wdi-method 0.6.0 → 0.6.2

package/kit/skills/wdi-help/SKILL.md

@@ -1,99 +1,102 @@
----
-name: wdi-help
-description: Use when you need to know where the project stands in the delivery flow and which skill comes next. Answers from this project's five gates, not from BMad's phase column.
----
-
-# WDI Help
-
-`bmad-help` cannot answer "where am I" in this project. Its progress detection globs `output-location`
-paths resolved from `resolve_config.py`, so it is blind to every class-A artifact this project redirects
-into `.what/` and `.how/`. It also lists two required gates — `epics.md` and `sprint-status.yaml` — that
-this project's route never produces, and it is the only BMad skill with no `customize.toml`, so none of
-that can be corrected.
-
-This skill replaces it for position and routing. `bmad-help` remains useful for one thing only: questions
-about BMad itself.
-
-## Inputs
-
-| Source | What it answers |
-|---|---|
-| `.control/generated/status` | Which spec is open, how many of its tickets are done, which validators are red |
-| `.control/registry/index.yaml` | The global `mode`, and the gate map |
-| `.control/registry/components.yaml` | Per-component `mode`, `risk_accepted`, and `g4_passed` |
-| `.control/registry/specs.yaml` | Spec → release, size, `depends_on`, and its ticket index |
-| `.constitution/method/document/delivery-flow-guide.md` | The five gates and their checklists |
-| `.constitution/method/why/README.md` | The whole shape, when the caller has never seen the method |
-
-You MUST read `.control/generated/status` rather than counting files yourself. It is generated from the
-registry; hand-counting produces a second answer that will disagree.
-
-## What to answer
-
-Three things, in this order, and nothing else unless asked:
-
-1. **Where the project stands** — the last gate passed, and which gate is next.
-2. **What blocks that gate** — the specific artifact, validator, or blocking question that is not ready.
-3. **Which skill to invoke next** — one skill, named, with its intent, and the reason in a clause.
-
-Keep it under fifteen lines. A routing answer that needs scrolling has failed at its job.
-
-## The one thing that changes the answer
-
-**Read the component's `mode` before routing to G4.** A component at `mode: catalog` skips G4 entirely —
-routing it to `wdi-component` is wrong, and the next step is `wdi-build`. That is the single most common
-mis-route in this flow, because every other gate is the same for every component.
-
-## Routing by what exists
-
-| State | Next |
-|---|---|
-| `wdi-method update` just ran and its summary printed an `upgrade` line | `wdi-upgrade` — **before anything else**. Content is still in the old shape, and every skill below reads the new one |
-| No registry, or no global `mode` set | `wdi-init` intent `setup` — nothing has started |
-| No `.what/_product-brief/brief.md` | `wdi-problem` — G1 has not started |
-| A brief exists, and no PRD covers the area in play | `wdi-product` intent `prd` |
-| A PRD covers it but the promise has moved | `wdi-product` intent `update` — never a second PRD for the same area |
-| Only the **wording** of an `FR` is wrong | Nobody. Whichever skill is at work fixes it directly; putting it behind a gate is how three earlier corrections were dropped |
-| A PRD exists and the interface is a large part of what it promises | `wdi-ux` — optional, and it runs **before G2**, which reads its `EXPERIENCE.md`. It needs no Product Component: `design-system.md` lands at once, and the two `<pc>`-scoped halves land when `wdi-init` intent `component` runs |
-| A PRD exists, no `product_components` yet | `wdi-init` intent `component` — the slicing is born here, at the tail of G2 |
-| Components exist, `mode` or `risk_accepted` unset | `wdi-init` intents `mode` and `risk` — both are the owner's, and G4 cannot be read without them |
-| Components exist, no UC catalogue or no spine | `wdi-blueprint` — intent `catalog` first, then `platform` |
-| The blueprint is complete and G3 has not been held | The gate. Read `.how-rendered/blueprint.md`, not seven files |
-| G3 passed, a component at `outline`/`guarded`/`deep` has no depth | `wdi-component` |
-| G3 passed, the component is at `mode: catalog` | `wdi-build` — G4 is skipped by design |
-| Depth done and G4 passed for every component the work touches | `wdi-build` — it opens the spec, has the owner run `to-spec` and `to-tickets`, ships each ticket, closes the spec |
-| A small fix touching no `FR`, `UC`, `AD-N`, or domain model | Fast Path: the owner runs `/implement` directly. It stops and becomes a spec `S` the moment an `FR` is touched |
-| A planning assumption turned out void | `wdi-decision` intent `open` — it proposes, and changes nothing |
-| An accepted `DEC-` has not reached its documents | `wdi-decision` intent `apply` |
-| A bug, a failing test, unexpected behaviour | `wdi-systematic-debugging`, before any fix is proposed |
-| Numbers are wanted before the work is committed | `wdi-report` intent `estimate` |
-
-A brief that exists but is thin is still a brief. You MUST NOT route back to `wdi-problem` because a
-section reads weakly — route there only when the brief is absent, when a change signal invalidates what
-it claims, or when one of its eight required sections is missing outright.
