@event4u/agent-config 14.22.0 → 15.0.0

package/dist/agent-src/guidelines/prompt-templates.md

@@ -0,0 +1,189 @@
+# Prompt Templates
+
+Reference catalogue of prompt structures the [`prompt-optimizer`](../skills/prompt-optimizer/SKILL.md)
+skill picks from during the **Develop** step of the 4-D methodology.
+Cited by the [`refine-prompt`](../skills/refine-prompt/SKILL.md)
+skill in `mini` mode for stack-aware shaping.
+
+Templates are tools, not dogma. Pick by request type, not by upstream
+whitelist — see the [Rejection note](#rejection-note) at the bottom.
+
+## When-to-pick rubric
+
+| Request shape | First-choice template | Fallback |
+|---|---|---|
+| One-shot technical change (refactor, lint fix) | **RTF** | File-Scope |
+| Multi-file refactor across a codebase | **File-Scope** | RTF |
+| Marketing / brand / tone-heavy copy | **CO-STAR** | CRISPE |
+| Mixed-audience explainer (technical + lay) | **CRISPE** | CO-STAR |
+| Step-by-step explainer / tutorial | **RISEN** | Few-Shot |
+| Pattern-heavy task (classification, extraction) | **Few-Shot** | RISEN |
+| Multi-step reasoning or math | **CoT** | ReAct |
+| Tool-using agent (web search, file ops) | **ReAct** | CoT |
+| Image AI (Midjourney, SD, DALL·E) | **Visual Descriptor** | Reference-Image-Edit |
+| Image edit from a source image | **Reference-Image-Edit** | Visual Descriptor |
+| ComfyUI / node-graph image workflows | **ComfyUI** | Visual Descriptor |
+| Reverse-engineer an existing good prompt | **Prompt Decompiler** | — |
+| Honest critical feedback on a finished artifact (post, design, naming, proposal) — any domain | **Honest Sparring Partner** | CRISPE |
+
+## Text templates
+
+### RTF — Role · Task · Format
+Smallest viable structure. Three lines: who the AI is, what to do,
+how the output should look. Best for one-shot technical asks.
+
+### CO-STAR — Context · Objective · Style · Tone · Audience · Response
+Six-slot structure originally from the Singapore GovTech prompt
+study. Best for copy where audience and tone carry the message.
+
+### RISEN — Role · Input · Steps · Expectation · Narrowing
+Step-explicit shape. Best for tutorials, walkthroughs, and any
+output where the reader follows the prompt's structure.
+
+### CRISPE — Capacity · Role · Insight · Statement · Personality · Experiment
+Six-slot, persona-heavy. Best when the *voice* matters more than
+the structure (creative writing, explainers with a strong narrator).
+
+### CoT — Chain-of-Thought
+Append "Think step by step" or "Reason aloud before answering" to
+any base template. Best for multi-step reasoning, math, planning.
+Pairs well with RTF or RISEN.
+
+### Few-Shot
+Two to five worked examples inline before the actual ask. Best for
+classification, extraction, format-mimicking. Costs tokens — keep
+examples minimal and representative.
+
+### File-Scope
+Codebase-aware variant of RTF. Names the files in scope, the
+allowed-edit list, and the "do not touch" list explicitly. Best for
+agent-driven refactors where blast radius matters.
+
+```
+Role: senior TypeScript engineer
+Files in scope: src/auth/*.ts, tests/auth/*.ts
+Do not modify: src/db/*, package.json, tsconfig.json
+Task: migrate from jsonwebtoken to jose; keep the exported API stable
+Format: unified diff
+```
+
+### ReAct — Reason + Act
+Interleaved thought / action / observation loop. Best for agents
+with tools — web search, file ops, shell. Each cycle:
+
+```
+Thought: <why I need this next step>
+Action: <tool call>
+Observation: <result>
+... repeat ...
+Final Answer: <synthesis>
+```
+
+### Honest Sparring Partner
+Domain-agnostic stance template for getting honest critical feedback on
+a finished artifact — blog post, design draft, naming decision, business
+proposal, care-plan, marketing copy. Works for any role (engineer,
+graphic designer, nurse, founder) because the role slot is filled by
+the user's actual profession, not hard-coded.
+
+Five-slot shape:
+
+```
+Role: <user's domain> — e.g. graphic designer, geriatric nurse, founder
+Stance: honest sparring partner, not yes-man. Push back when something
+        is weak; acknowledge when something is solid; stay silent when
+        there is nothing substantive to add. No flattery openings, no
+        artificial criticism for its own sake.
+Context-fit: ask ONE clarifying question only if real context is missing
+             (role, audience, constraint). Otherwise answer directly.
+Artifact: <the finished thing — paste, link, or describe>
+Ask: <what kind of reaction the user wants — "does the argument hold?",
+     "is the naming clear?", "would this land with audience X?">
+```
+
