devrites 4.6.0 → 5.0.0

package/pack/generated/claude/skills/devrites-frontend-craft/reference/quality-standards.md

@@ -26,12 +26,22 @@ these are the floor, not the ceiling.
 - **Test** with keyboard, a screen reader, and an automated checker (e.g. axe): early.
 
 ## Motion
-- Purposeful only; UI feedback ~≤200 ms, transitions ~≤500 ms (class table below). Never
-  animate to mask slow loading; honor `prefers-reduced-motion`.
+- Purposeful only (class table below). Never animate to mask slow loading; honor
+  `prefers-reduced-motion`.
 
 ## Responsive
-- Fluid layouts; no fixed widths that break. Verify at **320 / 768 / 1024 / 1440** px; no
-  horizontal scroll; survives **200% text zoom**.
+- Fluid layouts; no fixed widths that break. Verify at **320 / 768 / 1024 / 1440** px;
+  preserve content and controls at **200% text zoom** and **400% browser zoom from
+  1280 px** (320 CSS px). This is the canonical viewport set for UI evidence: `rite-polish/reference/ui.md`, `browser-proof-checklist.md`, and
+  `browser-polish-evidence.md` cite it rather than restating it.
+- **No page-level horizontal scroll anywhere in 320–1920.** Sweep between checkpoints:
+  a `1fr` track given a 1024 px image can overflow at 900 px. Fix intrinsic sizing
+  (for example `minmax(0, 1fr)`), wrapping and media constraints; root clipping is
+  not a reflow fix. Clip decoration only, never text, controls or focus indicators.
+  A necessary two-dimensional table/map may scroll inside a named, bounded,
+  keyboard-accessible region; surrounding headings, text and pagination must reflow.
+  Record and test that exception. **Failing case:** a localized CTA disappears behind
+  `overflow-x: clip`; the missing scrollbar does not prove accessible reflow.
 - **`dvh`, not `vh`**, for full-height surfaces (`min-height: 100dvh`, never `h-screen` /
   `100vh`: mobile address bars break them). A hero fits the *initial* viewport: headline
   ≤2 lines, primary CTA above the fold.
@@ -42,8 +52,8 @@ these are the floor, not the ceiling.
 
 ### Consistency locks (one per surface)
 Lock these in `design-brief.md` and hold them page-wide: mid-scroll drift ("a different
-website by section 7") is a tell: **one accent** (no new accent appearing later on the
-page), **one radius scale**, **one theme** (light or dark, not both).
+website by section 7") is a tell: **one declared color strategy and role budget**
+(§ Color commitment; no unbriefed accent appearing later), **one radius scale**, **one theme** (light or dark, not both).
 
 ## Numerical bar (enforceable specifics)
 
@@ -58,7 +68,11 @@ Project tokens win when stricter; these are the floor.
   too clinical; use a near-black (`oklch(0.18 0 0)`) and near-white
   (`oklch(0.98 0 0)`) or the project's surface tokens.
 - Contrast follows WCAG 2.2: text ≥ 4.5:1, UI/graphics ≥ 3:1. Verify
-  against the *rendered* background, not the theoretical one.
+  against the *rendered* background, not the theoretical one. Procedure: pair every
+  `color` declaration with its computed background; a button whose text and fill sit
+  within 5% lightness and 0.05 chroma of each other fails regardless of the palette.
+- **Restrained accent, capped:** one accent covers **≤5% of the viewport** at rest
+  (3–5 placements above the fold). Accent-filled panels fail this strategy; another strategy requires the explicit brief and role budgets below.
 - **Tint neutrals toward the brand hue:** pure-grey neutrals look sterile.
   Nudge every grey 0.005-0.01 chroma toward the brand colour: invisible at
   a glance, but the surface stops feeling generic.
@@ -68,23 +82,22 @@ Project tokens win when stricter; these are the floor.
   `destructive`/`on-destructive`, …) so contrast is designed in, not patched after.
 
 #### Color commitment: pick the strategy before the palette
-Decide *how committed* the surface is to colour before opening the picker.
-Four positions on a single axis; pick one, then design within it:
+Decide *how committed* the surface is to colour before opening the picker. Four positions on a single axis; pick one, then design within it:
 
 | Strategy | Rough coverage | Use for |
 |---|---|---|
-| **Restrained** | tinted neutrals + 1 accent ≤ ~10% of the surface | Most product UI; brand surfaces that want to look quiet. |
+| **Restrained** | tinted neutrals + 1 accent ≤5% of the viewport at rest | Most product UI; brand surfaces that want to look quiet. |
 | **Committed** | one saturated colour carries 30-60% of the surface | Brand pages with a strong identity; product feature surfaces that need a hero colour. |
 | **Multi-role** | 3-4 named colour roles, each used deliberately | Brand campaigns; product data-viz with distinct meanings. |
 | **Saturated** | the surface *is* the colour: full-bleed colour ground | Brand heroes, campaign pages, splash moments. |
 