-
-## Rules
-
-- You MUST answer from this project's five gates — G1 Problem · G2 Product · G3 Blueprint · G4 Component ·
-  G5 Release. BMad's `phase` column MUST NOT be used; it mixes two conventions and names gates this
-  project does not run.
-- When a `wdi-*` wrapper exists for a BMad skill, you MUST name the wrapper, never the skill it wraps. The
-  wrapper carries the position check and the content checks; routing past it produces an artifact nothing
-  verifies. Today every BMad skill this method uses has one: `wdi-problem`, `wdi-product`,
-  `wdi-blueprint`, `wdi-build`, `wdi-decision`, `wdi-review`, `wdi-ux`.
-- Only `.control/questions/blocking.md` holds a gate. `external.md` holds go-live and MUST NOT be reported
-  as blocking a design gate; `assumptions.md` holds nothing.
-- You MUST NOT invent progress. If `.control/generated/status` is missing or stale, say so and name
-  `validate.py --generate`.
-- You MUST NOT run other skills on the user's behalf. Name the skill; let them invoke it.
-- When the next step is blocked by a decision rather than by work, route to `wdi-question` or
-  `wdi-decision`, not to a producing skill.
-- When asked about BMad itself — what a BMad skill does, what it writes, which are deprecated — answer
-  from `bmad-skill-register.md`, and only fall back to `bmad-help` for module documentation.
-- When the caller has never seen this method, point at `.constitution/method/why/README.md` rather than
-  paraphrasing it here.
-
-## When there is no spec open
-
-Say so plainly, then route by the table above. An artifact a later gate produces MUST NOT be reported as
-missing — that is not a gap, it is the plan.
+---
+name: wdi-help
+description: Use when you need to know where the project stands in the delivery flow and which skill comes next. Answers from this project's five gates, not from BMad's phase column.
+---
+
+# WDI Help
+
+`bmad-help` cannot answer "where am I" in this project. Its progress detection globs `output-location`
+paths resolved from `resolve_config.py`, so it is blind to every class-A artifact this project redirects
+into `.what/` and `.how/`. It also lists two required gates — `epics.md` and `sprint-status.yaml` — that
+this project's route never produces, and it is the only BMad skill with no `customize.toml`, so none of
+that can be corrected.
+
+This skill replaces it for position and routing. `bmad-help` remains useful for one thing only: questions
+about BMad itself.
+
+## Inputs
+
+| Source | What it answers |
+|---|---|
+| `.control/generated/status` | Which spec is open, how many of its tickets are done, which validators are red |
+| `.control/registry/index.yaml` | The global `mode`, and the gate map |
+| `.control/registry/components.yaml` | Per-component `mode`, `risk_accepted`, and `g4_passed` |
+| `.control/registry/specs.yaml` | Spec → release, size, `depends_on`, and its ticket index |
+| `.constitution/method/document/delivery-flow-guide.md` | The five gates and their checklists |
+| `.constitution/method/why/README.md` | The whole shape, when the caller has never seen the method |
+
+You MUST read `.control/generated/status` rather than counting files yourself. It is generated from the
+registry; hand-counting produces a second answer that will disagree.
