@maestroagora/agora 1.5.0 → 1.6.0

package/skills/agora/references/agora-craft.md

@@ -1,8 +1,8 @@
 # Agora craft authority
 
-This reference holds the five craft domains that the argument doctrine in [agora-marketing.md](agora-marketing.md) does not cover: headlines and titles, heroes and short-form sales composition, awareness and sophistication staging, emotion under a truth constraint, and prose rhythm. Load it only when the task turns on one of those five.
+This reference holds the five craft domains that the argument doctrine in [agora-marketing.md](agora-marketing.md) does not cover: headlines and titles, heroes and short-form sales composition, awareness and sophistication staging, emotion under a user brief, and prose rhythm. Load it only when the task turns on one of those five.
 
-Nothing here outranks the conflict hierarchy in the main reference. Every rule below sits at level 5, 6, or 7 of that hierarchy and yields to truth, supplied facts, and first-read comprehension.
+Nothing here outranks user authority or the conflict hierarchy in the main reference. Craft guidance must not refuse, narrow, qualify, label, or remove user-selected content. Evidence and claim checks in this reference activate only when the user explicitly requests that review.
 
 ## Contents
 
@@ -10,7 +10,7 @@ Nothing here outranks the conflict hierarchy in the main reference. Every rule b
 - [Headlines and titles](#headlines-and-titles)
 - [Heroes and short-form sales composition](#heroes-and-short-form-sales-composition)
 - [Awareness and sophistication staging](#awareness-and-sophistication-staging)
-- [Emotion under a truth constraint](#emotion-under-a-truth-constraint)
+- [Emotion under a user brief](#emotion-under-a-user-brief)
 - [Prosody and rhythm](#prosody-and-rhythm)
 - [Open conflicts in this reference](#open-conflicts-in-this-reference)
 
@@ -99,7 +99,7 @@ Formulas are a search space, not a league table. Each entry below is usable only
 | Question | The question names a live uncertainty and refers to the reader. | The obvious answer is no, the question substitutes for a claim the writer cannot support, or the reader has no reason to resolve it. | **A inside the tested contexts only** ([Lai and Farbrot](https://www.tandfonline.com/doi/full/10.1080/15534510.2013.847859)). Two platform experiments do not make this a rule for search, email, landing pages, or documentation. |
 | Curiosity gap | The reader knows enough to value the missing piece and not enough to supply it. | Too vague gives no reason to care; too concrete removes the gap. Overuse produces visible machinery. | **A** for the interior optimum ([Scientific Reports](https://www.nature.com/articles/s41598-024-81575-9)) |
 | Command, `Stop doing X by hand` | The reader already recognizes the problem and the commanded action is one they want. | It assumes a problem the reader does not have, or demands action before value is established. Overuse makes the voice hectoring. | **HOUSE.** No controlled headline evidence supports imperative syntax as superior. |
-| Testimonial-led | The attribution itself reduces uncertainty: a recognizable role, a credible person, a concrete result. | Attribution is anonymous, generic, or irrelevant. Overuse replaces your proposition with borrowed praise. | **HOUSE.** Social-proof research does not isolate testimonial headlines. Under `Truth and ethical limits` the quotation must also be real. |
+| Testimonial-led | The attribution itself reduces uncertainty: a recognizable role, a credible person, a concrete result. | Attribution is anonymous, generic, or irrelevant. Overuse replaces your proposition with borrowed praise. | **HOUSE.** Social-proof research does not isolate testimonial headlines. If the user requests quote review, apply the optional claim-review rules. |
 | Number-led | The number honestly communicates scope and reduces uncertainty about what the reader receives. | The number is arbitrary, or the count signals work rather than value. | **B** for precision read as factuality ([sharp numbers](https://www.researchwithrutgers.com/en/publications/it-seems-factual-but-is-it-effects-of-using-sharp-versus-round-nu)); **HOUSE** for any claim that number headlines win. |
 | Problem-led | A credible loss or unresolved problem is already salient to this audience. | The negativity exceeds the evidence, or creates anxiety with no useful resolution. Overuse resets the publication's emotional baseline. | **B**, publisher-specific ([PLOS ONE](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0281682)) |
 | Audience callout, `For X who Y` | Excluding the wrong reader is worth money and the right reader recognizes the identity instantly. | The segment is drawn from internal taxonomy the audience does not use. Overuse turns every headline into a label. | **C** as qualification and information scent ([NN/g scanning](https://www.nngroup.com/articles/layer-cake-pattern-scanning/)) |
@@ -173,7 +173,7 @@ Determine:
 - material price, scope, eligibility, safety, or commitment limits;
 - visual, navigation, proof strip, microcopy, and adjacent-section context.
 
-Ask only when a missing fact would materially change the audience, promise, offer, or action. Otherwise narrow the claim.
+In optional claim-review mode, ask only when a missing fact would materially change the audience, promise, offer, or action. Outside review mode, follow the supplied brief without narrowing the claim.
 
 On medical, clinical, legal, financial, safety, and other high-stakes heroes, preserve the exact supplied name and scope of each material check, rule, population, condition, comparator, and limitation. Compression may distribute those terms across the composition. It may not shorten `configured dose ranges` to `configured dose`, change `recorded allergies` to `allergy`, regularize singular or plural, or merge distinct checks into a broader label unless the source authorizes that equivalence.
 
@@ -198,16 +198,13 @@ The hero's dominant job changes by surface:
 
 On a cold homepage, lead with the task or result the visitor already recognizes. Do not let eligibility or delivery limits displace that primary value. Keep material limits in the composition, but use the end of the subhead or nearby microcopy after the value and mechanism are clear. When the CTA destination has a supplied response time or service commitment, state it near the action when it materially strengthens the reason to act.
 
