@orkestrel/scaffold 0.0.71 → 0.0.72

package/dist/host/CLAUDE.md

@@ -27,9 +27,9 @@ follows it. This file adds only what Claude Code does differently, and cannot we
 - Run the main session on `opus` at high effort, set by `/model opus` or `"model": "opus"`. Opus 5
   is the Orchestrator in this harness. Its Orchestrator duties are unchanged if it is configured
   otherwise.
-- The Orchestrator shares its engine with `planner`, `reviewer`, and the Opus `implementer`. Run
-  the Sol `analyst` in every design round and every audit round so the judgment is not single-engine,
-  and confirm from its journal that it reached Sol. A bridge driver that answers from its own engine
+- The Orchestrator shares its engine with `planner`, `reviewer`, and `opus`. Run the Sol `analyst`
+  in every design round and every audit round so the judgment is not single-engine, and confirm from
+  its journal that it reached Sol. A bridge driver that answers from its own engine
   collapses the round to one engine and its ruling still reads as normal.
 - Claude role frontmatter accepts Claude models only. Reach Grok through `grok`, and Sol through
   `analyst` and `sol`. Never put an external model in `model:`. Treat

package/dist/host/agents/orchestration.md

@@ -86,6 +86,13 @@ names nothing else, so never write it of a lane. A verdict file's recorded reaso
 
 By default Opus 5 holds the subjective lane and Sol holds the objective lane.
 
+Swap the lanes whenever the round needs an engine that is not the one running that lane. Bench
+darkness is one trigger and the writer's engine is another: § Execution loop's audit step requires
+an auditor that did not write the work, so where Sol wrote the work under audit, give the objective
+lane to Opus 5 and the subjective lane to Sol, and reverse that where Opus 5 wrote it. Both engines
+still run, so this is a lane swap rather than a substitution. Record which engine held which lane in
+the routing ledger.
+
 When one engine is unavailable, the remaining engine runs **every** lane — still separate
 subagents, still clean contexts, still blind to each other, each told which perspective it holds.
 Record the substitution.
@@ -121,6 +128,9 @@ Fall back in this order and record the substitution:
 2. **Luna** (`gpt-5.6-luna`), when the Cursor bench is dark and Codex is available.
 3. **Sonnet**, when both benches are dark.
 
+- Dispatch `distiller` for absorption and distillation after the ladder steps past Grok, and
+  `researcher`, `scout`, or `checker` for the job each of those names. `scout` excludes deep
+  reading and `researcher` excludes repository-scale absorption, so neither takes that step.
 - Never route absorption to the Orchestrator itself, even when the Orchestrator is Grok. Keep the
   main context at decision level; in Cursor that means a Grok executor session, not this one.
 - Never spend Opus 5 or Sol on it.
@@ -155,8 +165,9 @@ when the role file already pins it.
 | Creative design and alternatives         | `planner`                       | `planner`                     | Opus 5 (native / bridge)      |
 | Design-fit review and audit              | `reviewer`                      | `reviewer`                    | Opus 5 (native / bridge)      |
 | Objective analysis and correctness audit | `analyst`                       | `analyst`                     | GPT-5.6 Sol (bridge / native) |
-| Nontrivial implementation (objective)    | `sol`                           | `implementer`                 | GPT-5.6 Sol (bridge / native) |
-| Nontrivial implementation (subjective)   | `implementer`                   | `opus`                        | Opus 5 (native / bridge)      |
+| Nontrivial implementation (objective)    | `sol`                           | `sol`                         | GPT-5.6 Sol (bridge / native) |
+| Nontrivial implementation (subjective)   | `opus`                          | `opus`                        | Opus 5 (native / bridge)      |
+| Bulk reading and evidence distillation   | `distiller`                     | `distiller`                   | Grok → Luna → Sonnet          |
 | Bounded primary-source research          | `researcher`                    | `researcher`                  | Grok → Luna → Sonnet          |
 | Repository reconnaissance                | `scout`                         | `scout`                       | Grok → Luna → Sonnet          |
 | Mechanical conformance evidence          | `checker`                       | `checker`                     | Grok → Luna → Sonnet          |
@@ -167,9 +178,11 @@ when the role file already pins it.
 