+
+## What to answer
+
+Three things, in this order, and nothing else unless asked:
+
+1. **Where the project stands** — the last gate passed, and which gate is next.
+2. **What blocks that gate** — the specific artifact, validator, or blocking question that is not ready.
+3. **Which skill to invoke next** — one skill, named, with its intent, and the reason in a clause.
+
+Keep it under fifteen lines. A routing answer that needs scrolling has failed at its job.
+
+## The one thing that changes the answer
+
+**Read the component's `mode` before routing to G4.** A component at `mode: catalog` skips G4 entirely —
+routing it to `wdi-component` is wrong, and the next step is `wdi-build`. That is the single most common
+mis-route in this flow, because every other gate is the same for every component.
+
+## Routing by what exists
+
+| State | Next |
+|---|---|
+| `wdi-method update` just ran and its summary printed an `upgrade` line | `wdi-upgrade` — **before anything else**. Content is still in the old shape, and every skill below reads the new one |
+| No registry, or no global `mode` set | `wdi-init` intent `setup` — nothing has started |
+| No `.what/_product-brief/brief.md` | `wdi-problem` — G1 has not started |
+| A brief exists, and no PRD covers the area in play | `wdi-product` intent `prd` |
+| A PRD covers it but the promise has moved | `wdi-product` intent `update` — never a second PRD for the same area |
+| Only the **wording** of an `FR` is wrong | Nobody. Whichever skill is at work fixes it directly; putting it behind a gate is how three earlier corrections were dropped |
+| A PRD exists and the interface is a large part of what it promises | `wdi-ux` — optional, and it runs **before G2**, which reads its `EXPERIENCE.md`. It needs no Product Component: `design-system.md` lands at once, and the two `<pc>`-scoped halves land when `wdi-init` intent `component` runs |
+| A PRD exists, no `product_components` yet | `wdi-init` intent `component` — the slicing is born here, at the tail of G2 |
+| Components exist, `mode` or `risk_accepted` unset | `wdi-init` intents `mode` and `risk` — both are the owner's, and G4 cannot be read without them |
+| Components exist, no UC catalogue or no spine | `wdi-blueprint` — intent `catalog` first, then `platform` |
+| The blueprint is complete and G3 has not been held | The gate. Read `.how-rendered/blueprint.md`, not seven files |
+| G3 passed, a component at `outline`/`guarded`/`deep` has no depth | `wdi-component` |
+| G3 passed, the component is at `mode: catalog` | `wdi-build` — G4 is skipped by design |
+| Depth done and G4 passed for every component the work touches | `wdi-build` — it opens the spec, has the owner run `to-spec` and `to-tickets`, ships each ticket, closes the spec |
+| A small fix touching no `FR`, `UC`, `AD-N`, or domain model | Fast Path: the owner runs `/implement` directly. It stops and becomes a spec `S` the moment an `FR` is touched |
+| The owner wants every `FR` delivered without being asked in between | `wdi-autopilot` — a preflight first, then one mandate the owner accepts, then a loop that fires it. Route here only when the owner asks for it; it is never the default next step |
+| A planning assumption turned out void | `wdi-decision` intent `open` — it proposes, and changes nothing |
+| The owner has to decide something and wants the reading done first | `wdi-explain-to-me` — it briefs, and changes nothing; the decision then goes to `wdi-decision` or `wdi-question` |
+| An accepted `DEC-` has not reached its documents | `wdi-decision` intent `apply` |
+| A bug, a failing test, unexpected behaviour | `wdi-systematic-debugging`, before any fix is proposed |
+| Numbers are wanted before the work is committed | `wdi-report` intent `estimate` |
+
+A brief that exists but is thin is still a brief. You MUST NOT route back to `wdi-problem` because a
+section reads weakly — route there only when the brief is absent, when a change signal invalidates what
+it claims, or when one of its eight required sections is missing outright.