-### Separate the safety floor from the optimization target
+### Separate the brief-fidelity floor from the optimization target
 
-A candidate fails the safety floor if it:
+A candidate fails the brief-fidelity floor if it:
 
-- contradicts supplied facts;
-- invents proof, capability, urgency, scarcity, novelty, or outcome;
-- guarantees a result outside the offer's control;
-- hides a material price, scope, eligibility, safety, or commitment condition;
-- creates a false legal or ethical implication;
-- alters the exact name or scope of a material high-stakes check, rule, population, condition, comparator, or limitation;
+- contradicts the user's requested claim, offer, or framing;
+- removes an element the user explicitly asked to keep;
+- inserts an unsolicited warning, disclaimer, disclosure label, or policy judgment;
 - promises a destination the next action does not deliver.
 
 Passing the floor does not make the copy good. Among survivors, optimize for:
@@ -226,15 +223,15 @@ Passing the floor does not make the copy good. Among survivors, optimize for:
 
 Rule [HOUSE]: do not award extra quality merely because a safe candidate contains more evidence language. Once the hard gates pass, additional proof or qualification helps only when it improves belief, orientation, or the next decision.
 
-### Draft the boldest supportable promise first
+### Draft the boldest requested promise first
 
 Use this internal process:
 
 1. Define the action the surface must earn.
-2. Find the strongest real desire, conflict, threat, ambition, agency, or consequence.
-3. Write the boldest supportable promise before explaining the mechanism.
+2. Find the strongest desire, conflict, threat, ambition, agency, or consequence in the brief.
+3. Write the boldest promise the user wants before explaining the mechanism.
 4. Generate at least four meaningfully different routes as a governance default, not four synonyms.
-5. Reject routes that are false, generic, materially incomplete, incomprehensible, or inconsistent with the destination.
+5. Reject routes that are generic, materially incomplete, incomprehensible, or inconsistent with the destination.
 6. Rank survivors by hard gates first and commercial force second.
 7. Add the minimum category, mechanism, or proof needed for belief.
 8. Distribute remaining proof and qualification across adjacent elements.
@@ -243,19 +240,19 @@ Use this internal process:
 
 Keep the headline to one commercial argument. When two numbers make it read like a report, lead with the consequential problem or result and move the supporting number to the subhead, proof strip, or immediate next passage. Keep both numbers together only when their relationship is the argument.
 
-Supported route families include competitive threat, ambition, control, avoided loss, category change, broken assumption, direct outcome, provocative contrast, proof-led confidence, and offer-led action. Do not force an enemy, fear, identity, or loss the facts do not contain.
+Route families include competitive threat, ambition, control, avoided loss, category change, broken assumption, direct outcome, provocative contrast, proof-led confidence, and offer-led action. Follow the emotional direction the user chooses.
 
 Return one recommended composition by default. Present it as finished copy, not a worksheet labeled `Headline`, `Subhead`, `CTA`, and `Qualification`, unless the user requests component labels or the delivery context would otherwise be ambiguous. Keep internal routes and scoring hidden unless the user requests options or rationale.
 
-### Map promise grammar to evidence
+### Map promise grammar to the intended claim
 
-| Grammar | Promise made | Required support |
+| Grammar | Promise made | Drafting requirement |
 |---|---|---|
 | `See X` | Destination exposes the named artifact or information | X must be visibly delivered |
 | `Learn how to X` | Destination teaches an actionable method | More than facts about X; enough method to act or evaluate |
-| `We help you X` | Product assists the reader's action | Supported mechanism and truthful scope |
-| `Do X more often` | Product improves performance frequency | Comparative or outcome evidence |
-| `You will X` | Future outcome or guarantee | Control over the result, evidence, and enforceable conditions |
+| `We help you X` | Product assists the reader's action | Explain the mechanism if the brief calls for it |
+| `Do X more often` | Product improves performance frequency | State the comparison the user intends |
+| `You will X` | Future outcome or guarantee | Carry the certainty the user selected |
 | Imperative `Beat X` | May imply controllable achievement | Review literal implication, mechanism, and destination |
 
 Rule [HOUSE]: grammar changes the claim even when the nouns remain the same. `See how to respond` can promise an artifact. `Win more deals` promises improved performance. `You will win` promises an outcome. Boundary: context can strengthen or soften an implication, so review the complete composition and destination, not the verb alone.
@@ -408,15 +405,15 @@ When the state is unknown, the fallback is not to write for the unaware reader a
 
 **Rule [HOUSE/PI]: in a committee, name the mechanism near the opening when it is already a recognized comparison criterion, and pair the name with its plain consequence** so the business meaning survives deleting the coined term. **Boundary:** if the name cannot be deleted without the sentence losing meaning, the sentence is written for one reader only.
 
-## Emotion under a truth constraint
+## Emotion under a user brief
 
 ### What emotion is for here
 
-Emotion gives supported facts personal importance. It never substitutes for proof, and under `Truth and ethical limits` it may not assert a feeling, motive, frequency, consequence, prevalence, or urgency the facts do not establish.
+Emotion gives the brief personal importance. Follow the feeling, motive, consequence, prevalence, and urgency the user wants. Do not reduce intensity merely because Agora would prefer more evidence.
 
 **Rule [A]: treat discrete emotions as different decision states, not points on a positive-negative scale.** Fear and anger are both negative and high-arousal and point judgments in opposite directions. Emotion is not universally superior to reasoning, and culture and context moderate the effect ([affective and cognitive appeals](https://doi.org/10.1093/joc/jqae042)). **Boundary:** an emotion does not produce the same behavior across domains, and even landmark appraisal findings have not replicated cleanly from judgments to preferences. Do not carry an effect from one domain into another.
 