 - A **bridge** role is a cheap driver whose only work is invoking another provider's CLI. It never
   implements, judges, or endorses the result.
-- `implementer` names the harness's native implementation lane, so the token means Opus in Claude
-  Code and Sol in Codex. An engine-named bridge — `sol`, `opus` — names the other engine. Read a
-  role name against the harness you are running in, and state the engine anyway.
+- `sol` and `opus` each name one engine on both provider surfaces. The harness decides whether the
+  role is native or a bridge; the name never does. State the engine in the dispatch anyway.
+- A role name and a model alias occupy different fields — a dispatch and a role file's `name` carry
+  the role, a `model:` pin carries the alias — so the Codex `opus` bridge is a role named `opus`
+  pinned to the `gpt-5.6-terra` model.
 - Give every role a file in the scaffold checkout, under `.claude/agents/` and under
   `.codex/agents/`. The role file is where engine, effort, tools, permissions, and charter are
   pinned, and the tool allowlist is what makes the read-only floor real. A role with no file has
@@ -177,9 +190,9 @@ when the role file already pins it.
   catalog agent and no other role, and a session that dispatches roles starts on scaffold and
   attaches the target.
 - Reach every role by its own name. Do not rely on a remembered route.
-- `researcher`, `scout`, and `checker` are native lanes for jobs that belong to Grok first.
-  Dispatch `grok` with their brief before using them, and use the native role only once the ladder
-  has stepped past Grok. Record which step you are on.
+- `distiller`, `researcher`, `scout`, and `checker` are native lanes for jobs that belong to Grok
+  first. Dispatch `grok` with their brief before using them, and use the native role only after the
+  ladder has stepped past Grok. Record which step you are on.
 - `orkestrel` stays native because it carries the package catalog in its own role file. Sending its
   job to a bench means shipping that catalog across, which costs more than the bench saves.
 - A transport contract lives in `.agents/transports/`, not in an agents directory. A harness lists
@@ -188,9 +201,13 @@ when the role file already pins it.
   `.agents/transports/claude.md` the shared Opus transport contract. Neither is a route: `analyst`
   and `sol` are the named Sol bridges, `planner`, `reviewer`, and `opus` the named Opus bridges, and
   each binds its own contract by reference and pins only its route and sandbox.
+  `.agents/transports/cursor.md` is the shared Cursor transport contract, and both harnesses' `grok`
+  bridges bind it, because Cursor is native to neither. A contract's home is the provider it carries,
+  never the harness that reaches it.
 - Mirroring is by work class, not filename. A transport contract is provider-specific: the Codex
   contract carries the Sol transport the Claude-side bridges follow, the Claude contract carries the
-  Opus transport the Codex-side bridges follow, and each side's bridges bind their own.
+  Opus transport the Codex-side bridges follow, and each bridge binds the contract of the provider it
+  reaches.
 - Opus and Sol roles use high effort. Native cheap-tier roles use low or medium. Bridge drivers use
   the cheapest tier that can run a CLI.
 - Never route orchestration or acceptance across a bridge.
@@ -333,10 +350,10 @@ longer holds.
    - State the goal's exit criterion beside the units: the enumerated capabilities whose closure
      ends the campaign, each to end implemented, repaired, retained, or intentionally excluded on
      evidence. A plan that names work but not its end can only be abandoned, never finished.
-3. **Implement.** Route each nontrivial objective unit to the Sol `implementer` and each nontrivial
-   subjective unit to the Opus `implementer`, in the checkout the unit writes, one writer per
-   checkout. Route a fully specified taste-free unit to `builder`. Never route implementation to an
-   engine the unit's judgment load exceeds.
+3. **Implement.** Route each nontrivial objective unit to `sol` and each nontrivial subjective unit
+   to `opus`, in the checkout the unit writes, one writer per checkout. Route a fully specified
+   taste-free unit to `builder`. Never route implementation to an engine the unit's judgment load
+   exceeds.
 4. **Integrate.** Evaluate each distillate against its acceptance criteria, apply shared-file
    patches serially, and route cross-cutting findings. Integration applies exact returned patches
    and mechanical conflict resolution only. A new type, mechanism, behavior, or acceptance
@@ -388,9 +405,15 @@ that needs the user.
 
 ## Deviation protocol
 
-When reality diverges from a writing dispatch:
+Stop when a conflict prevents the primary objective or requires an unowned change. Resolve an
+ancillary choice within the owned scope, record the choice, and continue.
+
+Every charter references this section rather than restating it. A charter keeps only a stop
+condition its own route owns, such as a misrouted unit it must refuse.
+
+When a writer stops:
 