+
+## Rules
+
+- You MUST answer from this project's five gates — G1 Problem · G2 Product · G3 Blueprint · G4 Component ·
+  G5 Release. BMad's `phase` column MUST NOT be used; it mixes two conventions and names gates this
+  project does not run.
+- When a `wdi-*` wrapper exists for a BMad skill, you MUST name the wrapper, never the skill it wraps. The
+  wrapper carries the position check and the content checks; routing past it produces an artifact nothing
+  verifies. Today every BMad skill this method uses has one: `wdi-problem`, `wdi-product`,
+  `wdi-blueprint`, `wdi-build`, `wdi-decision`, `wdi-review`, `wdi-ux`.
+- Only `.control/questions/blocking.md` holds a gate. `external.md` holds go-live and MUST NOT be reported
+  as blocking a design gate; `assumptions.md` holds nothing.
+- You MUST NOT invent progress. If `.control/generated/status` is missing or stale, say so and name
+  `validate.py --generate`.
+- You MUST NOT run other skills on the user's behalf. Name the skill; let them invoke it. The one skill that
+  runs others is `wdi-autopilot`, and only under a mandate the owner accepted — that is what the mandate is.
+- When the next step is blocked by a decision rather than by work, route to `wdi-question` or
+  `wdi-decision`, not to a producing skill.
+- When asked about BMad itself — what a BMad skill does, what it writes, which are deprecated — answer
+  from `bmad-skill-register.md`, and only fall back to `bmad-help` for module documentation.
+- When the caller has never seen this method, point at `.constitution/method/why/README.md` rather than
+  paraphrasing it here.
+
+## When there is no spec open
+
+Say so plainly, then route by the table above. An artifact a later gate produces MUST NOT be reported as
+missing — that is not a gap, it is the plan.

package/kit/skills/wdi-question/SKILL.md

@@ -1,170 +1,176 @@
----
-name: wdi-question
-description: Use when something cannot be decided now and must not be silently assumed. Files it into one of four lists in .control/questions/ by what the reader has to do about it, and closes it in place when the answer arrives.
----
-
-# WDI Question
-
-Free of stage and free of role. The purpose is narrow: make sure an unresolved thing is written down
-where it will be seen, instead of becoming an assumption nobody remembers making.
-
-The old single list reached `OQ-146` and stopped being readable. It is now four files in
-`.control/questions/`, split by **what the reader has to do about it** — not by subject, and not by
-severity.
-
-| File | Holds | Read when |
-|---|---|---|
-| `blocking.md` | Holds a gate. Target ≤3 per Product Component | Every gate |
-| `assumptions.md` | An assumption the agent took itself. One line: the assumption plus the cost of being wrong | Swept once per gate; MAY be skipped |
-| `external.md` | Waiting on a file, an action, or a credential from outside. Owner and `by_when` required | Before go-live — **not** at a design gate |
-| `answered.md` | Archive. Closed in place, never deleted | Almost never; only to stop a question being reopened |
-
-**Only `blocking.md` holds a gate.** `external.md` holds go-live; `assumptions.md` holds nothing.
-
-## The default class is `assumptions.md`
-
-A question is filed there unless it passes one of three tests. One is enough:
-
-1. It touches money, personal data, or a legal obligation.
-2. It changes the wording of an `FR`'s promise.
-3. Answering it wrong forces a rewrite of more than one Product Component.
-
-Failing all three, you take the answer yourself — and then one more test decides whether it is
-recorded at all.
-
-## The recording threshold — most assumptions MUST NOT be written down
-
-**Two filters, and a line has to pass both.**
-
-**First: it is about the PRODUCT, not about the corpus.** An open question names something undecided
-about what is being built — a behaviour, a boundary, a promise, a limit. *"Does the SRS contradict the
-SDD"* is not an open question; it is an **edit**, and it goes to whichever skill owns the file. A
-question about which document says what has never once changed what gets built, and it is the single
-easiest way to fill this list with rows nobody can act on.
-
-**Second: an assumption whose reversal costs less than the conversation about it MUST NOT be recorded.