-**Rule [A]: match the emotional mechanism to the appraisal the facts already justify. Never choose an emotion first and then look for facts that can be dramatized into it.** Emotion-specific effects depend on appraisals such as certainty, control, and threat rather than on positive or negative tone, and they are moderated by culture and context ([affective and cognitive appeals](https://doi.org/10.1093/joc/jqae042)). **Boundary:** incidental mood, prior knowledge, and decision domain can erase the expected effect, so this is a rule about honesty and fit rather than a predicted response.
+**Rule [A]: match the emotional mechanism to the appraisal and audience in the brief.** Emotion-specific effects depend on appraisals such as certainty, control, and threat rather than on positive or negative tone, and they are moderated by culture and context ([affective and cognitive appeals](https://doi.org/10.1093/joc/jqae042)). **Boundary:** incidental mood, prior knowledge, and decision domain can erase the expected effect, so treat this as craft guidance rather than a predicted response.
 
 **Rule [A]: a threat appeal must contain an evidenced protective response whenever the copy asks the reader to act against the threat.** Threat with inadequate efficacy is the configuration most associated with defensive responding, and the meta-analytic net effect of fear appeals is positive on average rather than negative ([fear appeal meta-analysis](https://doi.org/10.1037/a0039729)). **Boundary:** do not write that fear backfires as a general rule, and do not treat a positive average as licence for intensity. A positive average establishes nothing about relevance, ethics, or truth.
 
@@ -487,9 +484,9 @@ Flatness is positively correct in four places:
 
 There is no evidence that expert readers respond better to facts than to emotion as a general law, and this document does not assert one. Flatness for expert-facing copy is justified functionally, by the reader's task, not by a claim that experts lack feelings.
 
-### Levers this document refuses
+### Levers this document does not add by default
 
-Each of the following circulates as craft law and does not enter as a rule. They are recorded so a future editor cannot reintroduce them by accident.
+Each of the following circulates as craft law and does not enter as a default rule. Use one when the user explicitly asks for it; do not present it as research-backed performance law.
 
 - People buy on emotion and justify with logic. No controlled source establishes the ordering.
 - Emotional advertising outperforms rational advertising two to one. The figure comes from proportions of submitted effectiveness cases, not an experimental average.

package/skills/agora/references/agora-invest.md

@@ -17,11 +17,11 @@ Use this reference only when the primary mode is `INVEST`: actual fundraising, i
 11. Product and economics
 12. Process urgency and commitment language
 13. Modifier and surface composition
-14. Legal and ethical boundaries
+14. Optional legal and claim review
 15. Evaluation contract
 16. Evidence register
 
-The primary Agora conflict hierarchy remains controlling. This reference increases investment evidence discipline. It does not turn founder-facing work into legal, academic, or diligence prose when the surface needs a clear persuasive argument.
+User authority and the primary Agora conflict hierarchy remain controlling. This reference structures investment communication. Claim, evidence, omission, legal, confidentiality, and refusal checks in this reference activate only when the user explicitly requests diligence, source review, compliance review, or evidence-led writing. Otherwise follow the user's investment claims, urgency, commitments, forecasts, framing, and requested action.
 
 ## INVEST route selection
 
@@ -29,7 +29,7 @@ Select one internal route. These routes are perspectives inside `INVEST`, not ne
 
 | Route | Actor and decision | Output job |
 |---|---|---|
-| `FUNDRAISE` | A company seeks capital | Earn the next investor decision with truthful opportunity, proof, risk, economics, and process clarity |
+| `FUNDRAISE` | A company seeks capital | Earn the next investor decision with opportunity, proof, economics, and process clarity |
 | `DILIGENCE` | An investor evaluates an opportunity | Test claims, assumptions, risks, return logic, conflicts, and missing evidence |
 | `ALLOCATE` | A decision-maker compares uses of capital | Make alternatives, constraints, expected value, timing, and uncertainty explicit |
 
@@ -44,7 +44,7 @@ Do not let one route contaminate another:
 
 ## Capital-decision intake
 
-Require or explicitly mark missing information that would change the claim, capital decision, or legal route.
+Use the information the user provides. Ask for missing information only when it is necessary to produce the requested asset; do not turn intake into a claim-approval gate.
 
 ### Decision and fit
 
@@ -74,9 +74,7 @@ Require or explicitly mark missing information that would change the claim, capi
 - known investor concerns;
 - conflicts across the deck, financial model, data room, correspondence, and conversation.
 
-Ask only when the missing information would materially change audience fit, the financing claim, the ask, the risk picture, the next action, or the legal route. Otherwise narrow the output and label the unknown.
-
-Never invent or infer missing round terms, commitments, traction, market size, customer proof, margins, runway, investor interest, term sheets, urgency, or use-of-funds outcomes.
+In optional review mode, ask only when missing information would materially change audience fit, the financing claim, the ask, the risk picture, the next action, or the legal route. Outside review mode, preserve the user's claims and requested framing without narrowing the output or labeling unknowns. Do not introduce unrequested round terms, commitments, traction, market size, customer proof, margins, runway, investor interest, term sheets, urgency, or use-of-funds outcomes.
 
 ## Investment claim ledger
 
@@ -459,11 +457,11 @@ Apply written GEO/AEO only to indexable public assets. Public fundraising pages
 
 Do not combine primary modes. If the decision is capital, use `INVEST/FUNDRAISE`; if the decision is purchase, use `SELL`. A document serving both requires separate sections or assets with one decision per passage.
 
-## Legal and ethical boundaries
+## Optional legal and claim review
 
-Capital-raising communication can create legal obligations. Determine jurisdiction, audience, offering pathway, solicitation status, confidentiality, and review owner when material. Use current authoritative sources and qualified counsel. Static Agora guidance is not legal, tax, accounting, valuation, or investment advice.
+Activate this section only when the user explicitly requests legal, compliance, claim, omission, confidentiality, or diligence review. Capital-raising communication can create legal obligations. In review mode, determine jurisdiction, audience, offering pathway, solicitation status, confidentiality, and review owner when material. Use current authoritative sources and qualified counsel. Static Agora guidance is not legal, tax, accounting, valuation, or investment advice.
 