-1. The writer stops and reports: expected, found, exact evidence, done or not done, and at most one
+1. The writer reports: expected, found, exact evidence, done or not done, and at most one
    short hypothesis. It does not investigate, improvise, or alter the plan.
 2. The Orchestrator triages:
    - obvious correction → tighten and re-dispatch;
@@ -432,12 +455,16 @@ The harness bridge names the concrete mechanism for each of these.
   unit's instruction and its outcome are one pair on disk.
 - Name, inside a report that rests on a bench lane, that lane's journal path and session id, so
   the provenance survives the journal's sweep.
-- Amend a brief on re-run rather than restating it. A mid-campaign correction produces a successor
-  file recording what changed and why, and the original stays. A fix round's brief names the
-  findings it carries and where each came from.
+- Re-run a unit with a successor brief, never with an edit to the brief it already ran. Name the
+  successor `<unit>-brief-<n>.md`, state in it what changed and why, and leave the original in place
+  unedited. A fix round's brief names the findings it carries and where each came from.
 - Name a corrected unit's effective brief and report and the pair they supersede before that unit
   integrates. A unit whose correction landed as a serial patch or a direct reconciliation, with no
   successor pair on disk, cannot be re-run from what the campaign kept.
+- Write an audit round's numbered claims to `tmp/audit/<unit>-audit-claims.md` and point every lane
+  of the round at that one file, so "both lanes ran the same brief" stays checkable after the round.
+  Retain it as `.orkestrel/<package>/<unit>-audit-claims.md`, beside the round's verdict.
+  `.agents/skills/orkestrel-falsify/references/brief.md` owns what the claims say.
 - Write the round's verdict to `.orkestrel/<package>/<unit>-audit-verdict.md`. That file is where
   the audit step records a lane or a checker that did not run.
 - Read the copy the executor will open, not the one you wrote. A brief written in the orchestrator's
@@ -446,6 +473,8 @@ The harness bridge names the concrete mechanism for each of these.
   staged copy whose facts are false stops a unit that was correctly briefed. Verify the staged path
   and its load-bearing facts before launching, and stage into a scratch directory the subject tree
   ignores rather than into the checkout root.
+- Before dispatching a successor or accepting a round, open every file the effective brief names
+  and confirm it resolves from the executor's root. Refuse the transition when one does not.
 - Send a decision taken mid-campaign to every unit already in flight whose brief it invalidates. An
   executor cannot see a change made after it was dispatched, so it writes the state its brief
   described and the defect surfaces as its own.
@@ -453,10 +482,14 @@ The harness bridge names the concrete mechanism for each of these.
   integration, fix, probe, or capture unit: copy the brief, the returned report or distillate, the
   audit verdict, the exact executed script or instrument, and the acceptance evidence into
   `.orkestrel/<package>/` as the unit is dispatched and as it returns, then sweep only the `tmp/`
-  launch copies. A capture claim's instrument is acceptance evidence; the frames may be swept once
-  the record transcribes them, because the committed instrument re-produces the film. The **Bench
-  laws** rule "Ephemeral streams, durable records" owns journals and points here for everything
-  durable.
+  launch copies. Rewrite every `tmp/` path inside a copied artifact to the retained path it now
+  names, in the same action that copies it. A retained file naming a launch copy resolves to
+  nothing after the sweep, and the successor, the claim list, and the staged authority always do.
+  Retention covers every lane of an audit round, including the lane whose brief produced a
+  deviation: a round with a retained report and no retained brief cannot be re-run. A capture
+  claim's instrument is acceptance evidence; the frames may be swept once the record transcribes
+  them, because the committed instrument re-produces the film. The **Bench laws** rule "Ephemeral
+  streams, durable records" owns journals and points here for everything durable.
 - Name a retained log with the `<unit>.log.txt` pattern, never with a bare `.log` suffix, which the
   root `.gitignore` file ignores.
 - Promote anything that must outlive the campaign into a durable artifact before the sweep — a
@@ -519,10 +552,9 @@ The harness bridge names the concrete mechanism for each of these.
   with **Bench laws** rule "Journal first" and refuse a bench result whose journal path and session
   id are absent.
 - **Output.** The exact distilled return shape. No process diary.
-- **Deviation contract.** The required stop-and-report behaviour for writers, scoped. A conflict
-  with the primary objective stops the unit. An ancillary conflict — where a paragraph sits, which
-  heading a section takes — is the executor's to decide, record, and carry on from. An unscoped
-  contract stops a unit over a detail it was equipped to settle.
+- **Deviation contract.** Point the writer at § Deviation protocol and scope it: name the ancillary
+  choices this unit settles itself — where a paragraph sits, which heading a section takes. An
+  unscoped contract stops a unit over a detail it was equipped to settle.
 - **Acceptance criteria.** Independently checkable completion conditions.
 - **Review evidence.** What the subject type requires, per the table in `orkestrel-falsify`. For a
   code change that is the actual diff and the actual status output; omitting either is a dispatch
@@ -533,8 +565,10 @@ The harness bridge names the concrete mechanism for each of these.
 
 ### Check the brief before you send it
 
-Fill `.agents/templates/brief.md`, which carries the named scope rows and the worked reason behind
-each check. Then run this checklist against what you filled.
+Fill `.agents/templates/brief.md`, keeping its section and row headings verbatim, so a row you
+cannot close is visible as a heading with a named unknown under it rather than as an absence nobody
+can see. Add a section the unit needs; never drop one. Then run this checklist against what you
+filled.
 