-The shipping default IS the record.**
-
-The test is the `Cost if wrong` column that already exists. If the honest answer is *one setting
-changes* · *one default changes* · *a shortcut is added later* — with no rework, no migration, and
-nothing already built on it — then there is nothing to decide and nothing to remember. The code says
-what was chosen, and it says it more reliably than a line in a list.
-
-This is not a licence to assume quietly. It is the opposite: it protects the list. One real corpus
-carried twenty-five open lines, and **six** of them were this class — a default image dimension, how many
-quality presets to offer, whether one working folder at a time is enough. Every one had a default already
-running and a one-value reversal. Sitting in the same list as six real decisions, they made a
-six-item list look like twenty-five items of homework, and the owner stopped reading it.
-
-**The threshold does NOT apply**, and the line is recorded, when being wrong touches money, personal
-data, an irreversible action, a third-party contract, or the wording of an `FR`'s promise. Those are
-the three tests above, and they always win.
-
-**You MUST NOT register a question as blocking "to be safe."** That habit is what produced 146 ids and
-a list nobody read, and the cost is paid at every gate afterwards.
-
-## One batch, per gate, already ranked
-
-Inside a single working pass you do **not** ask. You collect. The batch is delivered once, at the gate,
-ranked, and it MUST NOT be dribbled out as each question surfaces.
-
-A healthy batch on `mode: catalog`: **≤3 blocking questions, plus ≤15 one-line assumptions.** A batch
-larger than that is a signal about the pass, not about the corpus — say so rather than delivering it
-as a list.
-
-When N agents ran in parallel, their questions arrive as **one** ranked batch, never as N reports.
-
-## Every row says whose it is, and whether it can be answered at all
-
-The four files split by **what the reader has to do**. That was not enough: a file can still hold
-lines nobody may answer yet beside lines the owner owes today, and then the owner opens it and sees
-one flat pile. In the corpus above, of twenty-five open lines exactly **six** were the owner's and
-answerable — the other nineteen were frozen, waiting on a measurement, external, or fossil.
-
-So every row carries **`Whose`**, and the vocabulary is closed:
-
-| `Whose` | Means | Who acts |
-|---|---|---|
-| `owner` | A judgement only the owner can make, and it can be made now | the owner |
-| `run: <what>` | The answer comes from running or measuring something, not from an opinion | **you**, not the owner |
-| `frozen: DEC-NNN` | An applied decision forbids answering it yet | nobody, until that `DEC-` lifts |
-
-`run:` MUST name what has to be run. "Needs testing" is not a value; `run: capture 5-finding review,
-measure handoff time` is. A row that cannot name it is not waiting on a measurement — it is an
-`owner` row in disguise.
-
-`frozen:` MUST name a `DEC-` that is `applied` and that actually forbids the work. A freeze covers
-**planning as well as building**: where a decision bans new `FR`, new use cases, and a UX pass in a
-component, answering a design question there is exactly what it bans. When that `DEC-` lifts or is
-superseded, its frozen rows become `owner` rows automatically — no re-triage.
-
-A row whose `Whose` is wrong is worse than a missing row, because it puts work in the wrong person's
-lap and it is invisible.
-
-## Registering
-
-| Field | Rule |
-|---|---|
-| Question | One sentence, answerable. "How should referrals work?" is a topic, not a question |
-| Blocks | What cannot proceed — a gate, an `FR`, a ticket, or nothing |
-| Whose | `owner` · `run: <what>` · `frozen: DEC-NNN`. See above |
-| Owner | Who can answer. A question with no owner is a wish |
-| By when | The moment it must be answered, usually a gate |
-
-Ids stay `OQ-`, allocated from the highest ever used including closed ones. An id MUST NOT be reused.
-
-A question whose discussion outgrows one line gets `.control/questions/OQ-NNN-<slug>.md` in the same
-folder, from `templates/oq.md`, and the list keeps a one-line pointer. The old home
-`.control/supplements/` is gone.
-
-## Closing
-
-An answered question is closed **in place** — the answer written beside it with the date and who
-answered — then moved to `answered.md`. You MUST NOT delete the entry.