+**Anti-pattern this rejects:** "what do you honestly think?" prompts that
+either default to praise ("looks great!") or default to manufactured
+criticism ("here are 5 problems...") regardless of whether the work
+warrants either reaction. The stance slot makes the honest-when-warranted
+contract explicit.
+
+**Package equivalents** — inside this agent-config, the
+[`adversarial-review`](../skills/adversarial-review/SKILL.md)
+skill implements the same stance via an Attack-Defend-Revise loop and is
+the right tool when the user submits finished work for a critical take.
+This template is for **end-users prompting their own LLM** (ChatGPT,
+Claude, Gemini) outside this package.
+
+## Image templates
+
+### Visual Descriptor
+Subject · style · composition · lighting · medium · mood · technical
+parameters (aspect ratio, resolution). Best for Midjourney, Stable
+Diffusion, DALL·E from a blank canvas.
+
+### Reference-Image-Edit
+Source image reference + change set + preservation set. Names what
+to change, what to keep, and the desired output framing. Best for
+inpainting, style transfer, character consistency.
+
+### ComfyUI
+Node-graph-aware. Names the workflow nodes (KSampler, CLIPTextEncode,
+VAEDecode) and the parameter intent per node rather than the
+parameter values. Best for advanced SD pipelines.
+
+## Reverse template
+
+### Prompt Decompiler
+Given an existing good output, reconstruct the prompt that would
+produce it. Used to mine prompts from public LLM artifacts. Not a
+shaping template — a forensic one.
+
+## Viral-prompt anti-patterns — what this catalogue deliberately omits
+
+Prompt collections that circulate socially optimise for looking impressive
+on the way in, not for what the target model can act on. None of the
+templates above encodes the three patterns below, and that is a decision
+rather than an oversight — a template is a slot structure, and these three
+are slots the model cannot fill honestly.
+
+| Anti-pattern | Why no template carries it |
+|---|---|
+| **Grandiose persona** — "world's foremost", "legendary", "10× expert" | Every template's role slot takes a *capability* (`RTF` Role, `CRISPE` Capacity, `CO-STAR` Style). A superlative is not a capability: it spends tokens and changes nothing the model does. |
+| **Presupposed canon** — "the 7 laws of X", "the standard X framework", for a body of knowledge that may not exist | A presupposition in the context slot is answered by confabulation, and the invented canon inherits the authority of the frame. `Few-Shot` exists precisely so that a real pattern is *shown* rather than asserted. |
+| **Scope stuffing** — analysis *and* strategy *and* copy *and* a checklist in one prompt | Each template has one Expectation / Objective / Format slot by construction. Four deliverables in one prompt produce four shallow ones; split them, or name the primary. |
+
+The catalogue's own position: a template earns its place by making a
+request *checkable*, not by making it sound authoritative. Where a rough
+prompt carries one of these three, the
+[`prompt-optimizer`](../skills/prompt-optimizer/SKILL.md)
+strips it in its de-inflation sub-step before any template is picked —
+and strips nothing else, because everything outside these three is a
+requirement the author meant. This section is own analysis; it records a
+decision about this catalogue rather than adopting an outside claim.
+
+## Rejection note
+
+An external prompt-collection claims that only five techniques
+are "safe" for production prompting:
+
+- few-shot
+- role assignment
+- structured output
+- constraint-based
+- chain-of-thought
+
+This package **rejects** that whitelist. CO-STAR, RISEN, CRISPE,
+ReAct, and the image-AI templates above are first-class. The
+"5 safe" framing came from a single benchmark on a single LLM
+generation — it does not generalise. See AI Council session
+`agents/runtime/council/responses/prompt-master-mini.json` (2026-05-17) for the analysis behind this rejection. <!-- council-ref-allowed: ADR decision trace -->
+
+The right gate is request-type fit, not technique-whitelist
+membership.
+
+## See also
+
+- [`prompt-optimizer`](../skills/prompt-optimizer/SKILL.md) — engine-outbound; cites this catalogue in its Develop step
+- [`refine-prompt`](../skills/refine-prompt/SKILL.md) — engine-inbound; uses templates in `mini` mode for stack-aware shaping
+- [`prompt-engineering-patterns`](../skills/prompt-engineering-patterns/SKILL.md) — production-LLM prompt patterns (sibling skill, not a catalogue)
+- AI Council session: `agents/runtime/council/responses/prompt-master-mini.json` (2026-05-17) <!-- council-ref-allowed: ADR decision trace -->