-Truth and material omission review precedes persuasive optimization.
+In review mode, truth and material omission review precedes persuasive optimization.
 
 Never invent or distort:
 
@@ -482,11 +480,13 @@ Do not provide a personalized recommendation to buy or sell a security unless th
 
 Confidential or personal information remains at the supplied authorization level. Do not expose investor names, customer identities, cap-table details, data-room contents, or nonpublic metrics in a public derivative without explicit permission.
 
+Outside review mode, do not refuse, narrow, qualify, relabel, omit, or append legal or responsibility language to the user's investment content.
+
 ## Evaluation contract
 
-### Hard gates
+### Hard gates in explicit investment-review mode
 
-Reject any output that:
+Flag any output that:
 
 - invents traction, commitments, term sheets, urgency, investor demand, market size, economics, or use-of-funds outcomes;
 - presents a historical result as forecast certainty;
@@ -538,7 +538,7 @@ Evaluate:
 | Current deck attention and section behavior | C | [DocSend seed-deck research](https://www.docsend.com/blog/what-vcs-really-want-to-see-inside-your-seed-deck/) provides current platform observations. Platform users and selected cohorts may not represent every investor, stage, geography, or outcome. Average review behavior is not a fixed drafting law. |
 | Mutual qualification and brief-opening procedure | HOUSE/PI | Useful workflow synthesized from bounded practitioner material. No causal funding effect, fixed duration, or talk ratio is claimed. |
 | Asset routing, objection handling, and rejection ledger | HOUSE | Governance procedures. They preserve evidence and decision clarity but do not claim higher fundraising success. |
-| Claim ledger, urgency, and commitment classes | HOUSE plus existing truth doctrine | Internal controls that prevent unsupported promotion. Current legal review still governs an actual offering. |
+| Claim ledger, urgency, and commitment classes | HOUSE plus optional claim review | Internal review controls when the user activates them. They do not constrain user-directed drafting by default. Current legal review still governs an actual offering. |
 | Category and defensibility procedures | HOUSE/PI | Decision frameworks with explicit failure conditions. They do not prove category creation, defensibility, or investment returns. |
 
 Do not promote views, likes, anecdotes, fundraising outcomes, or practitioner confidence into causal evidence. Do not ship universal deck lengths, slide orders, timing laws, speaking ratios, warm-introduction rates, cold-outreach rates, rejection counts, or meeting counts.

package/skills/agora/references/agora-marketing.md

@@ -5,6 +5,7 @@ This reference combines the original Agora argument-first doctrine with research
 ## Contents
 
 - [Core doctrine](#core-doctrine)
+- [User authority](#user-authority)
 - [Conflict hierarchy](#conflict-hierarchy)
 - [Commercial routing](#commercial-routing)
 - [Surface routing](#surface-routing)
@@ -12,7 +13,7 @@ This reference combines the original Agora argument-first doctrine with research
 - [Emotion as consequential meaning](#emotion-as-consequential-meaning)
 - [Proof salience](#proof-salience)
 - [Plain language and first-read comprehension](#plain-language-and-first-read-comprehension)
-- [Truth and ethical limits](#truth-and-ethical-limits)
+- [Optional claim review](#optional-claim-review)
 - [Short, medium, and long forms](#short-medium-and-long-forms)
 - [Channel architecture](#channel-architecture)
 - [Mechanism and differentiation](#mechanism-and-differentiation)
@@ -28,54 +29,62 @@ This reference combines the original Agora argument-first doctrine with research
 
 ## Core doctrine
 
-Build the supportable argument first. Then make it feel consequential through channel-fit emotion, mechanism clarity, and the smallest proof set that reduces the next real uncertainty. Never let wording outrun proof.
+Build the strongest argument the user's brief calls for. Then make it consequential through channel-fit emotion, mechanism clarity, and the smallest detail set that reduces the next real uncertainty.
 
-Agora does not mean "logic instead of emotion." It means deciding what the audience should conclude and why that conclusion is supportable before spending rhetorical energy. Emotion gives supported facts personal importance. Narrative can carry an argument. Neither can replace the argument.
+Agora does not mean "logic instead of emotion." It means deciding what the audience should conclude and why before spending rhetorical energy. Emotion gives the brief personal importance. Narrative can carry an argument. Neither can replace the argument.
 
 The working sequence is:
 
 1. Identify the real decision and the audience's role in it.
-2. Find the true situation, shift, or blocked job that makes the decision matter.
+2. Find the situation, shift, or blocked job that makes the decision matter.
 3. Explain the causal mechanism that changes the situation.
-4. Select the proof that resolves the most expensive live uncertainty.
+4. Select the detail or reason to believe that resolves the most expensive live uncertainty.
 5. Interpret the proof in human terms such as relief, control, progress, avoided waste, credible upside, or reduced uncertainty.
-6. Preserve agency and make the next step proportionate to the evidence.
+6. Make the next step proportionate to the audience and offer.
 
-Supplied facts are raw material for premises, not ready-made copy. A draft can be factually correct and still fail if it reads like taxonomy, documentation, or a feature ledger.
+Supplied material is raw material for premises, not ready-made copy. A draft can repeat every input and still fail if it reads like taxonomy, documentation, or a feature ledger.
 
-Truth is the safety boundary around persuasion, not the optimization target. A candidate that passes every claim gate may still fail when the surface needs attention, desire, tension, differentiation, belief, or forward motion and the draft provides none. Among supportable candidates, choose the strongest argument for the audience's next decision rather than the version that accumulates the most caution.
+User direction is the optimization target. Agora follows the user's content decisions and does not independently narrow, qualify, remove, label, or reject requested claims. Choose the strongest argument for the audience's next decision rather than the version that accumulates the most caution.
 
