play" tagline (prior usage) | Foxglade Interactive marketing | https://... | Client's own prior use — note as supportive |
 
 ### PR / reputational risk
 

package/driver/skills/prelim-search/SKILL.md

@@ -259,7 +259,7 @@ The driver runs the delivery stage on **every** completed run — the search is
 
 **Methodology lives in the Excel Methodology tab, NOT in the email body.** Do not include paragraph-length descriptions of search approach, sub-skills invoked, variants generated, etc. in the client-facing email. That bloat is what the render-layer split fixes.
 
-**The email is a COVER NOTE; the HTML report is the single master document (wp50).** The house default for every customer: the email carries only the headline risk tier, the report link, and any surviving scope/verdict/handling flags plus reviewer's open questions — no findings body, no client-voice prose, no hand-holding preamble. Client-voice findings live in the **HTML report** (the one surface the client reads). The last exception — Aurora's review-table overlay (`delivery.email:'table'`) — is DELETED as of 2026-07-28, along with the knob that asked for it: a second full findings surface in the mail was the seam that let per-conflict tiers diverge from the report, and on the knockout lane it shipped internal purple notes over the wire. A lawyer who needs a bespoke, forwardable client mail asks the assistant to draft one from the run's `report-data.json` — formatting is judgement, and it belongs where judgement lives, not in a profile enum. The operative delivery spec is [delivery-contract.md](delivery-contract.md) + the driver's `report-synthesis` stage. (The `client-summary` stage, which re-voiced the findings into a separate client-facing document, is RETIRED as of 2026-08-01 — the one report is the one surface.)
+**The email is a COVER NOTE; the HTML report is the single master document (wp50).** The house default for every customer: the email carries only the headline risk tier, the report link, and any surviving scope/verdict/handling flags plus reviewer's open questions — no findings body, no client-voice prose, no hand-holding preamble. Client-voice findings live in the **HTML report** (the one surface the client reads). The last exception — a customer's review-table overlay (`delivery.email:'table'`) — is DELETED as of 2026-07-28, along with the knob that asked for it: a second full findings surface in the mail was the seam that let per-conflict tiers diverge from the report, and on the knockout lane it shipped internal purple notes over the wire. A lawyer who needs a bespoke, forwardable client mail asks the assistant to draft one from the run's `report-data.json` — formatting is judgement, and it belongs where judgement lives, not in a profile enum. The operative delivery spec is [delivery-contract.md](delivery-contract.md) + the driver's `report-synthesis` stage. (The `client-summary` stage, which re-voiced the findings into a separate client-facing document, is RETIRED as of 2026-08-01 — the one report is the one surface.)
 
 Structure (content shared across templates):
 

package/driver/skills/prelim-search/report-prose.md

@@ -19,6 +19,88 @@ writes lives in that stage's own file — the finding sentence and the grouped r
 [synthesis-rules.md](synthesis-rules.md), the card and section shape in
 [delivery-contract.md](delivery-contract.md). What is below is general and is stated only here.
 