package/dist/agent-src/guidelines/redundancy-taxonomy.md

@@ -0,0 +1,208 @@
+# Redundancy Taxonomy
+
+> The one place this package names what duplication *is*, what may be decided
+> about it, and how to tell a second explanation that adds information from one
+> that only adds length. Cited by [`code-clarity`](code-clarity.md) at the
+> authoring moment, by `skill:code-review` at the review moment, and by
+> `skill:code-refactoring` at the refactoring moment. Those three cite it —
+> they do not restate it, because three copies of a redundancy taxonomy would
+> be the defect it describes.
+
+Finding duplication is not a decision. Every finding reaches a **named verdict**
+with a reason, and several of the verdicts keep the duplication. The goal is not
+the lowest clone percentage — it is **one honest authority per shared fact**,
+without marrying independent concepts through a wrong abstraction.
+
+## The classes
+
+**Implementation** — the same code exists twice.
+
+| Class | What it is |
+|---|---|
+| Exact clone | Same tokens. |
+| Renamed clone | Same structure; identifiers or literals differ. |
+| Near clone | Shared core with local additions or deletions. |
+| Structural pattern | Same shape, no copy/paste lineage. |
+| Boilerplate | Framework, protocol, or generated ceremony. |
+| Test repetition | Repeated setup or assertion structure. |
+| Intentional independence | Similar today, meant to diverge. |
+| Wrong abstraction | Already shared, now growing caller flags and modes. |
+
+**Knowledge** — the same *fact* is encoded twice. Usually more actionable than
+raw clone percentage, because a clone can be harmless and a divided fact rarely is.
+
+| Class | What it is |
+|---|---|
+| Knowledge duplication | One business rule, constant, or algorithm encoded more than once. |
+| Policy duplication | One governance decision represented across independent surfaces. |
+| Contract duplication | One external protocol or CLI contract reimplemented instead of consumed. |
+| Delivery-authority duplication | Two authored sources can produce the same shipped artifact. |
+
+**Representation** — the same *meaning* is presented twice to a reader: a
+comment, label, hint, tooltip, placeholder, badge, heading, caption, or toast.
+
+| Class | What it is |
+|---|---|
+| Exact text echo | The same text repeated in the same context. |
+| Paraphrase echo | A second surface restating the first in other words. |
+| Structural narration | Prose naming what the code or UI already shows. |
+| Decorative metadata | An eyebrow, badge, or heading with no scanning or semantic value. |
+| Feedback echo | Status text duplicating already-obvious state. |
+| Accessibility conflict | Removing it would delete required semantic information. |
+
+An accessibility conflict is a **hard guard, never a deletion candidate**. A
+reduction that improves the visual channel by breaking the semantic one is not a
+reduction; it is a defect.
+
+**Naming** — the *dual* of a representation echo. An echo says one meaning twice;
+divergent naming says one meaning with two words, so the reader cannot tell
+whether they are looking at one concept or two. It is a modelling defect rather
+than a style preference: a concept carries one term across the whole model, and
+several terms for one concept is the model telling you it has not decided.
+<!-- harvest:one-language-per-concept-inconsistency-is-a-model-defect -->
+
+| Class | What it is |
+|---|---|
+| Spelling variant | One word, two spellings (`artifact` / `artefact`). No semantic difference; decidable without judgement. |
+| Synonym drift | One concept, several terms. Needs a term map, because the terms may denote different things. |
+| Homonym collision | One term, several meanings. The opposite failure, and usually `keep-duplicated` when the meanings are module-local. |
+
+Naming verdicts: `canonicalize-term` · `keep-distinct` (with the recorded reason
+— an external compatibility value, a quoted name, a genuinely different concept)
+· `defer-for-context`.
+
+**Only a spelling variant is mechanically decidable, and the split between the
+prose layer and the identifier layer is decisive.** Prose is a substitution;
+filenames, symbols and their test and task references are a rename refactor with
+its own blast radius, and the same cluster can be committed to different sides on
+each layer. Measure both before proposing either — the measured example is in
+`agents/evidence/analysis/wording-baseline-2026-08-25.md`, where nothing imports
+across the split and the identifier layer is therefore `keep-duplicated` while
+the prose layer is `canonicalize-term`.
+
+Synonym drift is the class to be slowest about. Words that read as synonyms in
+translation frequently denote different mechanisms — here `route`, `dispatch`,
+`delegate`, `spawn` and `forward` are five mechanisms, not one concept spelled
+five ways — so a sweep over them destroys information the echo classes exist to
+protect.
+
+## The avoid-list — one term, one concept
+
+A homonym collision is only half-diagnosed when it is classified. The other
+half is the **decision**: which concept keeps the word, and what every other
+sense is called instead. This list carries the decided ones. A word is added
+here when the same term has been observed denoting more than one shipped
+mechanism; it is removed only when the collision is gone from the tree, never
+because the entry became inconvenient.
+
+Read the columns as a rename instruction for **prose you write from now on**.
+The identifier layer is decided separately and per cluster, exactly as the
+prose/identifier split above requires — a term may be `canonicalize-term` in
+prose and `keep-distinct` in identifiers, and both verdicts are recorded.
+
+| Term | Concept that keeps the word | Other senses, and what to call them | Identifier verdict |
+|---|---|---|---|
+| `envelope` | The **transport wrapper** around a payload — `OutcomeEnvelope` (a run's terminal outcome, `src/scripts/_lib/outcome_envelope.ts`) and the `CHECKPOINT` envelope a worker capsule rides in. | The **session continuity record** is a **capsule**. The word is not chosen for readability — it is the shipped discriminator (`CAPSULE_SCHEMA_VERSION`, `CAPSULE_VARIANTS = ['worker','main_session']`, `src/scripts/_lib/subagent_capsule.ts`), so the surviving term is read off what ships rather than off what reads best. | `keep-distinct` for now. `MainSessionRecycleEnvelope` and `RECYCLE_ENVELOPE_*` keep their names until a rename is costed on its own; the prose rule binds immediately and the symbols are a separate blast radius. |