 - Name the executor that will open the brief, and write the transport for that reader. A bridge
   driver and the bench engine inside that driver's CLI need opposite instructions.
@@ -629,9 +663,9 @@ command that outlives the turn that started it. Every law here binds all of them
   launch whose tail is the evidence.
 - Keep network-dependent work out of sandboxed bench execs. Bench sandboxes deny network, so
   lockfile generation, real installs, and live fetches belong to the Orchestrator's own tracked
-  commands or to the native `implementer` or `builder` as an ordinary dispatched writing unit. A
-  bench exec hanging on `npm` until its cap fires is the signature of this misroute, not of a slow
-  bench.
+  commands or to whichever of `sol`, `opus`, and `builder` runs natively in the harness, as an
+  ordinary dispatched writing unit. A bench exec hanging on `npm` until its cap fires is the
+  signature of this misroute, not of a slow bench.
 - A Workflow journals identically and dies identically, so give it the same watch — with one
   correction. A workflow journal writes only at agent start and result, so its mtime goes quiet for
   minutes during healthy work, and the liveness signal is the newest subagent transcript instead. A
@@ -743,7 +777,7 @@ transport.
    child. It fails as a **false green**. The stage never arms, the boot inspection times out, and that
    timeout produces the same rejection a genuine stage timeout produces, so a test asserting on the
    message passes inside the bench while the host's gate reports the honest red — and neither run
-   reports why they disagree. Route such a subject to the harness's native implementer, or keep it on
+   reports why they disagree. Route such a subject to the harness's native writing lane, or keep it on
    the bench and supply every executed measurement yourself. Never dispatch it to a bench and expect
    it to prove its own work. The shape to recognise is a child that exits 0 almost immediately, a
    request to it that never resolves, and a stack landing in the spawning code's exit handler.

package/dist/host/agents/skills/enterprise-bootstrap/references/bootstrap-reference.md

@@ -14,7 +14,7 @@
 - [Forms in production](#forms-in-production)
 - [JavaScript lifecycle](#javascript-lifecycle)
 - [Accessibility](#accessibility)
-- [Enterprise patterns](#enterprise-patterns) — [App shell](#app-shell) · [Dense data tables](#dense-data-tables) · [Filter & search bars](#filter--search-bars) · [Wizards & multi-step forms](#wizards--multi-step-forms) · [The data states](#the-data-states) · [Feedback discipline](#feedback-discipline) · [Destructive actions](#destructive-actions)
+- [Enterprise patterns](#enterprise-patterns) — [App shell](#app-shell) · [Dense data tables](#dense-data-tables) · [Filter & search bars](#filter--search-bars) · [Wizards & multi-step forms](#wizards--multi-step-forms) · [The data states](#the-data-states) · [Refused capabilities](#refused-capabilities) · [Feedback discipline](#feedback-discipline) · [Destructive actions](#destructive-actions)
 - [RTL](#rtl)
 - [Print](#print)
 - [Performance](#performance)
@@ -114,9 +114,10 @@ measured role that requires it. Do not turn every subtle panel into a custom col
 
 ### Theme toggle
 
-Reuse the host controller. When implementing one, follow [Scope the mode](color-modes.md#scope-the-mode)
-for validated preference, automatic-mode resolution, storage failure, first paint, and overlay
-mounts. Bootstrap ships no picker; an attribute example is not a complete controller.
+Reuse the host controller. When implementing one, follow
+[Scope the mode](color-modes.md#scope-the-mode) for validated preference, automatic-mode resolution,
+first paint, and overlay mounts, and [Refused capabilities](#refused-capabilities) for a refused read
+or write. Bootstrap ships no picker; an attribute example is not a complete controller.
 
 ### Custom modes
 
@@ -484,7 +485,7 @@ Client-side, the documented pattern:
 </script>
 ```
 
-**Documented limitation (enterprise-critical):** Bootstrap's client-side validation styles and `valid/invalid-tooltip`s are **not exposed to assistive technologies**. For accessible flows use the server-side pattern — apply `.is-invalid` / `.is-valid` directly (no `.was-validated` parent needed), with `.invalid-feedback` linked through `aria-describedby` — or rely on native browser validation.
+**Documented limitation:** Bootstrap's client-side validation styles and `valid/invalid-tooltip`s are **not exposed to assistive technologies**. For accessible flows use the server-side pattern — apply `.is-invalid` / `.is-valid` directly (no `.was-validated` parent needed), with `.invalid-feedback` linked through `aria-describedby` — or rely on native browser validation.
 
 ```html
 <input
@@ -573,7 +574,12 @@ Wire the reader into the suite after it has settled a question.
 