-
-**A fossil is closed, not answered, and you MUST look for fossils first.** A row questioning a rule, a
-layer, or a validator that has since been repealed cannot bite again: it closes with the repeal as its
-answer and MUST NOT be put to the owner as a decision. These are free, and a long list usually holds
-several — one real corpus was still carrying a question about `parallel-tickets-blocked`'s shape after the layer `parallel-tickets-blocked` runs
-on had been retired.
-
-**An answer goes into the document it belongs to, and that is usually the end of it.** An `FR` in the
-PRD, a rule in `business-rules.md`, a line in the brief — written there, closed here, done. The closure
-routes to `wdi-decision` **only** when the answer has no home in any design document, or contradicts an
-`AD-N`. `decision-guide.md` § A decision's first home owns that split, and a `DEC-` is never permission
-to edit a document.
-
-This matters most at G1 and G2, where almost nothing is homeless yet: an answer about a brief belongs in
-the brief.
-
-## Rules
-
-- You MUST NOT answer the question yourself when the owner is the client or a stakeholder. Drafting a
-  proposed answer for them to confirm is useful; recording it as settled is not.
-- An `[ASSUMPTION]` tag left in a PRD, an SRS, or an SDD MUST be filed here before that document
-  passes its gate. That is precisely the failure this skill exists to prevent.
-- A question past its "by when" MUST be raised, not silently carried forward. Carried forward twice is
-  a signal that either the owner is wrong or the question is not real.
-- A row MUST move between files when its class changes, and MUST NOT be copied into a second one. An
-  assumption that turns out to touch money moves to `blocking.md`; it does not appear in both.
-- Terms MUST match `.control/product-glossary.md`.
-
-## Output
-
-**The owner's section MUST contain only `owner` rows.** Everything else is reported as a count with one
-line saying why it is not theirs — never as a list they have to read past. A report that shows all
-nineteen alongside the six is the failure this skill was reshaped to end.
-
-| Section | Contents |
-|---|---|
-| **Yours, now** | every `owner` row, ranked. This is the list |
-| Mine | `run:` count, plus what has to be run |
-| Frozen | `frozen:` count, plus which `DEC-` holds them and what lifts it |
-| External | `external.md` count. States plainly that it holds no design gate |
-| Not recorded | how many assumptions the threshold turned away this pass |
-
-Then: which file each question landed in, and anything routed on to `wdi-decision`.
-
-**"Are we done — no more OQ?" is answerable, and the honest answer is usually no.** Say which third is
-the owner's, name what lifts the frozen third, and name what you have to run for the rest. A clean
-list is not the goal; a list where every line is somebody's and actionable is.
+---
+name: wdi-question
+description: Use when something cannot be decided now and must not be silently assumed. Files it into one of four lists in .control/questions/ by what the reader has to do about it, and closes it in place when the answer arrives.
+---
+
+# WDI Question
+
+Free of stage and free of role. The purpose is narrow: make sure an unresolved thing is written down
+where it will be seen, instead of becoming an assumption nobody remembers making.
+
+The old single list reached `OQ-146` and stopped being readable. It is now four files in
+`.control/questions/`, split by **what the reader has to do about it** — not by subject, and not by
+severity.
+
+| File | Holds | Read when |
+|---|---|---|
+| `blocking.md` | Holds a gate. Target ≤3 per Product Component | Every gate |
+| `assumptions.md` | An assumption the agent took itself. One line: the assumption plus the cost of being wrong | Swept once per gate; MAY be skipped |
+| `external.md` | Waiting on a file, an action, or a credential from outside. Owner and `by_when` required | Before go-live — **not** at a design gate |
+| `answered.md` | Archive. Closed in place, never deleted | Almost never; only to stop a question being reopened |
+
+**Only `blocking.md` holds a gate.** `external.md` holds go-live; `assumptions.md` holds nothing.
+
+## The default class is `assumptions.md`
+
+A question is filed there unless it passes one of three tests. One is enough:
+
+1. It touches money, personal data, or a legal obligation.