+| `handoff` | The **session-to-session continuity handover** a developer invokes — the `handoff` verb and the `/agent-handoff` command. | The lint over senior-tier skills' `## Related Skills` edges is a **cross-wing skill link**, never "a handoff". | `keep-distinct`, recorded reason: `lint_handoffs.ts` mirrors a ported CLI contract (ADR-200) whose name is an external surface. Its module docstring already says "cross-wing", which is the disambiguation the prose rule now requires everywhere else. |
+
+**Why a list and not a linter.** `lint_canonical_terms` decides *spelling*
+pairs, where one side is mechanically wrong. A homonym is not mechanically
+wrong anywhere — every occurrence is a legitimate word for a legitimate
+concept, and only the reader's inability to tell them apart is the defect. A
+gate that flagged `envelope` would flag the entry that is supposed to survive.
+So this list is enforced at review, by citation, and its cost of being ignored
+is the cost the taxonomy already names: the model telling you it has not
+decided.
+
+## Why any of this is worth a gate at all
+
+Generated code trends toward duplication rather than reuse: measured
+longitudinally over roughly 211 million changed lines, copy/pasted code rose from
+8.3 % to 12.3 % of changes over the period assistance became common.
+<!-- harvest:ai-agents-raise-copy-paste-share --> The pressure this document
+resists is therefore not a hypothetical — it is the default direction of the tool
+writing the code, which is why `keep-duplicated` needs to be a recorded verdict
+rather than an unstated outcome.
+
+Where enforcement follows, the shape is already known: separate the term list
+from the rules, and control false positives by **syntax awareness** — skip
+frontmatter, fenced code and inline code rather than matching inside them.
+<!-- harvest:prose-linter-vocabulary-accept-reject --> `check_md_language.ts`
+already carries exactly that skip machinery.
+
+## The verdicts
+
+For implementation and knowledge findings: `extract-local` · `extract-module` ·
+`canonicalize-knowledge` · `canonicalize-contract` · `single-copy-delivery` ·
+`data-drive` · `compose-strategy` · `generate` · **`keep-duplicated`** ·
+`defer-for-evidence` · **`de-abstract`**.
+
+For representation findings: `keep` · `drop` · `consolidate` ·
+`rewrite-for-signal` · `accessibility-block` · `defer-for-context`.
+
+`keep-duplicated` and `de-abstract` are **successful outcomes**, not failures to
+act. A wrong abstraction costs more than the duplication it replaced, so a
+recorded decision to leave two copies alone — or to split one shared unit back
+apart — closes a finding as legitimately as an extraction does. What is not
+allowed is silence: a finding with no recorded verdict stays open.
+
+## Before sharing an implementation
+
+1. Is it the same knowledge, or two facts that currently look alike?
+2. Would both copies change for the same reason?
+3. Is there one honest domain name that fits every call site?
+4. Can the common core stay free of caller-specific flags and modes?
+5. Is the dependency direction healthy?
+6. Does this reduce maintenance risk, or only line count?
+7. Are public contracts preserved, and do tests prove behavioural equivalence?
+8. Is this generated or protocol ceremony that should stay explicit?
+9. **If the two copies diverged tomorrow, would that be a defect or legitimate
+   evolution?**
+
+A "legitimate evolution" answer to the last question is decisive: prefer
+independence, verdict `keep-duplicated`.
+
+## The Information Delta Test
+
+Before adding any comment, docblock, label, hint, tooltip, placeholder, badge,
+caption, empty-state line, or explanatory sentence, in code or in a user
+interface:
+
+- **A — Information delta.** What fact becomes unavailable if this text is
+  deleted? A non-obvious reason, an invariant, a required format, a unit, a
+  consequence, a safety warning, a recovery action, a privacy implication, an
+  unfamiliar concept, an accessibility name, or necessary grouping all count. If
+  the answer is "nothing", delete it.
+- **B — Representation delta.** Is that fact already carried adequately by a
+  nearby representation — the name, the type, the component structure, the
+  semantic element, the visible control text, an icon, a test? If so,
+  consolidate; do not repeat.
+- **C — Channel preservation.** Would deleting it weaken visual comprehension,
+  semantic accessibility, or both? Never optimise one channel by breaking the
+  other.
+- **D — Persistence.** Will it still be true after the next ordinary refactor?
+  Text describing the current implementation rather than the durable constraint
+  is noise with a delay fuse.
+- **E — Actionability.** For user-facing copy: does it change what the reader
+  understands, chooses, enters, expects, or does next? If not, it is a strong
+  deletion candidate.
+
+The rule is **not** "less text". It is: if removing the text loses no
+information in any required channel, remove it — and if the information is
+required, express it once, in the strongest native form available. A visible
+form label is required information, so it stays; a placeholder repeating that
+label is an exact text echo, so it goes.
+
+## Legacy is baseline, new duplication is the finding
+
+Existing duplication does not fail an unrelated change. A review or refactor
+raises a finding when a change **introduces** high-confidence knowledge, policy,
+contract, or delivery-authority duplication — or when it touches a surface that
+already carries some. Anything else is debt with a measurement, not a blocker.
+
+## See also
+
+- [`code-clarity`](code-clarity.md) — the authoring moment; comment discipline
+  and the banned classes this test generalises.
+- [`abstraction-thresholds`](abstraction-thresholds.md) — how much repetition
+  earns an abstraction, per artifact class.