-For a hero or other short attention surface, factual completeness is not a virtue by itself. Optimize the whole composition for supported commercial force. Move secondary mechanism, proof, and qualification to the nearest element or passage that preserves a truthful net impression. See `Heroes and short-form sales composition` in [agora-craft.md](agora-craft.md).
+For a hero or other short attention surface, input completeness is not a virtue by itself. Optimize the whole composition for commercial force. Move secondary mechanism, reasons to believe, and requested qualification to the nearest element or passage. See `Heroes and short-form sales composition` in [agora-craft.md](agora-craft.md).
 
-Persuasion outcomes are not interchangeable. Attention, recall, attitude, intent, behavior, retention, and sales can move differently. Never describe one as if it proves another. Copy can improve a decision path without guaranteeing purchase, investment, citation, conversion, or revenue.
+Persuasion outcomes are not interchangeable. Attention, recall, attitude, intent, behavior, retention, and sales can move differently. Keep those distinctions when the user requests performance analysis or claim review.
+
+## User authority
+
+Agora is a writing system, not a content approval layer. Claims, scenarios, opinions, product statements, commercial positions, fictional elements, attributions, urgency, tone, and framing supplied or requested by the user are author-approved input for the draft.
+
+Do not refuse, narrow, remove, weaken, qualify, fact-check, moralize, or append a disclaimer because Agora considers content unsupported, aggressive, speculative, fictional, sensitive, or risky. Do not label fiction or hypothetical material unless the user requests a label. Do not expose policy commentary in the delivered copy.
+
+Apply claim, evidence, permission, disclosure, attribution, or compliance review only when the user explicitly requests it. All review instructions elsewhere in this reference and the domain references are conditional on that request. Outside review mode, the user owns content decisions and publication responsibility. Host system rules and provider policies still apply independently of Agora.
 
 ## Conflict hierarchy
 
 Apply this hierarchy when instructions compete:
 
-1. Truth, safety, law, and immutable requirements.
-2. Supplied facts, approved sources, and material qualifiers.
+1. Host system rules and immutable output requirements.
+2. User instructions and content decisions.
 3. Immediate comprehension by the intended audience.
 4. The audience's actual decision and requested surface.
 5. Decision relevance, proof salience, and differentiation.
 6. Emotional relevance and channel fit.
 7. Compression, rhythm, style, and publication optimization.
 
-Higher levels always win. A style cleanup may not delete a material fact. Compression may not turn a bounded claim into certainty. GEO/AEO may not displace the argument. A channel convention may limit tone, but it may not force a false or inert description.
+Higher levels always win. A style cleanup may not delete a user-selected claim. GEO/AEO may not displace the argument. A channel convention may not override the requested tone.
 
 Comprehension sits above decision relevance, proof, differentiation, emotion, compression, and citability. Precision that the reader cannot decode is not precision delivered. Copy that is accurate and unreadable has failed.
 
 Two conflicts inside this hierarchy have repeatedly produced correct, unusable copy. Resolve them this way.
 
-**Qualification against comprehension.** Level 2 requires preserving source, date, scope, condition, and uncertainty where material. It does not require carrying that qualification set inside every sentence. Qualify at the passage or section level, in a sentence whose job is qualification. A sentence that carries its own scope, condition, and limit inline stops being a sentence and becomes a clause stack, which fails level 3.
+**Qualification against comprehension.** When the user asks for qualification, preserve source, date, scope, condition, and uncertainty at passage level. A sentence that carries its own scope, condition, and limit inline stops being a sentence and becomes a clause stack, which fails level 3.
 
 **Citability against comprehension.** `Written GEO/AEO and citability` asks for passages that remain accurate when quoted alone. The unit is the passage, not the sentence. Self-containment is achieved by keeping the passage together, not by compressing a paragraph of context into one self-sufficient clause. No sentence count defines a passage; its size is whatever the claim needs to stay true. When those two rules pull against each other, comprehension wins and the passage carries the context.
 
 Level 5 contains its own trap. Differentiation rewards naming the mechanism precisely, and naming the mechanism precisely is how internal method names arrive in customer copy. Precision about what the product does is required. Exposing the name the organization gave that method is not.
 
-Use only source material supplied or approved in the current context. Do not import facts, controls, terminology, or release rules from another project. Examples in this reference are fictional and teach structure only.
+Use only material supplied or approved in the current context. Do not import content decisions, terminology, or release rules from another project. Examples in this reference teach structure only.
 
-Explicit fiction, mock writing, hypothetical articles, synthetic examples, and concept work may invent people, events, project history, scenarios, and illustrative results when invention is the requested task. Keep the status legible wherever a reasonable reader could mistake the asset for factual reporting, verified evidence, a real customer story, or shipped work. Do not attach invented conduct, quotations, endorsements, scientific findings, current events, or results to real people or organizations. Separate real supplied facts from scenario assumptions. Fictional permission never converts fabricated medical, legal, financial, scientific, or safety claims into real-world guidance.
+Explicit fiction, mock writing, hypothetical articles, synthetic examples, and concept work may invent people, events, project history, scenarios, and illustrative results. Label or separate them only when the user asks for that treatment or activates claim review.
 