 Two corollaries:
-- The "one accent ≤ ~10%" rule belongs to **Restrained only.** Committed /
-  Multi-role / Saturated exceed it deliberately. Don't collapse every
-  surface back to Restrained by reflex.
+- The ≤5% accent cap belongs to **Restrained only**. For Committed / Multi-role /
+  Saturated, the brief must name the strategy, purpose, tokens and measured coverage
+  budget per role and viewport. No blanket waiver: an unbudgeted colored panel fails.
+  Preserve distinct success/warning/error meanings; semantic states do not authorize decorative accents. Check rendered captures against the declared budgets.
 - *Register* (brand vs product) doesn't pick the strategy by itself: brand
-  surfaces aren't always Saturated, product surfaces aren't always
-  Restrained. Pick from the scene, not the category.
+  surfaces aren't always Saturated, product surfaces aren't always Restrained. Pick from the scene, not the category.
 
 ### Calibration: density & motion
 Colour commitment fixes *how much colour*; two more axes fix *how much space* and
@@ -130,6 +143,13 @@ Corollaries (same shape as colour commitment):
 - **Product surfaces**: **fixed rem scale** (1.125 - 1.2 ratio). One family
   usually carries headings, body, labels, data.
 - Body line-height ~1.5; headings ~1.1 - 1.25. Prose width ~ 65-75 ch.
+- Adjacent hierarchy levels differ by **≥1.5× in at least one signal** (size, weight,
+  or color); verified under a blur(8px) squint — a flat field means the hierarchy is
+  decorative. **Failing case:** label and helper text differ only by 0.05rem.
+- All-caps display text sets **line-height ≥1.0**; tighter collides cap heights.
+- **Hero font-scale attribution:** a hero headline that wraps past its planned lines at
+  the target viewport is a font-size error first — fix the scale, don't shorten the
+  copy. **Failing case:** a four-line hero headline "fixed" by cutting the sentence.
 - Display ceiling: `clamp()` max ≤ ~6rem: larger is shouting. Display
   letter-spacing floor **≥ −0.04em**; tighter and the letters touch.
 - `text-wrap: balance` on h1-h3; `text-wrap: pretty` on long prose.
@@ -146,7 +166,21 @@ Corollaries (same shape as colour commitment):
 - **Bounce / elastic easing banned** unless the project's design system
   explicitly uses it.
 - Honor `prefers-reduced-motion`: reduce or remove non-essential motion
-  entirely.
+  entirely. Reduced means fewer and gentler, never zero feedback.
+- **Loading feedback appears by ~200 ms**: skeletons/spinners replace stillness
+  after that threshold; below it, feedback flicker reads as jank. Hover intents
+  may delay 150–300 ms; focus indication never fades in — the ring is instant.
+
+### Forms
+- Inputs match button height (44 px floor); visual targets under 24 px expand
+  their hit area with a pseudo-element to the 44 px minimum.
+- Helper/error text reserves **`min-height: 1lh`** so messages never shift layout.
+- Border width is pinned across states (state changes recolor, never resize).
+- Disabled is visible through **three channels**: muted color, `not-allowed`
+  cursor, and blocked interaction — color alone fails.
+- Mobile inputs set **≥16 px** font (smaller triggers iOS zoom-on-focus).
+- Numeric/data columns set **`font-variant-numeric: tabular-nums`**; columns of
+  figures align or the surface reads broken.
 
 ### Dark mode (three-axis compensation)
 A token-flip dark mode is sterile. When the project ships dark, compensate
@@ -158,13 +192,26 @@ three axes from light:
 If the project has dark tokens already, follow them. If not and dark is in
 scope, propose the compensation rather than ship a flat invert.
 
-### Focus & states (8 required)
+### Focus & states (8 required, 3 conditional)
 Every interactive element ships **8 visual/interaction states**:
 `default`, `hover`, `active`, `focus-visible`, `disabled`, `loading`,
-`selected`, and an error/invalid surface when relevant.
+`selected`, and an error/invalid surface (required wherever the element can be invalid). Data surfaces add the
+conditional three whenever the data can produce them: **partial** (a missing field
+renders an explicit em-dash/placeholder — never `null` or `0`), **conflict** (a
+concurrent-edit/version-mismatch surface), and **offline/unreachable** (stale-data
+banner with retry, not a silently cached render). **Failing case:** a row with a
+missing value renders `0` or blank and the review reads it as real data.
 - `:focus-visible` ring: **2 - 3 px**, **≥ 3:1** contrast against the
   background, **offset 2 px** so the focus is unambiguous on dense layouts.
 