package/dist/agent-src/guidelines/wing4-handoff.md

@@ -0,0 +1,127 @@
+# Wing-4 Handoff
+
+Wing-4-specific prose for the four load-bearing senior-skill chains
+in the Money / Strategy / Operations cluster. The mechanical contract
+— initiator → delegated(input) → output-artifact, lint rules, worktree
+boundary — lives in
+[`docs/contracts/cross-wing-handoff.md`](../contracts/cross-wing-handoff.md).
+The cross-wing routing prose (when to hand off at all, L4 / C8
+boundary, decision tree) lives in
+[`docs/guidelines/cross-role-handoff.md`](cross-role-handoff.md). The
+Wing-3 sibling — chains inside GTM / Growth — lives in
+[`docs/guidelines/gtm-handoff.md`](gtm-handoff.md). This guideline
+covers **what crosses each Wing-4 boundary**, **what the typed
+artifact looks like**, and **who owns the failure mode when the
+chain breaks**.
+
+Cycle / dangling / tier-mismatch enforcement is not duplicated here —
+The `lint-handoffs` task (per cross-wing-handoff § 4) is the mechanical
+gate.
+
+## Chain 1 — money → strategy
+
+Three-step chain that turns unit-economics cognition into a
+build-buy-partner verdict. Finance cluster owns the first two steps;
+the cluster line crosses on the handoff to Strategy.
+
+```
+unit-economics (O1)
+  → scenario-modeling (O4)
+    → build-buy-partner (P1)
+```
+
+| Step | Hands off when | Typed artifact crossing the boundary | Failure-mode owner |
+|---|---|---|---|
+| O1 → O4 | CAC / LTV / contribution-margin / payback-period cognition locked for the segment. | `unit-economics-frame.md` — CAC / LTV ratio, contribution margin, payback band, burn-multiple verdict, segment scope. | O1 owns drift: a margin frame O4 cannot stress-test = O1's unit definition was wrong scope. |
+| O4 → P1 | Three-statement scenarios + sensitivity bands + optionality reasoning locked across at least two cases. | `scenario-set.md` — base / upside / downside cases, sensitivity table, decision-relevant variables, optionality cost per case. | O4 owns drift: scenarios without an optionality-cost row force P1 to re-derive build-vs-buy economics. |
+
+P1 self-closes against `build-buy-partner.md` — insource-vs-outsource-
+vs-acquire verdict, integration-cost band, dependency-risk score,
+exit-cost analysis.
+
+## Chain 2 — strategy → people
+
+Two-step chain that turns a build-buy-partner verdict into an
+org-design shape. Strategy cluster ships the verdict; People-Strategy
+cluster reads it as input and owns the structure decision.
+
+```
+build-buy-partner (P1)
+  → org-design (Q1)
+```
+
+| Step | Hands off when | Typed artifact crossing the boundary | Failure-mode owner |
+|---|---|---|---|
+| P1 → Q1 | Insource-vs-outsource verdict + dependency-risk profile + integration-cost band locked. | `build-buy-verdict.md` — verdict (build / buy / partner / acquire), capability scope, dependency-risk score, integration cost, exit cost, optionality preservation note. | P1 owns drift: a verdict without exit-cost reasoning leaves Q1 designing teams against an unowned constraint. |
+
+Q1 self-closes against `org-design-shape.md` — team-shape (functional /
+cross-functional / squad), span-of-control band, Conway's-law alignment
+note, reorg-cost ledger.
+
+## Chain 3 — people → EM
+
+Two-step chain that specializes a generalized hiring loop for
+engineering. People-Strategy cluster owns the generalized cognition;
+Engineering-Manager cluster owns the engineering specialization.
+
+```
+hiring-loop-design (Q-generalized, composed inside `org-design`)
+  → hiring-loop-design × eng-context (S2)
+```
+
+| Step | Hands off when | Typed artifact crossing the boundary | Failure-mode owner |
+|---|---|---|---|