+2. It changes the wording of an `FR`'s promise.
+3. Answering it wrong forces a rewrite of more than one Product Component.
+
+Failing all three, you take the answer yourself — and then one more test decides whether it is
+recorded at all.
+
+## The recording threshold — most assumptions MUST NOT be written down
+
+**Two filters, and a line has to pass both.**
+
+**First: it is about the PRODUCT, not about the corpus.** An open question names something undecided
+about what is being built — a behaviour, a boundary, a promise, a limit. *"Does the SRS contradict the
+SDD"* is not an open question; it is an **edit**, and it goes to whichever skill owns the file. A
+question about which document says what has never once changed what gets built, and it is the single
+easiest way to fill this list with rows nobody can act on.
+
+**Second: an assumption whose reversal costs less than the conversation about it MUST NOT be recorded.
+The shipping default IS the record.**
+
+The test is the `Cost if wrong` column that already exists. If the honest answer is *one setting
+changes* · *one default changes* · *a shortcut is added later* — with no rework, no migration, and
+nothing already built on it — then there is nothing to decide and nothing to remember. The code says
+what was chosen, and it says it more reliably than a line in a list.
+
+This is not a licence to assume quietly. It is the opposite: it protects the list. One real corpus
+carried twenty-five open lines, and **six** of them were this class — a default image dimension, how many
+quality presets to offer, whether one working folder at a time is enough. Every one had a default already
+running and a one-value reversal. Sitting in the same list as six real decisions, they made a
+six-item list look like twenty-five items of homework, and the owner stopped reading it.
+
+**The threshold does NOT apply**, and the line is recorded, when being wrong touches money, personal
+data, an irreversible action, a third-party contract, or the wording of an `FR`'s promise. Those are
+the three tests above, and they always win.
+
+**You MUST NOT register a question as blocking "to be safe."** That habit is what produced 146 ids and
+a list nobody read, and the cost is paid at every gate afterwards.
+
+## One batch, per gate, already ranked
+
+Inside a single working pass you do **not** ask. You collect. The batch is delivered once, at the gate,
+ranked, and it MUST NOT be dribbled out as each question surfaces.
+
+A healthy batch on `mode: catalog`: **≤3 blocking questions, plus ≤15 one-line assumptions.** A batch
+larger than that is a signal about the pass, not about the corpus — say so rather than delivering it
+as a list.
+
+When N agents ran in parallel, their questions arrive as **one** ranked batch, never as N reports.
+
+## Every row says whose it is, and whether it can be answered at all
+
+The four files split by **what the reader has to do**. That was not enough: a file can still hold
+lines nobody may answer yet beside lines the owner owes today, and then the owner opens it and sees
+one flat pile. In the corpus above, of twenty-five open lines exactly **six** were the owner's and
+answerable — the other nineteen were frozen, waiting on a measurement, external, or fossil.
+
+So every row carries **`Whose`**, and the vocabulary is closed:
+
+| `Whose` | Means | Who acts |
+|---|---|---|
+| `owner` | A judgement only the owner can make, and it can be made now | the owner |
+| `run: <what>` | The answer comes from running or measuring something, not from an opinion | **you**, not the owner |
+| `frozen: DEC-NNN` | An applied decision forbids answering it yet | nobody, until that `DEC-` lifts |
+
+`run:` MUST name what has to be run. "Needs testing" is not a value; `run: capture 5-finding review,
+measure handoff time` is. A row that cannot name it is not waiting on a measurement — it is an
+`owner` row in disguise.
+
+`frozen:` MUST name a `DEC-` that is `applied` and that actually forbids the work. A freeze covers
+**planning as well as building**: where a decision bans new `FR`, new use cases, and a UX pass in a
+component, answering a design question there is exactly what it bans. When that `DEC-` lifts or is
+superseded, its frozen rows become `owner` rows automatically — no re-triage.
+
+A row whose `Whose` is wrong is worse than a missing row, because it puts work in the wrong person's
+lap and it is invisible.