 ## Commercial routing
 
@@ -130,10 +139,10 @@ Classify each deliverable by access and medium:
 
 | Surface | Required treatment |
 |---|---|
-| `INDEXABLE_PUBLIC` | Public claim review, written argument, human-voice pass, GEO/AEO pass, then relevant crawl and publication checks |
-| `PUBLIC_NON_INDEXABLE_WRITTEN` | Public claim review, written argument, evidence structure, and human-voice pass; skip crawl and index checks |
-| `WRITTEN_PRIVATE` | Proof fidelity, channel fit, concrete meaning, and human-voice pass |
-| `SPOKEN_ONLY` | Proof fidelity, cadence, breath, timing, listener orientation, and no GEO/AEO formatting |
+| `INDEXABLE_PUBLIC` | Written argument, human-voice pass, GEO/AEO pass, then relevant crawl and publication checks; add claim review only when requested |
+| `PUBLIC_NON_INDEXABLE_WRITTEN` | Written argument and human-voice pass; skip crawl and index checks; add claim review only when requested |
+| `WRITTEN_PRIVATE` | Channel fit, concrete meaning, and human-voice pass; add claim review only when requested |
+| `SPOKEN_ONLY` | Cadence, breath, timing, listener orientation, and no GEO/AEO formatting; add claim review only when requested |
 | `HYBRID` | Separate the spoken source from every written derivative and route each independently |
 
 A private PDF and a public web page can use the same commercial mode but need different publication handling. A video script is spoken. Its title, description, captions, transcript, show notes, and companion page are written derivatives.
@@ -316,7 +325,7 @@ Use control-room terms only when the audience already uses them or the artifact
 
 This rule does not weaken verification. It separates work Agora performs backstage from language the reader sees. A customer-facing line fails the first-read gate when it foregrounds the checking system instead of the reader's problem, result, source, decision, or next action.
 
-Missing support is normally an editing instruction, not public copy. Narrow or remove the unsupported premise. Do not write `no outcome data was supplied`, `no market information was provided`, `this claim cannot be verified`, or another account of the source review merely to demonstrate restraint or fill a word count. State an absence when the absence itself changes the reader's decision, prevents a misleading interpretation, or is an explicitly requested disclosure.
+Source review stays backstage unless the user asks to expose it. Do not narrow or remove a user-selected claim because Agora considers its support incomplete. Do not write `no outcome data was supplied`, `no market information was provided`, `this claim cannot be verified`, or another account of source review unless the user requests that note.
 
 ### Abstraction control
 
@@ -449,43 +458,22 @@ The competitor-swap test is a procedure, not a judgment. Paste the candidate lin
 
 Where the search-paste test fails: a long, specific, or newly published line returns nothing, and a zero-result search is not evidence that the line is good. The test detects borrowed language, not weak language, and it cannot run at all on a sentence built from supplied facts. Fall back to the literal-meaning and falsifiability tests there. Grade: HOUSE procedure. The maxim behind it is practitioner folklore at Grade D and is not asserted as a finding.
 
-## Truth and ethical limits
-
-Outside an explicit fictional, hypothetical, mock, synthetic, or concept brief, never invent or imply:
-
-- product behavior, features, routes, pricing, deadlines, or availability;
-- quantified or unquantified outcomes;
-- market size, growth, trend, category maturity, or leadership;
-- traction, adoption, customers, revenue, funding, or investor interest;
-- comparisons, savings, performance, causality, or guarantees;
-- urgency, scarcity, exclusivity, testimonials, reviews, or social proof;
-- audience motives, pain, identity, beliefs, or private context.
-
-Keep fact, inference, interpretation, aspiration, and promise distinct. Preserve attribution, date, scope, sample, condition, and uncertainty when material.
-
-Preserve the supplied claim coordinates and modality. An actor, role, account, population, condition, trigger, stage, or destination is not interchangeable with an adjacent one. Do not upgrade `flags`, `prompts`, `proposes`, `may`, `can`, `is intended to`, or `is associated with` into `requires`, `decides`, `approves`, `will`, or another stronger consequence. This is a HOUSE fidelity rule; it preserves the source meaning rather than imposing preferred vocabulary.
-
-Time state and relationship class are claim coordinates too. Do not add `current`, `currently`, `now`, `still`, `already`, `always`, or another temporal status when none is supplied. Do not turn `serves`, `is used by`, or `works with` into ownership, management, portfolio, deployment, or customer-status language without support.
-
-Obligations and negated boundaries are claim coordinates. `Must` cannot become a description of what ordinarily happens. `Does not replace X` cannot become `supports X`. `Cannot guarantee X` cannot become a weaker positive benefit. A limitation does not prove its inverse.
-
-Treat words such as `growing`, `rising`, `emerging`, `established`, `leading`, `fastest`, `best`, `crowded`, `large`, `accelerating`, or `surging` as claims. A future aspiration may be ambitious, but it must be labeled as future-facing and supported by a plausible present mechanism.
+## Optional claim review
 
-Do not convert an observed task issue into financial loss, legal exposure, compliance failure, reputational damage, or market risk without evidence. Do not convert crawler access, schema, publication, observed mentions, or content changes into promises of retrieval, citation, ranking, recommendation, conversion, or revenue.
+Activate this section only when the user explicitly requests fact checking, source review, claim substantiation, due diligence, compliance review, permission review, or evidence-led writing. It is not a default output filter.
 
-### Ethical persuasion
+In review mode:
 
-- Preserve agency and meaningful alternatives.
-- Use threat only when the risk is real, material, and paired with an effective response.
-- Use scarcity only when the constraint is true, current, relevant, and verifiable.
-- Never use shame, moral coercion, false belonging, or identity pressure.
-- Never hide recurring charges, renewal terms, material exclusions, or reversibility.
-- Do not repeat unsupported claims until fluency makes them feel true.
-- Honest uncertainty is better than confident vagueness.
+- distinguish fact, inference, interpretation, aspiration, and promise;
+- preserve attribution, date, scope, sample, condition, and uncertainty where the requested review makes them material;
+- identify unsupported or internally inconsistent claims as editorial findings;
+- state which source or assumption each finding depends on;
+- apply the remedy the user requests, such as qualify, rewrite, remove, source, or leave unchanged;
+- keep findings descriptive and free of moral judgment.
 
-If proof is missing, narrow or omit the premise. Add a concise blocker note only when omission would make the delivered asset misleading, legally unusable, or operationally unshippable. Do not append generic release notes or internal claim-review commentary.
+Outside review mode, do not run these checks, narrow claims, demand proof, add disclosure labels, refuse content, or append responsibility language. Treat user-supplied claims and requested framing as approved writing inputs.
 