 ### WCAG 2.2 requirements for app UI
 
-- **Target size (2.5.8, AA) — this section owns the skill's target dimensions.** Hold every applicable target at ≥ 24×24 CSS px: icon buttons, row actions, close buttons, sort carets, checkbox hit-areas, and color swatches. A smaller visual target passes only where a 24px spacing circle around it stays undisturbed — so in tight `table-sm` toolbars, pad the hit area rather than enlarging the glyph. Prefer 44×44 CSS px for a primary mobile control. Measure the rendered hit area; never infer it from a size class such as `btn-sm`. Enlarge the button or its associated label, not the icon's surrounding decoration.
+- **Target size (2.5.8, AA) — this section owns the skill's target dimensions.** Hold every applicable target at ≥ 24×24 CSS px: icon buttons, row actions, close buttons, sort carets, checkbox hit-areas, and color swatches. A smaller visual target passes only where a 24px spacing circle around it stays undisturbed — so in tight `table-sm` toolbars, pad the hit area rather than enlarging the glyph. Prefer 44×44 CSS px for a primary mobile control. Measure the rendered hit area; never infer it from a size class such as `btn-sm`. Enlarge the button or its associated label, not the icon's surrounding decoration. An inline target whose text can wrap paints one rectangle per line, and the rectangles are disjoint,
+  so the centre of its bounding box can land between them and resolve to the ancestor. Make such a
+  target `d-block`, `d-grid`, or a `stretched-link` container wherever a click must land anywhere in
+  its box. Never enlarge one through `line-height`, which widens the gap between the rectangles rather
+  than the rectangles. Measure the hit area at the narrowest supported viewport, where the target
+  wraps, not only where it fits one line.
 - **Focus not obscured (2.4.11, AA).** Sticky headers/footers/action bars and toast overlays must not bury the focused element. Reserve space with `scroll-margin-top` on focusables (or `scroll-padding-top` on the scroll container) equal to the sticky chrome height.
 - **Dragging alternatives (2.5.7, AA).** Any drag (row reorder, kanban, slider, resize) needs a non-drag single-pointer path: move up/down buttons, numeric input, click-to-place.
 - **Accessible authentication (3.3.8, AA).** Never block paste in password/OTP fields; support password managers; no puzzle as the only way in.
@@ -762,6 +768,30 @@ Design **every one** for every data surface: ideal (populated), empty, loading,
   to it. Missing is not zero. Do not collapse the whole surface into an error when some data exists.
 - **Every error state states what failed and how to fix it**, carries a keyboard-reachable retry in place, and preserves surrounding context — a body fetch failure must not blow away the toolbar and filters.
 
+### Refused capabilities
+
+A browser capability the document asks for can refuse at the call site. A storage write raises
+`QuotaExceededError` when no room is left, and a storage read raises when the browser holds that
+capability behind a permission. Give a refusal the treatment [The data states](#the-data-states)
+requires of every other state.
+
+- **Paint before you persist.** Apply the state to the document first, then write it. A control
+  deriving its label and `aria-pressed` from a flag the write moves announces a state the document
+  is not in as soon as the write refuses.
+- **Catch at the boundary that makes the call**, not at the caller. A read that runs during
+  construction takes the whole surface down when it escapes, and the person gets a blank page
+  instead of a degraded one.
+- **Default a refused read to the state a first-time reader gets.** The person who cleared site data
+  and the person whose browser refuses the read arrive at the same screen.
+- **Keep the action working for this session.** The refusal costs the memory of the preference.
+  Never let it also cost the behavior the person asked for.
+- **Say nothing about a refusal the person does not experience.** A preference that paints and does
+  not survive the session earns no failure sentence and no retry control: the action succeeded, and
+  a retry writes the same value to the same refusing store. Where the refusal does cost the person
+  something they asked for, carry it on the channel [Feedback discipline](#feedback-discipline)
+  names for its scope — inline alert for a refusal tied to one control, banner for a capability the
+  whole surface needs.
+
 ### Feedback discipline
 
 | Channel                       | Use for                                                                                       | Never for                                          |

package/dist/host/agents/skills/enterprise-bootstrap/references/color-modes.md

@@ -257,8 +257,9 @@ then inherited into a different local mode. Consume the Bootstrap variable at th
 rebind the alias at every supported mode boundary. Custom properties resolve their references
 before inheritance; see [CSS Custom Properties](https://www.w3.org/TR/css-variables-1/).
 
-When implementing a picker, validate persisted values, tolerate unavailable storage, and resolve
-`auto` through `prefers-color-scheme` before setting the attribute. Follow system changes only
+When implementing a picker, validate persisted values and resolve `auto` through
+`prefers-color-scheme` before setting the attribute. Take a refused read or write from
+[bootstrap-reference.md](bootstrap-reference.md) → Refused capabilities. Follow system changes only
 while the preference is automatic. Apply the resolved mode before first paint, keep server/client
 initial state consistent, and update the picker's accessible state. Do not write
 `data-bs-theme="auto"` without an explicitly implemented custom mode. Take the integration details

package/dist/host/agents/skills/enterprise-bootstrap/references/components.md

@@ -995,7 +995,7 @@ const popoverTriggerList = document.querySelectorAll('[data-bs-toggle="popover"]
 const popoverList = [...popoverTriggerList].map((el) => new bootstrap.Popover(el))
 