+| Q → S2 | Generalized loop stages + calibration-design + signal-vs-noise audit locked at people-strategy level. | `hiring-loop-shape.md` — stage list, per-stage signal, calibration cadence, bar-raiser logic, signal-vs-noise findings. | Q owns drift: a generalized loop without a calibration cadence forces S2 to invent one for engineering and the cognition diverges from the rest of the org. |
+
+S2 self-closes against `eng-hiring-loop.md` — eng-specific stage
+specialization (screen → take-home / system-design / coding /
+behavioral / leadership), per-stage rubric, bar-raiser assignments,
+candidate-throughput target.
+
+## Chain 4 — finance → GTM
+
+Cross-wing chain — the only Wing-4 chain whose endpoint sits in
+Wing 3. Finance owns the **cognition**; RevOps owns the **call**.
+Interface-first-stub per iter-2 OQ4: O2-interface ships before the
+H10 sibling can start, parallel to O2 implementation.
+
+```
+forecasting (O2)
+  → forecast-accuracy (H10, Wing 3)
+```
+
+| Step | Hands off when | Typed artifact crossing the boundary | Failure-mode owner |
+|---|---|---|---|
+| O2 → H10 | `forecast-construction-shape` ADR locked: top-down vs bottom-up enum, confidence-band signature, retro-loop signature. | `forecast-band.json` — commit value, best-case value, pipeline value, confidence band, retro signature, construction-shape tag. | **Interface contract owned by O2** (per cross-wing-handoff § 5 / W4 chain): if the ADR drifts, O2 breaks the contract, not H10. Mirrors `gtm-handoff.md` Chain 2 H10 → O2 framing from the Wing-3 side. |
+
+H10's parallel-development rule (starts after O2-interface ≥ 100 %,
+runs in parallel with O2 implementation) is recorded in the
+`road-to-money-strategy-ops.md` O2 entry, the
+`road-to-gtm-and-growth.md` H10 entry, and the cross-wing-handoff
+contract — not duplicated here.
+
+## Reading the failure-mode column
+
+The column answers one question: **when a downstream skill cannot
+do its job, which upstream skill rewrites its artifact?** The owner
+is the **upstream** skill, not the consumer — drift is always a
+producer-side fix. This mirrors the W3 sibling and the W4 / W3
+forecasting chain in the contract (O2 owns the interface; H10 only
+consumes it).
+
+## See also
+
+- [`docs/contracts/cross-wing-handoff.md`](../contracts/cross-wing-handoff.md)
+  — typed-handoff mechanical contract; the `lint-handoffs` task enforces
+  cycles, dangling references, and tier mismatches over the graph.
+- [`docs/guidelines/cross-role-handoff.md`](cross-role-handoff.md)
+  — when to hand off at all, how to phrase the routing, L4 / C8
+  boundary.
+- [`docs/guidelines/gtm-handoff.md`](gtm-handoff.md) — Wing-3 sibling
+  for the brand → channel, discovery → pipeline, and funnel →
+  retention chains.
+- [`docs/contracts/context-spine.md`](../contracts/context-spine.md)
+  § Wing-4 slots — `fiscal-period`, `org-stage`, `regulatory-regime`;
+  every chain step opts into ≥ 1 slot or carries an ADR opt-out.
+- [`docs/contracts/adr-wing4-context-spine.md`](../contracts/adr-wing4-context-spine.md)
+  — durable record for the Wing-4 slot extension.

package/dist/agent-src/personas/README.md

@@ -102,7 +102,7 @@ cast (usually Core-6 for review skills, empty for others).
 ## Related
 
 - [`../docs/contracts/persona-schema.md`](../../docs/contracts/persona-schema.md) — locked schema (Core / Specialist)
-- [`../docs/guidelines/agent-infra/role-contracts.md`](../../docs/guidelines/agent-infra/role-contracts.md) — workflow modes personas compose with
+- [`../guidelines/agent-infra/role-contracts.md`](../../docs/guidelines/agent-infra/role-contracts.md) — workflow modes personas compose with
 - [`../rules/artifact-drafting-protocol.md`](../rules/artifact-drafting-protocol.md) — mandatory per new persona
 
 ## See also — sibling voice primitives

package/dist/agent-src/personas/_template-specialist/persona.md

@@ -83,7 +83,7 @@ action with a clear pass/fail outcome.
 