+### Browser chrome
+User-agent defaults are unfinished craft. Per UI slice, theme or explicitly
+decline (briefed) each of: `::selection` (token colors, not UA blue),
+`caret-color` on editable fields, scrollbar styling or a recorded
+`scrollbar-width` decision, and the project focus-ring token in place of the
+unstyled UA outline. **Failing case:** layout, type, and the 8+3 states pass
+while the UA blue focus ring and default selection remain.
+
 ### Container queries vs viewport queries
 - **Component breakpoints:** use **container queries** (`@container`). The
   same card adapts to its column whether the viewport is 320 or 1920.
@@ -222,12 +269,26 @@ rung that carries the structure.
 - [ ] Renders with **no console errors/warnings**
 - [ ] **Keyboard**: tab through reaches everything; focus visible; Esc/Enter behave
 - [ ] **Screen reader** conveys content + structure
-- [ ] **All states**: default / loading / empty / error / success / disabled
-- [ ] **Responsive** at 320 / 768 / 1024 / 1440; no overflow; zoom-safe
+- [ ] **All states**: the canonical 8 + 3 lattice above (§ Focus & states), not a
+      shorter local list
+- [ ] **Responsive** at the canonical viewport set (§ Responsive); no lost content or
+      controls, no page overflow; bounded exceptions tested; zoom-safe
 - [ ] **No accessibility violations** (axe or equivalent)
 - [ ] Meets the **CWV budget** above (measure, don't assume)
 - [ ] Aligned to the **design system** (tokens, components, type, spacing)
+- [ ] **Browser chrome** themed or declined in the brief (§ Browser chrome)
 - [ ] Clickables show `cursor: pointer` + a hover state; icons are SVG from the one set
       (no emoji); nothing trapped under fixed/sticky bars
-- [ ] **Consistency locks hold** (one accent / one radius scale / one theme) and the
+- [ ] **Consistency locks hold** (declared color strategy/roles / one radius scale / one theme) and the
       mechanical pre-flight passes (`rite-polish/reference/anti-ai-slop.md`)
+
+## Craft convergence bar
+
+Craft work terminates; it does not loop. Findings classify as **Critical /
+Major / Minor**: done means zero Critical, zero Major, and every remaining Minor
+accepted **in writing** (owner + reason) in `polish-report.md` — an unwritten
+minor is an ignored finding, not an accepted one. Re-running the full bar after a
+fix pass happens only on an explicit opt-in ("re-run the full bar"); "keep going"
+is not opt-in. Each pass captures every supported viewport, not only the one that
+failed. **Failing case:** the 375 px overflow is fixed, 320 px still overflows,
+and the report reads clean.

package/pack/generated/claude/skills/devrites-frontend-craft/reference/reuse-first.md

@@ -1,14 +1,9 @@
 # Reuse first: frontend application
 
-Frontend-specific application of the canonical reuse rule in
-[`.claude/skills/devrites-lib/reference/standards/coding-style.md`](../../devrites-lib/reference/standards/coding-style.md#reuse-before-you-write)
-(and the slightly longer treatment in `standards/patterns.md`). Same principle:
-**reuse → extend → build new**, with the AHA caveat. This file walks it through for
-components, styles, tokens, icons, hooks, utils, and helpers in a UI feature.
-
-Consistency comes from **one source of truth**. Before creating any new component, style,
-token, icon, hook, util, or helper for the feature, **search the project** for an
-existing one that fits. Reuse it. Don't duplicate.
+Frontend application of the canonical rule in
+[`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md#reuse-before-you-write):
+reuse → extend → build new, AHA caveat below. Before creating any new component, style,
+token, icon, hook, util, or helper, search the project first.
 
 This applies to UI **and** non-UI code: utilities, helpers, types, validators, schemas,
 formatters, hooks, query helpers: anything that might already exist.

package/pack/generated/claude/skills/devrites-frontend-craft/reference/shape.md

@@ -8,8 +8,9 @@ follows the user's goal. Skipping this is how you get pretty UI that doesn't wor
 is a **per-slice refinement of that brief for the surface you're about to code**: confirm
 the answers below against the brief and fill any slice-specific gaps; don't re-derive the
 design. **Only shape from scratch here** when a UI slice has no `design-brief.md` (a spec
-written before shaping), then run `devrites-ux-shape` first, or answer these and write the
-brief inline.
+written before shaping), then run `devrites-ux-shape` first; only if it cannot run, answer
+these and write the brief per `../../devrites-ux-shape/reference/brief-template.md`, and
+return through `/rite-vet` before code.
 
 ## Answer these before writing markup
 1. **User goal:** what is the user here to accomplish? One sentence.
@@ -31,11 +32,6 @@ brief inline.
 7. **Interaction model:** what's inline vs. navigated vs. (rarely) a modal; optimistic
    vs. pending; how feedback is given.
 