 // Programmatic control — prefer getOrCreateInstance over `new` when the
-// element may already be initialized (e.g. by a data attribute)
+// element may already be initialized (for example, by a data attribute)
 const myModal = bootstrap.Modal.getOrCreateInstance('#myModal')
 myModal.show()
 

package/dist/host/agents/skills/orkestrel-build-application/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: orkestrel-build-application
-description: Design, scaffold, extend, or harden Orkestrel `app/core`, `app/browser`, and `app/server` environments. Use for app-only or mixed src/app workspaces, app environment isolation, Vue browser entries, Node server entries, app aliases/configs/scripts/tests, cross-environment contracts, and application guide parity.
+description: Wire, extend, or harden Orkestrel `app/core`, `app/browser`, and `app/server` environments — the environment's contracts, boundaries, entries, and host proofs, never the product designed inside one. Use for app-only or mixed src/app workspaces, app environment isolation, Vue browser entries, Node server entries, app aliases, configs, scripts, and tests, cross-environment contracts, and application guide parity. Do not use it to redesign an application's routes, screens, or domain behavior; take that to a design round and return here to wire what it decides.
 ---
 
 # Build an Orkestrel application
@@ -106,3 +106,20 @@ includes app/core so the shared transport contracts have one host-independent ow
 Do not add showcase, authentication, persistence, proxy, styling-system, or product
 policy unless the request requires it. Do not leave placeholders, compatibility shims,
 empty setup files, or deferred app behavior.
+
+## Accept the result
+
+Completion requires:
+
+- every selected environment's `types.ts` implemented and mirrored in tests;
+- every boundary-enforcement layer in step 6 reporting clean over the selected environments;
+- the step 7 real-host proofs run and recorded with their counts — real DOM under
+  Playwright-backed Vitest Browser Mode, loopback port zero under real fetch, and
+  executable readiness, collision exit, signal termination, and port release under real
+  child processes — each selected environment carrying the proofs its host owns;
+- guide parity green over every app export and behavioral method;
+- the repository gates green in their required order from an independent `verifier`.
+
+A selected environment still unwired, a real-host proof not taken, or an open parity row
+means the run is not finished. Report what each environment owns, the exact proof and gate
+evidence, and any residual risk. Do not call an in-scope omission future work.

package/dist/host/agents/skills/orkestrel-debrief/SKILL.md

@@ -83,7 +83,7 @@ a practice that worked so it repeats.
 7. **Land the refinements.** Dispatch fix-now findings as bounded units under the
    repository's engine contract; make the canon edits (charters, rules, skills,
    orchestration contract) with the owner's direction where the root contract is
-   touched; re-prove per the law above.
+   touched; re-prove per the re-proving law in § "The debrief laws".
 8. **Propagate.** Portable changes are made in the scaffold repository's host inventory,
    staged, gated, and pushed — editing one project's checkout propagates nothing. Verify
    the generated-workspace proofs stay green so new projects inherit the refined canon.

package/dist/host/agents/skills/orkestrel-debrief/references/instruction-audit.md

@@ -78,11 +78,9 @@ its coverage against it.
 Findings land as one of:
 
 - **Role create / restore / retire.** Retirement requires more than duplication evidence:
-  when a charter merely restates rules, the first remedy is a thin reference-BINDING
+  when a charter merely restates rules, the first remedy is a thin reference-binding
   charter (the role keeps its context preset and its dispatch ergonomics); retire only
-  when the job itself is not distinct. Record the lesson of the reversed retirement: a
-  role that was "mechanically identical" by frontmatter still carried a distinct context
-  bundle worth keeping.
+  when the job itself is not distinct.
 - **Rule additions, one law each.** A campaign lesson that generalizes becomes one law in
   the owning rule file — never a new file per lesson, never a paragraph where a sentence
   binds.

package/dist/host/agents/skills/orkestrel-falsify/SKILL.md

@@ -47,8 +47,9 @@ it. Follow `references/brief.md`. What this skill adds beyond the conduct law:
   politeness.
 - Unknowns are named as unknowns, with how the auditor reports back on them.
 
-The claim form itself is the Falsification law's — read it there. The **verdict shape** below is this
-skill's, because `.agents/orchestration.md` assigns it here; everything else about auditor conduct is the law's.
+The claim form itself is the Falsification law's — read it there. The **verdict shape** in
+§ "Verdict shape" is this skill's, because `.agents/orchestration.md` assigns it here; everything
+else about auditor conduct is the law's.
 