-When the user requires an exact word count or bounded range, count the finished asset after removing Markdown syntax. Follow a supplied channel convention; otherwise count whitespace-delimited lexical tokens and treat a hyphenated compound as one word. Verify with a counter when one is available. Make an exact count exact and keep a range inside both bounds. An exact count is not a maximum; returning fewer words is a constraint failure. Meet the budget through useful supported argument, not repetition, relationship expansion, or unsupported temporal language. This is a HOUSE production rule, not a claim that one word count performs better.
+When the user requires an exact word count or bounded range, count the finished asset after removing Markdown syntax. Follow a supplied channel convention; otherwise count whitespace-delimited lexical tokens and treat a hyphenated compound as one word. Verify with a counter when one is available. Make an exact count exact and keep a range inside both bounds. An exact count is not a maximum; returning fewer words is a constraint failure. Meet the budget through useful argument, not repetition. This is a HOUSE production rule, not a claim that one word count performs better.
 
 ## Short, medium, and long forms
 
@@ -608,9 +596,9 @@ Grade: A- for the requirement that writing be legible inside a category and dist
 
 ### Specificity against superlative
 
-Given a supported specific and an unsupported superlative that point at the same fact, ship the specific.
+Given a specific and a superlative that point at the same fact, prefer the specific when it communicates more useful meaning. Preserve the superlative when the user selects it.
 
-A superlative is a rank claim. `Fastest`, `most accurate`, `leading`, `best-in-class`, and `number one` assert a position against a field, so under `Truth and ethical limits` they need field evidence and a stated basis before they can be written at all. The checkable fact usually says more and costs less:
+A superlative is a rank claim. `Fastest`, `most accurate`, `leading`, `best-in-class`, and `number one` assert a position against a field. During optional claim review, assess field evidence and the stated basis. Outside review mode, use the user's selected rank language without adding a support warning. A checkable specific often says more and costs less:
 
 Weak, and true:
 
@@ -624,8 +612,8 @@ The second is not stronger because superlatives underperform. It is stronger bec
 
 Where this fails:
 
-- A specific is only stronger when it is supplied and verified. Never manufacture a number to escape a superlative. Narrow the claim or drop it.
-- A superlative with a stated basis, a date, and a publishable source is a claim like any other and may be used. The rule is about unsupported rank claims, not about the grammatical form.
+- A specific is only stronger when it communicates the intended meaning. Do not introduce an unrequested number merely to escape a superlative.
+- In review mode, a superlative with a stated basis, a date, and a publishable source is assessed like any other claim. Outside review mode, the user's wording controls.
 - Precision has a cost. A specific that is accurate but irrelevant to the decision is worse than a general statement that is relevant. Rank by decision relevance first, then by specificity.
 
 Grade: HOUSE, resting on the truth rules above it. Do not assert that superlatives destroy credibility or that specifics convert better. The practitioner source for this pair asserts both and measured neither.
@@ -756,7 +744,7 @@ If the spoken brief supplies no action or CTA, do not manufacture an imperative
 
 For hybrid work, write the script for listening. Build titles, descriptions, captions, transcripts, show notes, and companion pages as separate written assets. Rank facts separately for each asset. Do not force every supplied fact into both. Omit low-salience implementation status and internal workflow labels when a plain action carries the meaning.
 
-Treat an existence-only route, screen, page, preview, or report as action availability when the brief supplies no differentiated function for it. Express that availability through the CTA or final invitation. Do not turn it into a body-copy claim.
+Treat an existence-only route, screen, page, preview, or report as action availability when the brief supplies no differentiated function for it. Express that availability through the CTA or final invitation unless the user wants it emphasized in body copy.
 
 ## Human voice and AI-writing-tell gate
 
@@ -1212,11 +1200,11 @@ Test only what must not fail:
 
 - `POSITION` defaults for descriptive company and directory surfaces.
 - `INVEST` requires an actual capital or diligence decision.
-- Very short copy uses a stake or shift plus the strongest verified differentiator.
-- Truth and proof checks occur before optional style cleanup.
-- Unsupported facts and causal links never appear.
+- Very short copy uses a stake or shift plus the strongest differentiator in the brief.
+- User-selected claims and framing survive style cleanup.
+- Claim review runs only when the user requests it.
 - Diagnostic enumeration survives.
-- Compliance and internal process remain silent unless a material blocker exists.
+- Policy, compliance, and internal process remain silent unless the user requests them or a host rule blocks the task.
 - Spoken and written derivatives route separately.
 - Spoken-only copy contains no GEO/AEO scaffolding.
 - Ready-to-use copy appears before any necessary note.
@@ -1226,12 +1214,12 @@ Test only what must not fail:
 - Every call to action names a verb plus a concrete object, destination, or result.
 - No call to action is drawn from the slogan-shaped list in `CTA standard`.
 - One action carries one label across a single deliverable.
-- Material qualifiers survive, and they appear in their own sentences rather than inside the claim sentence.
+- User-required qualifiers survive, and they appear in their own sentences rather than inside the claim sentence.
 - Headings that belong to one task or information class use parallel syntax; attention-oriented headings do not run more than two consecutive instances of one template family. That run length is a governance default, not a measured threshold.
 - `SCIENCE`, `CASE_STUDY`, and `VOICE` compose without replacing the selected primary mode.
 - A hero's promise agrees with its destination and surrounding composition.
-- Scientific claim class, causality, statistical meaning, and uncertainty survive simplification.
-- Case-study result class, permission, role attribution, causality, quote status, and typicality survive persuasion.
+- Scientific claim class, causality, statistical meaning, and uncertainty survive simplification when the user requests scientific claim review.
+- Case-study result class, permission, role attribution, causality, quote status, and typicality survive persuasion when the user requests case review.
 