 *Author note (delete before publishing): this template targets the
 7-section specialist spine locked in
-[`docs/contracts/persona-schema.md`](../../../docs/contracts/persona-schema.md).
+[`docs/contracts/persona-schema.md`](../../docs/contracts/persona-schema.md).
 Stay within the **≤ 100 line** budget (file total, including
 frontmatter). Replace every `{placeholder}` with concrete content.
 Run the project's CI / lint pipeline before commit.*

package/dist/agent-src/personas/product-owner.md

@@ -72,7 +72,7 @@ designs; holds the line on outcome, scope, and decision provenance.
   confidence forces split-recommendation.
 - Every cross-lens trade-off routes through `stakeholder-tradeoff`
   (L4) **before** code; in-flight conflicts in code review escalate
-  C8 → L4 per [`cross-role-handoff`](../docs/guidelines/cross-role-handoff.md).
+  C8 → L4 per [`cross-role-handoff`](../guidelines/cross-role-handoff.md).
 - A ticket without switch-event or evidence routes to
   [`customer-research`](../skills/customer-research/SKILL.md) before
   refinement.

package/dist/agent-src/rules/active-remediation.md

@@ -106,7 +106,7 @@ mentioned one. This rule ships `instruction-only` — the honesty boundary
 [`ui-audit-gate`](ui-audit-gate.md) state for their own obligations. The ladder
 is the control; skipping it is caught by nothing.
 
-Body migrated to [`guideline:agent-infra/active-remediation-mechanics`](../docs/guidelines/agent-infra/active-remediation-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — per-tier fix-now/note+ask/follow-up-PR criteria, version-gated modernization, anti-nagging guardrails.
+Body migrated to [`guideline:agent-infra/active-remediation-mechanics`](../guidelines/agent-infra/active-remediation-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — per-tier fix-now/note+ask/follow-up-PR criteria, version-gated modernization, anti-nagging guardrails.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also

package/dist/agent-src/rules/architecture.md

@@ -44,9 +44,9 @@ Fires on new files, classes, controllers, modules, or any structural decision ab
 ## Reusable components + object-oriented design
 
 - **Think in reusable units** — decompose UI into composable components; reuse the project's primitives / shared abstractions before building; extract a new unit only when the same shape repeats (audit existing first, per [`ui-audit-gate`](ui-audit-gate.md)).
-- **Object-oriented where it reduces complexity** — in an object-oriented / class-based codebase, encapsulation, single responsibility, composition over inheritance, behavior-rich domain objects, and design patterns *where they earn their place* are the high-priority default — never speculative abstraction, and never imposed on a functional / pipeline codebase (detect + defer to its paradigm). Bounded by [`minimal-safe-diff`](minimal-safe-diff.md) + [`senior-engineering-discipline`](senior-engineering-discipline.md), which **win on conflict**: a reviewer should be able to name the concrete duplication or second axis of change the abstraction removes (rule of thumb: two real repetitions before you extract a **code-level** abstraction; UI classes carry deliberately higher bars — per-class canon: [`abstraction-thresholds`](../docs/guidelines/abstraction-thresholds.md)).
+- **Object-oriented where it reduces complexity** — in an object-oriented / class-based codebase, encapsulation, single responsibility, composition over inheritance, behavior-rich domain objects, and design patterns *where they earn their place* are the high-priority default — never speculative abstraction, and never imposed on a functional / pipeline codebase (detect + defer to its paradigm). Bounded by [`minimal-safe-diff`](minimal-safe-diff.md) + [`senior-engineering-discipline`](senior-engineering-discipline.md), which **win on conflict**: a reviewer should be able to name the concrete duplication or second axis of change the abstraction removes (rule of thumb: two real repetitions before you extract a **code-level** abstraction; UI classes carry deliberately higher bars — per-class canon: [`abstraction-thresholds`](../guidelines/abstraction-thresholds.md)).
 
-Full standard — split FE / backend, with the stack carve-out index and the anti-over-engineering deference: [`component-oriented-and-oop-development`](../docs/guidelines/component-oriented-and-oop-development.md).
+Full standard — split FE / backend, with the stack carve-out index and the anti-over-engineering deference: [`component-oriented-and-oop-development`](../guidelines/component-oriented-and-oop-development.md).
 
 ## Architectural Decision Records (ADRs)
 

package/dist/agent-src/rules/artifact-drafting-protocol.md

@@ -59,7 +59,7 @@ Fires once per creation task, not once per edit.
   `late_artifacts: auto-research` is the only declared value that continues,
   capped at three per run (mechanics guideline § Late artifacts).
 