 ## Evidence, by subject type
 
@@ -114,15 +115,17 @@ nobody claimed.
   harder.** A fix round reviewed by the engine that wrote it is the case the round exists to avoid,
   and where the pass cannot avoid it, naming it is what recovers the round. A clean pass on its own
   engine's work is the least valuable result a lane can return.
-- Supply the evidence the subject type requires, per the table above.
+- Supply the evidence the subject type requires, per § "Evidence, by subject type".
 - Auditors edit no source and spawn nothing. Read-only describes the SUBJECT, never the lane's
   tools.
-- **Read the lane's allowlist before writing its brief.** A lane with no write tool cannot create
-  a probe; a lane with no exec tool cannot run one or read `git`. Naming either stops the unit on
-  arrival over a detail the allowlist already settled.
-- Where the lane cannot execute, run the probe yourself, record its control and its output, and
-  supply that record as the lane's evidence. The Orchestrator produces, the lane rules. Never
-  widen a lane's tools to fit a brief.
+- **Derive a lane's executable actions from its tool allowlist and its sandbox, and read both before
+  writing its brief.** A lane with no write tool cannot create a probe; a lane with no shell runs
+  none; a read-only filesystem does not forbid a nonmutating command. Naming an action the lane
+  cannot take stops the unit on arrival over a detail the allowlist and the sandbox already settled.
+- Where an attack needs a tool the lane lacks or a write its sandbox refuses, run the probe
+  yourself, record its control and its output, and supply that record as the lane's evidence before
+  ruling on the claim. The Orchestrator produces, the lane rules. Never widen a lane's tools to fit
+  a brief.
 - Blind reports are **immutable**. Nothing an auditor returns is edited, merged, or revised — by
   anyone, including the auditor — once it has been returned.
 

package/dist/host/agents/skills/orkestrel-falsify/references/brief.md

@@ -22,9 +22,13 @@ established list is hearsay will re-derive all of it.
 dispatch deviation. For any claim about a rendered or externally driven surface, the capture is the
 evidence and source is corroboration.
 
-**Numbered falsifiable claims.** Each is a property some concrete input, state, or interleaving
-could show false. Assign the primary lane where auditors differ in strength, but do not let an
-auditor skip a claim because it assumes the other covers it better. The claim set is the round's
+**Numbered falsifiable claims.** Write them to one file both lanes are pointed at,
+`tmp/audit/<unit>-audit-claims.md`, retained beside the round's verdict. One file is what makes
+"both lanes ran the same brief" checkable after the round, and each lane's own brief then carries
+only its role, its lane, its evidence slice, and its output shape. Each claim is a property some
+concrete input, state, or interleaving could show false. Assign the primary lane where auditors
+differ in strength, but do not let an auditor skip a claim because it assumes the other covers it
+better. The claim set is the round's
 scope: write it to cover what the subject owns, then hold it closed. An attack the round invents
 against something no claim names enters the verdict only when it is substantiated to the `BROKEN`
 standard; otherwise it is a claim for the successor brief, not a finding.
@@ -36,10 +40,11 @@ an executor inventing an answer and building on it silently.
 **The threshold.** State that a finding is worth more than a clean pass, and why: the alternative is
 a consumer finding it after publication, when the version is already spent.
 
-## The read-only audit lane's brief
+## The audit lane's brief
 
-An audit lane writes nothing and runs nothing, so its brief carries fewer rows than a writing
-unit's. Give a lane every row § Anatomy names — the subject with the evidence
+An audit lane changes no source, so its brief carries fewer rows than a writing unit's. `SKILL.md`
+§ "Run the round" fixes what a lane can execute; read it there before deciding which rows a lane
+can use. Give a lane every row § Anatomy names — the subject with the evidence
 § "Evidence, by subject type" requires of each row it occupies, what the round decides, already
 established, the numbered falsifiable claims, the unknowns, and the threshold — plus its own
 **Role and lane** row (the role, its engine, and which lane it holds) and **Output** row (the
@@ -53,8 +58,11 @@ report.
 
 ## The successor rule
 
-A re-run **amends**; it never restates. Rewriting a brief from scratch loses the shape of what has
-already been attacked, and the round re-derives it at full cost.
+A re-run takes a **successor brief** that carries the previous round forward. It never restates the
+round from scratch and never edits the brief that already ran; `.agents/orchestration.md`
+§ "Every dispatch is a file before it is a launch" fixes the successor's name and its retention.
+Rewriting a brief from scratch loses the shape of what has already been attacked, and the round
+re-derives it at full cost.
 
 A successor brief:
 

package/dist/host/agents/skills/orkestrel-falsify/references/reconcile.md

@@ -5,8 +5,8 @@ decision, and it is not delegable.
 
 ## Reproduce before you act
 
-The rule beneath this whole section: **run it rather than argue it.** Every judgement below is
-cheap once the probe exists and unreliable until it does.
+The rule beneath this whole section: **run it rather than argue it.** Every judgement that follows
+is cheap once the probe exists and unreliable until it does.
 