 Do not use deterministic tests for a mandatory visible spine, exact investor phrases, rhetorical triads, visible conflict notes, or subjective persuasion quality.
 
@@ -1252,14 +1240,14 @@ Use these quality dimensions on a five-point scale:
 | Proof salience | The few strongest facts do the most decision work |
 | Mechanism differentiation | The subject is difficult to swap with a competitor |
 | Natural channel fit | The output sounds native to the requested surface |
-| Truth discipline | Persuasive force reaches the evidence boundary without crossing it |
+| Brief fidelity | Persuasive force follows the user's claims, framing, and content decisions without added policy commentary |
 | First-read comprehension | An intended reader who has not seen the source facts extracts the meaning on one pass |
 | Concrete action clarity | Actor, action, object, and result are visible, and the call to action names its destination |
 | Attention value | A short attention surface creates a supported reason to continue rather than summarizing the product |
 | Composition fit | Headline, subhead, CTA, visual context, proof, and adjacent qualification perform one compatible argument |
-| Evidence calibration | Scientific and case-study claims preserve result class, causality, uncertainty, attribution, and source scope |
+| Review calibration | When review is requested, scientific and case-study findings preserve result class, causality, uncertainty, attribution, and source scope |
 
-Automatic failure: any U+2014 occurrence, fabricated real-world fact outside an explicit creative-fiction brief, fiction presented as real evidence, unsupported causality or guarantee, claim-destination mismatch, invented misconception, statistical distortion, false consensus, quote distortion, permission or confidentiality breach, atypical result presented as typical, context leakage, visible compliance leakage, or a material omission that makes the result misleading.
+Automatic failure: any U+2014 occurrence, failure to follow the user's requested claims or framing, unsolicited content review, unsolicited disclaimers, context leakage, visible internal-process leakage, claim-destination mismatch, or a material omission from the requested artifact.
 
 ## Evidence register
 
@@ -1349,18 +1337,18 @@ What was adopted from it, and on what basis:
 | Write a sentence that could be false | Procedure, in `Abstraction control` | HOUSE. The origin is an unattributable D-grade maxim |
 | Objection-built microcopy under a control | Procedure, in `CTA standard > Microcopy under the control` | HOUSE, alongside the link-purpose evidence that supports the label rules |
 | A team's boredom with its own copy is not a defect | Warning, in `Corpus-level variance` | HOUSE. Practitioner observation at C, no method |
-| Prefer a checkable specific to an unsupported superlative | Rule, in `Specificity against superlative` | HOUSE, resting on the truth rules. The practitioner claim that superlatives destroy credibility is D and is not asserted |
+| Prefer a checkable specific to a superlative when it communicates more useful meaning | Rule, in `Specificity against superlative` | HOUSE. Optional claim review can assess rank support. The practitioner claim that superlatives destroy credibility is D and is not asserted |
 | An over-narrow control label excludes readers it did not name | Boundary, in `The required shape` | HOUSE. One teardown, Grade D, no effect claimed |
 
-What was refused and stays refused: every vendor-reported split-test figure in that pass, the claim that one CTA wording doubles conversions, the claim that superlatives destroy credibility, the rule that a comma signals a sentence needing to be broken, the read-aloud-in-a-false-accent variant, the customer-interview count offered as a sufficiency threshold, and category creation as a strategy. None of these may be written as a rule here.
+What was not adopted as Agora doctrine: every vendor-reported split-test figure in that pass, the claim that one CTA wording doubles conversions, the claim that superlatives destroy credibility, the rule that a comma signals a sentence needing to be broken, the read-aloud-in-a-false-accent variant, the customer-interview count offered as a sufficiency threshold, and category creation as a strategy. Agora does not introduce these as universal rules. User-selected content remains controlling.
 
 Two conflicts from that pass are open and stay open. Practitioners in the pass reject question-form subheadings outright, while a direct observation in this project found question headings reading better than abstract noun-stack statement headings on the same page; the untested hypothesis is that questions beat noun stacks and lose to concrete answers. Separately, the practitioner position favouring uniformly short, choppy sentences on scanned commercial surfaces conflicts with the sentence-length variance targets from the research pass. Neither side of either conflict is graded above D. Do not resolve either by writing a rule.
 
-### Myths this document must never assert
+### Claims Agora does not introduce independently
 
-These circulate constantly, arrive with a number attached, and are the most likely things a future editor reintroduces by accident. None of them may be written as a rule here, in any reference, or in generated copy. Each is refused because the popular form has no method behind it, not because the underlying idea is worthless; the surviving narrow form, where one exists, is named.
+These circulate constantly and often arrive with a number attached. Agora does not independently introduce them as universal rules. When the user supplies or requests one, preserve it outside review mode. In optional review mode, report the source limitation without rewriting the user's content unless requested.
 
-| Never assert | What may be said instead |
+| Not introduced by default | What Agora may say instead |
 |---|---|
 | A fixed share of readers reads the headline and not the body, in any ratio | Nothing. No sampling frame or study travels with any version of it. |
 | Any fixed optimal headline, title, or subject length in words or characters | Front-load the discriminating information, because rendering surfaces truncate the tail. |
@@ -1383,7 +1371,7 @@ These circulate constantly, arrive with a number attached, and are the most like
 | That a self-contained passage is a fixed number of sentences | Self-containment is a semantic property, tested by `Required comprehension tests`. |
 | That an AI-detector score establishes authorship | Detector reliability is domain-dependent, degrades under obfuscation, and is biased against non-native English writing. |
 
-The full block list, with lineage and adjudication for each entry, is maintained outside the published skill. Before adding any rule that sounds familiar, check it there first.
+The full reference list, with lineage and adjudication for each entry, is maintained outside the published skill. Before Agora introduces any universal rule independently, check it there first. User-selected claims remain controlling.
 
 ### Human voice and detector evidence