-Body migrated to [`guideline:agent-infra/artifact-drafting-protocol-mechanics`](../docs/guidelines/agent-infra/artifact-drafting-protocol-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — Phase A/B/C procedure detail + the roadmap-run batch-mode carve-out (Research-once-at-contract-time, batch scope, no `artifact_protocol: skip`) + § Late artifacts (the `halt` default
+Body migrated to [`guideline:agent-infra/artifact-drafting-protocol-mechanics`](../guidelines/agent-infra/artifact-drafting-protocol-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — Phase A/B/C procedure detail + the roadmap-run batch-mode carve-out (Research-once-at-contract-time, batch scope, no `artifact_protocol: skip`) + § Late artifacts (the `halt` default
 and the five-step `auto-research` procedure).
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 

package/dist/agent-src/rules/ask-when-uncertain.md

@@ -30,7 +30,7 @@ Even if trivial or independent — exactly one.
 
 ## Vague-request triggers — MUST ask
 
-Nine patterns — "improve / optimize" · "add caching" · "make it better / cleaner" · "clean up this file" · "fix this" (no symptom) · "refactor X" · "use best practices" · "handle errors properly" · "add a UI / component / tile / page" in a mixed-framework repo. Match without context → ask **before** touching code. Per-pattern questions: [`asking-and-brevity-examples`](../docs/guidelines/agent-infra/asking-and-brevity-examples.md).
+Nine patterns — "improve / optimize" · "add caching" · "make it better / cleaner" · "clean up this file" · "fix this" (no symptom) · "refactor X" · "use best practices" · "handle errors properly" · "add a UI / component / tile / page" in a mixed-framework repo. Match without context → ask **before** touching code. Per-pattern questions: [`asking-and-brevity-examples`](../guidelines/agent-infra/asking-and-brevity-examples.md).
 
 **Escape hatch:** unambiguous from ticket / open file / prior turn → proceed, state the assumption.
 
@@ -48,7 +48,7 @@ Any "yes" → **collapse to ONE question**; hold the rest for their own turn.
 
 ### Ordering & handoff
 
-- **Session handoff** — ask LAST, after domain questions ([`agent-interaction-and-decision-quality`](../docs/guidelines/agent-infra/agent-interaction-and-decision-quality.md)).
+- **Session handoff** — ask LAST, after domain questions ([`agent-interaction-and-decision-quality`](../guidelines/agent-infra/agent-interaction-and-decision-quality.md)).
 - **Model switch** — [`model-recommendation`](model-recommendation.md) STOP-AND-WAIT gate is standalone.
 - **Blocking clarification** — ask FIRST, alone.
 - **Optional refinement** — don't ask; state the assumption, proceed.

package/dist/agent-src/rules/brand-source-of-truth.md

@@ -55,6 +55,12 @@ OR A VOICE RULE. A VALUE THAT TRACES TO NEITHER IS OFF-BRAND.
 NEVER SHIP AN ASSET THE ACTIVE BRAND CANNOT ACCOUNT FOR.
 ```
 
+**Artifact versus brand — apply before reconciling a value.** Under
+[`design-fidelity`](design-fidelity.md) the artifact is the spec: the brand
+token wins on the **value** with the distance reported, **structure**
+stays the artifact's, a conflict is surfaced not merged —
+[`design-reconciliation § Artifact versus brand`](../guidelines/design-reconciliation.md).
+
 ## Where the brand actually lives — and how to check
 
 ```
@@ -128,7 +134,7 @@ When a consumer brand profile is present, the brand register ("the impression IS
 the product") is active — use `brand-identity`, `iconography`, and
 `design-intelligence` as the primary skill cluster. For product/dashboard/admin
 surfaces within the same brand, the product register ("design serves the task")
-may apply per-surface. See [`docs/guidelines/design-modes.md`](../docs/guidelines/design-modes.md)
+may apply per-surface. See [`docs/guidelines/design-modes.md`](../guidelines/design-modes.md)
 for the full Brand-mode vs Product-mode discriminator.
 
 ## See also
@@ -137,10 +143,6 @@ for the full Brand-mode vs Product-mode discriminator.
 - [`brand`](../skills/brand/SKILL.md) — the gap-fill corpus this rule subordinates to consumer brand.
 - [`brand-identity`](../skills/brand-identity/SKILL.md) — defines the tokens the gate validates against.
 - [`brand-to-tokens`](../skills/brand-to-tokens/SKILL.md) — emits the DTCG token
-  source of truth. **Known contradiction, recorded not resolved:** that skill's
-  prose says to author `.tokens.json` while the only resolver in the tree reads
-  `tokens.json`, so a consumer following it literally produces a file nothing
-  loads. The authoring name is a consumer-visible decision and is not changed
-  here; `brand:status` surfaces the mismatch at the moment it matters.
+  source of truth; it carries the recorded `.tokens.json` filename contradiction.
 - [`design-intelligence`](../skills/design-intelligence/SKILL.md) — the "audit findings outrank corpus" precedent the gate mirrors.
-- [`docs/guidelines/design-modes.md`](../docs/guidelines/design-modes.md) — brand vs product register discriminator and routing.
+- [`docs/guidelines/design-modes.md`](../guidelines/design-modes.md) — brand vs product register discriminator and routing.