+## Two registers, and the reader of the first one is not a lawyer
+
+**The reader is a lawyer who layers advice on top — and that lawyer's client reads the same page.** The
+band, the summary, the basis line and the one-liners are the whole product for the second reader, and
+they were the hardest text on it: single sentences of seventy-odd words in the vocabulary of the
+profession.
+
+So the page has two registers, and which one a line is written in is decided by whether the reader has
+to open something to see it.
+
+**DEFAULT-VISIBLE TEXT CARRIES NO LEGAL OR ENGINE VOCABULARY.** Default-visible means anything a reader
+meets before opening a fold: the summary and the opening line, the basis for the rating, the points for
+and against and what would soften them, the one sentence under each name, the four answers, the
+reviewer's notes, the caveats, the coverage rows and the lines saying what needs a decision. Ordinary
+nouns. One idea per sentence. **No visible sentence over 25 words.** The conclusion first.
+
+Which stored fields those are is not prose's business and is not listed here — `DEFAULT_VISIBLE_FIELDS`
+in `driver/plain-register.mjs` names them for both products, in one place, so a field renamed once does
+not leave a doctrine file quietly describing a shape that no longer exists.
+
+**INSIDE A FOLD THE PROFESSION'S VOCABULARY IS ALLOWED**, where a plain word would lose precision: the
+card's detail paragraph, provenance, the drill bullets. Even there a term is glossed at first use on the
+page. Nothing is removed from the drill and the workbook is unchanged.
+
+### The swaps, as worked examples rather than a banned list
+
+A list of forbidden words is not the mechanism and must never become one. These are what the plain form
+sounds like; the instruction is always to rewrite the sentence, never to substitute the word and leave
+the rest of a lawyer's sentence standing around it.
+
+| written for a lawyer | what the reader needs |
+|---|---|
+| proprietor | owner |
+| subsisting | live |
+| senior | earlier, or came first |
+| specification | goods list |
+| DELPH-formative | names built on DELPH- |
+| prevail | win |
+| citable prior rights | earlier marks the office can raise against you |
+| vulnerable to a non-use attack | could be cancelled for not being used |
+| on the record as it stands | on what we found |
+| the marks-and-goods comparison | same name, same goods |
+| the confusion comparison meets on every limb | same name, same goods, same shops |
+| belt-and-braces classes | extra classes |
+| dispatch, instructed | the request, what was asked |
+| lane | class, or channel — whichever is meant |
+| chunk | never; it is an engine word |
+
+### The standard, in full sentences
+
+A basis line, rewritten: *"ORBIT is already the name of two satellite-tracking apps on the same app
+stores, and of an established satellite-communications company. Any of them would likely win a dispute
+over this name for this software. The word is a weak mark for these goods, which is why this is High and
+not Very High."*
+
+An answer, rewritten: *"Blocked. An identical earlier mark for the same goods stops registration in
+Switzerland, the EU and the US. Below that, earlier DELPH- marks in EU class 5 and US class 42 can be
+raised against the application."*
+
+A card's detail — allowed the fold's vocabulary, still written plainly: *"Same name, same goods, and
+their Swiss filing came first in every territory we searched. We see no argument against it."*
+
+A note, rewritten: *"Ask the client whether it already uses ORBIT. Its own earlier use would change the
+picture and is not reflected here."*
+
+**Shortening by dropping the reason is not the fix.** The "why" stays, in plain words. A visible line
+that is short because it no longer says why is worse than the long one it replaced.
+
+### What reads this, and what does not
+
+**No delivery gate fails on any of it, and no report is ever marked for it.** The reviewing stage that
+already rejects engine vocabulary applies this test to the default-visible fields and hands back a
+rewrite, in the same pass and the same voice it uses for everything else. A hit is a sentence rewritten.
+It is never a disclosure to the client, never a run failure, and it moves no band, no evidence and
+nothing that is searched — this is presentation.
+
+The reviewer is helped by `driver/plain-register.mjs`, which offers the plain form beside the term it
+found and never decides anything. **It cannot flag the mark the run is clearing**: half of these words
+are ordinary English and several — PREVAIL, SENIOR, SPECIFICATION — are perfectly good trademarks, so
+every term the run is about is removed from the text before it is read. A check that could not tell a
+mark from the profession's vocabulary would put its noise on the one report where it matters most.
+
 ## Fact · assessment · prescription
 
 Three different things, and only two of them belong in a report.

package/driver/skills/prelim-search/risk-framework-demo.manifest.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "framework_key": "demo",
   "title": "Demo Brand Owner risk framework",
-  "source_deck": "Demo Brand Owner risk framework, doc 50 shape",
+  "source_deck": "Demo Brand Owner risk framework, authored in-house for the demonstration account",
   "entity_label": "Demo Brand Owner",
   "bands": [
     { "label": "Very High", "tone": "severe" },

package/driver/skills/prelim-search/risk-framework-triage.manifest.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "framework_key": "house-triage",
   "title": "House knockout triage ladder (Stage 0)",
-  "source_deck": "Ported from the interactive knockout-searches skill's 5-tier rating system (SKILL.md rating table + calibration rules), doc 50 shape",
+  "source_deck": "Cordillera house triage scale for knockout screening, authored in-house; five rating tiers",
   "entity_label": "the client",
   "bands": [
     { "label": "Very High", "tone": "severe" },

package/driver/skills/prelim-search/risk-framework.manifest.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "framework_key": "house-default",
   "title": "Generic default risk framework",
-  "source_deck": "Generic house default — IP Risk Assessment Framework.pptx (Privileged & Confidential), completed by the reviewing lawyer 2026-08-31; supersedes the 2026-07-05 transcription (doc 50), which was partial",
+  "source_deck": "Cordillera house risk framework, authored in-house and reviewed by counsel; 2026-08-31 revision",
   "entity_label": "the company",
   "bands": [
     { "label": "Very High", "tone": "severe" },

package/driver/skills/prelim-search/synthesis-rules.md

@@ -14,7 +14,7 @@ Across the synthesis, two postures are load-bearing:
 