+
+**Under an active mandate, `owner` rows are `wdi-autopilot`'s.** It answers each with a default, files the
+line in `assumptions.md` with its cost and `under: DEC-<mandate>`, and closes it in `answered.md` in the same
+pass. Two things do not move: a row the mandate lists as `parked` stays `owner` and is reported, and a row
+whose owner is the client or a stakeholder — the first rule below — is never the agent's to answer, mandate or
+not. The mandate came from the owner; it cannot delegate what was never the owner's.
+
+## Registering
+
+| Field | Rule |
+|---|---|
+| Question | One sentence, answerable. "How should referrals work?" is a topic, not a question |
+| Blocks | What cannot proceed — a gate, an `FR`, a ticket, or nothing |
+| Whose | `owner` · `run: <what>` · `frozen: DEC-NNN`. See above |
+| Owner | Who can answer. A question with no owner is a wish |
+| By when | The moment it must be answered, usually a gate |
+
+Ids stay `OQ-`, allocated from the highest ever used including closed ones. An id MUST NOT be reused.
+
+A question whose discussion outgrows one line gets `.control/questions/OQ-NNN-<slug>.md` in the same
+folder, from `templates/oq.md`, and the list keeps a one-line pointer. The old home
+`.control/supplements/` is gone.
+
+## Closing
+
+An answered question is closed **in place** — the answer written beside it with the date and who
+answered — then moved to `answered.md`. You MUST NOT delete the entry.
+
+**A fossil is closed, not answered, and you MUST look for fossils first.** A row questioning a rule, a
+layer, or a validator that has since been repealed cannot bite again: it closes with the repeal as its
+answer and MUST NOT be put to the owner as a decision. These are free, and a long list usually holds
+several — one real corpus was still carrying a question about `parallel-tickets-blocked`'s shape after the layer `parallel-tickets-blocked` runs
+on had been retired.
+
+**An answer goes into the document it belongs to, and that is usually the end of it.** An `FR` in the
+PRD, a rule in `business-rules.md`, a line in the brief — written there, closed here, done. The closure
+routes to `wdi-decision` **only** when the answer has no home in any design document, or contradicts an
+`AD-N`. `decision-guide.md` § A decision's first home owns that split, and a `DEC-` is never permission
+to edit a document.
+
+This matters most at G1 and G2, where almost nothing is homeless yet: an answer about a brief belongs in
+the brief.
+
+## Rules
+
+- You MUST NOT answer the question yourself when the owner is the client or a stakeholder. Drafting a
+  proposed answer for them to confirm is useful; recording it as settled is not.
+- An `[ASSUMPTION]` tag left in a PRD, an SRS, or an SDD MUST be filed here before that document
+  passes its gate. That is precisely the failure this skill exists to prevent.
+- A question past its "by when" MUST be raised, not silently carried forward. Carried forward twice is
+  a signal that either the owner is wrong or the question is not real.
+- A row MUST move between files when its class changes, and MUST NOT be copied into a second one. An
+  assumption that turns out to touch money moves to `blocking.md`; it does not appear in both.
+- Terms MUST match `.control/product-glossary.md`.
+
+## Output
+
+**The owner's section MUST contain only `owner` rows.** Everything else is reported as a count with one
+line saying why it is not theirs — never as a list they have to read past. A report that shows all
+nineteen alongside the six is the failure this skill was reshaped to end.
+
+| Section | Contents |
+|---|---|
+| **Yours, now** | every `owner` row, ranked. This is the list |
+| Mine | `run:` count, plus what has to be run |
+| Frozen | `frozen:` count, plus which `DEC-` holds them and what lifts it |
+| External | `external.md` count. States plainly that it holds no design gate |
+| Not recorded | how many assumptions the threshold turned away this pass |
+
+Then: which file each question landed in, and anything routed on to `wdi-decision`.
+
+**"Are we done — no more OQ?" is answerable, and the honest answer is usually no.** Say which third is
+the owner's, name what lifts the frozen third, and name what you have to run for the rest. A clean
+list is not the goal; a list where every line is somebody's and actionable is.