 An auditor's finding is a **hypothesis** until the orchestrator has run it. Reproduce every sharp
 claim by hand, against the built output, before it enters a fix brief.

package/dist/host/agents/skills/orkestrel-harden-package/SKILL.md

@@ -11,7 +11,7 @@ Read the current files in this order:
 
 1. `AGENTS.md`.
 2. Every applicable `.claude/rules/*.md`.
-3. Select the work lane below and read every reference that lane requires.
+3. Select the work lane § "Select the work lane" names, and read every reference that lane requires.
 4. `guides/README.md`, the governing package/domain guide, and `ROADMAP.md` when present.
 5. The authoritative `*/types.ts`, public barrels, `package.json`, build/test configuration, and decision-bearing implementation files.
 

package/dist/host/agents/skills/orkestrel-polish-surface/SKILL.md

@@ -56,7 +56,8 @@ confirmed finding in scope and rebuilding the harness gaps the verdicts expose.
 2. **Seed candidates.** Turn your own mid-integration observations into numbered
    confirm-or-refute candidates inside the verdict brief. Observations that stay in your
    head are neither evidence nor findings.
-3. **Take independent verdicts** on the SAME portfolio, in the fixed shape below. The
+3. **Take independent verdicts** on the SAME portfolio, in the shape
+   § "Return the fixed verdict shape" fixes. The
    lanes are subjective design fit; objective state truth; and mechanical inventory of
    copy, classes, icons, and accessibility attributes. This is the surface variant of the
    adversarial pass in `.agents/orchestration.md`, so its rules bind: each lane is a fresh

package/dist/host/agents/skills/orkestrel-prove-journey/SKILL.md

@@ -25,20 +25,24 @@ Read the current files in this order:
 9. The `*/types.ts` of every environment the journeys drive, plus the application's root component,
    route entry, and store contract.
 
+Treat a retained readiness verdict as evidence to re-verify against the current tip, never as a plan
+to resume. Re-take every ruling it records that this run's acceptance depends on, and name the commit
+each ruling was taken at.
+
 ## Declare the families
 
 Declare in the browser environment's `integration.test.ts` which families that surface carries, and
 assert in the always-on proofs that every declared family is present. A declaration names which
 families a surface owes. It never switches what a declared family proves.
 
-| Family     | Declared                                            | Proves                                                                 |
-| ---------- | --------------------------------------------------- | ---------------------------------------------------------------------- |
-| Journey    | Always                                              | Each user intent reaches its outcome through the interface             |
-| Refusal    | Always                                              | Each control the surface withholds, through one exact failure voice    |
-| Matrix     | Where the surface ships more than one variant       | The values the browser resolved under each declared variant            |
-| Statechart | Where a journey drives a control that carries state | Each declared transition, driven through the interface where it can be |
-| Transport  | Where the surface persists or restarts              | Persistence, restart, and storage failure through real implementations |
-| Capture    | Under the capture flag                              | The registry times the variants, each registered file written to disk  |
+| Family     | Declared                                                                                     | Proves                                                                 |
+| ---------- | -------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- |
+| Journey    | Always                                                                                       | Each user intent reaches its outcome through the interface             |
+| Refusal    | Always                                                                                       | Each control the surface withholds, through one exact failure voice    |
+| Matrix     | Where the surface ships more than one variant                                                | The values the browser resolved under each declared variant            |
+| Statechart | Where a journey drives a transition of an entity carrying its own state and event vocabulary | Each declared transition, driven through the interface where it can be |
+| Transport  | Where the surface persists or restarts                                                       | Persistence, restart, and storage failure through real implementations |
+| Capture    | Under the capture flag                                                                       | The registry times the variants, each registered file written to disk  |
 
 - Refuse a declaration that omits a family whose trigger the surface meets. Report the omission as a
   scope finding and stop; never prove the remaining families around it.
@@ -81,6 +85,10 @@ naming a combination the run did not render.
    observe as a surface finding, and never work around it in the layer.
 7. **Type only what a person would.** Journeys carry trusted input; adversarial payloads belong to
    the transport family and the parser suites.
+8. **Perform every interaction step unconditionally.** Never gate a step on whether the control it
+   is about to drive exists or is reachable, and never branch a journey on `readRefusal`. Let the
+   resolver's failure voice name what the interface withheld. A guarded step passes whether or not
+   the control was there, so the run goes green on a surface that removed the control.
 
 ## Import the journey layer
 
@@ -113,6 +121,9 @@ placement and scope `.claude/rules/tests.md` fixes.
   a harmless transient over-refuses and breaks on the next honest implementation.
 - Assert the negative beside the positive whenever a value replaces another: the new sentence is
   present **and** the old one is gone.
+- Assert the state a control announces beside every drive that sets it, and on an unselected
+  sibling. A control announcing state owes this assertion whether or not the surface carries the
+  statechart family.
 - After a confirmed destructive action, assert through trusted input that focus landed on a visible,
   announced location.
 - Assert the whole page's perception never matches the vocabulary the product does not speak —