 3. **Optics is annotation, not a rating.** Partner-relationship, channel-conflict, PR, and reputational concerns — however prominently `matter-context` or the manifest raise them — are surfaced as client-facing annotations (the separate PR / reputational section below; a "relationship-level heads-up"). PR is a separate category, **never rated on the framework's bands**, and an existing business relationship is an *either-way* practical factor, not a band multiplier. The rating answers what the framework in force asks — anchored in *if this party sued us, would they win?*, set by the consumer-confusion read (mark-as-whole × G&S). Never let optics/PR/partner/size move the band; annotate beside it.
 
-4. **The framework in force rates the matter (doc 50).** Every run reads exactly one risk framework — **the customer's own framework if the profile has one on file, else the house default. Nothing in between.** That framework is the customer's own legal judgment written down: reason each conflict *with* it — its band definitions (Legal position × Practical position × Potential outcomes), or its matrix where it states one — and state the rating as **its band word, verbatim**. It is a reasoning authority, never a lookup table: no numeric thresholds, no score-to-band mapping, no vocabulary borrowed from another framework. **The band follows the words** — state the likelihood in plain words first (*"the prior owner is likely to win, though credible defences exist"*), then give the band those words require under the framework's own definitions; the prose read and the band are one judgment and may not disagree. Where the framework states **ceilings or matrix mappings, honour them exactly as written** — they are that framework's own anti-escalation mechanism, and no practical or optics factor lifts a rating past what its stated method yields. A conflict the client **clearly wins with no material risk is not a rated conflict at all** (most frameworks' lowest band still describes *real* residual risk — nuisance claims, weak strategic complaints, registration obstacles — never clear wins): surface it unrated as commercial awareness if worth knowing, else omit it. Voice the client side as the framework's **entity** names it (*"the company"*, *"Zephyr/Nimbus/Kestrel"*, *"Aurora Interactive"*). The three-question discipline stays: **legal risk** (*would they win?* — the confusion read net of merits defences), **practical risk** (*would they act?* — enforcement reality), and **impact** (*if they did, what follows?*). The framework's band definitions integrate the first two — reason both, in that order, through its own terms. **Impact stays client-surfaced, never rating-moving**: name the consequences for the client to weigh (we do not conclude acceptability), beside the band, exactly as before.
+4. **The framework in force rates the matter (doc 50).** Every run reads exactly one risk framework — **the customer's own framework if the profile has one on file, else the house default. Nothing in between.** That framework is the customer's own legal judgment written down: reason each conflict *with* it — its band definitions (Legal position × Practical position × Potential outcomes), or its matrix where it states one — and state the rating as **its band word, verbatim**. It is a reasoning authority, never a lookup table: no numeric thresholds, no score-to-band mapping, no vocabulary borrowed from another framework. **The band follows the words** — state the likelihood in plain words first (*"the prior owner is likely to win, though credible defences exist"*), then give the band those words require under the framework's own definitions; the prose read and the band are one judgment and may not disagree. Where the framework states **ceilings or matrix mappings, honour them exactly as written** — they are that framework's own anti-escalation mechanism, and no practical or optics factor lifts a rating past what its stated method yields. A conflict the client **clearly wins with no material risk is not a rated conflict at all** (most frameworks' lowest band still describes *real* residual risk — nuisance claims, weak strategic complaints, registration obstacles — never clear wins): surface it unrated as commercial awareness if worth knowing, else omit it. Voice the client side as the framework's **entity** names it (*"the company"*, *"Coastline/Nimbus/Kestrel"*, *"Foxglade Interactive"*). The three-question discipline stays: **legal risk** (*would they win?* — the confusion read net of merits defences), **practical risk** (*would they act?* — enforcement reality), and **impact** (*if they did, what follows?*). The framework's band definitions integrate the first two — reason both, in that order, through its own terms. **Impact stays client-surfaced, never rating-moving**: name the consequences for the client to weigh (we do not conclude acceptability), beside the band, exactly as before.
 
 ## Contents