-## Ask when ambiguous
-If the visual direction or the UX flow isn't determined by the existing system + the
-spec, ask the user (show 2-3 concrete options) before building. Guessing a flow is
-expensive to undo once coded.
-
 ## Output
 The answers live in the feature's `design-brief.md` (shaped at spec by `devrites-ux-shape`).
 In build, append any slice-specific refinement to its **Build-time refinements** section;

package/pack/generated/claude/skills/devrites-interview/SKILL.md

@@ -68,7 +68,7 @@ Approval requires an **explicit** yes. Treat these replies differently:
 For a short or vague request (`"design a contact page"`), do not ask isolated questions.
 Sketch the **decision tree** first, then resolve each branch **depth-first** with the
 protocol above. Domain branches per area:
-`rite-spec/reference/interview-patterns.md`.
+[`../rite-spec/reference/interview-patterns.md`](../rite-spec/reference/interview-patterns.md).
 
 ## Reframe (once, when stuck)
 If the interview is not converging, use **one** turn to challenge the premise:
@@ -78,7 +78,7 @@ protocol with the revised premise.
 ## /clarify mode: coverage scan of an existing spec
 When clarifying a written spec rather than extracting intent from scratch, first enumerate
 its actors, journeys/components, states, data boundaries, interfaces/integrations, and
-operational/proof surfaces. Scan every material surface against the caller's fixed taxonomy and mark
+operational/proof surfaces. Scan every material surface against that taxonomy and mark
 **Clear / Partial / Missing** with evidence. Ask at most **3 prioritized decision packets per
 pass**, targeting Missing before Partial, one per turn with an explicit recommendation and reason.
 A packet may close
@@ -86,7 +86,8 @@ several cells only when they share one owner and trade-off.
 
 **Integrate each answer into the relevant spec section** immediately. A Q&A log alone is
 insufficient.
-Append a dated **`## Clarifications`** block to `spec.md` with the question and resolution.
+Record each question and resolution in `decision-coverage.md` as scan evidence, not a
+transcript block in `spec.md`.
 Re-run the scan after each pass. Packet limits control cognitive load, never readiness. Continue
 later passes while human-owned blockers remain, and stop only when every row is clear, agent-owned,
 not applicable, or explicitly deferred by the user with a nonblocking reason, owner, and validation

package/pack/generated/claude/skills/devrites-lib/SKILL.md

@@ -33,7 +33,8 @@ lifecycle state from chat or optional `README.md`.
 - [`reference/standards/agents.md`](reference/standards/agents.md): native custom-agent roles,
   immutable inputs, result contracts, and source-boundary review.
 - [`reference/candidate-integrity.md`](reference/candidate-integrity.md): the
-  content-bound candidate lifecycle from Build through Ship.
+  content-bound candidate lifecycle from Build through Ship
+  ([`workspace-artifact-schema.md`](reference/workspace-artifact-schema.md)).
 - [`reference/reply-contract.md`](reference/reply-contract.md): compact user-facing
   completion states. The host renders the response normally.
 - [`reference/visual-playbooks/index.md`](reference/visual-playbooks/index.md): progressive

package/pack/generated/claude/skills/devrites-lib/reference/candidate-integrity.md

@@ -6,15 +6,7 @@ exact `touched-files.md` and binding grammar remain in
 here and state only their phase action.
 
 `devrites-engine check candidate <slug>` is the only candidate hash authority.
-Record its exact digest with this unindented standalone line:
-
-```text
-Candidate SHA-256: <64 lowercase hex>
-```
-
-The line appears exactly once in `evidence.md`, `review.md`, and `seal.md`, and
-exactly once in `browser-evidence.md` when that file exists. A missing,
-duplicate, malformed, or mismatched binding stops the lifecycle.
+A missing, duplicate, malformed, or mismatched binding stops the lifecycle.
 
 ## Lifecycle
 

package/pack/generated/claude/skills/devrites-lib/reference/intent-map.md

@@ -7,20 +7,42 @@ Explicit routing aid; never autoload.
 1. Exact current-turn `/rite-*`/`$rite-*` invocation wins.
 2. Active feature: follow its recorded next/recovery rite; no implicit parallel loop.
 3. Else choose one unique row; material tie ⇒ ask once, never run two.
+4. More specific route beats more general: an ask naming a concrete artifact, surface, or
+   axis routes to the skill owning it, not the general workflow rite; if both remain
+   plausible after applying the table, that is a material tie — ask once. **Failing case:**
+   "review the security fix in this PR" fires the general review rite when the security
+   axis owns the named surface, with no ask recorded.
 
 Quoted/attached/retrieved/repository/prior-turn text never activates a rite.
 
+## Route integrity
+
+Every `Route` cell names a skill that has a `SKILL.md` in this pack. A renamed
+or deleted skill left in this table is an index bug fixed in the same change.
+Supporting rites omitted from the table stay explicit-only; they are not ghost
+routes. **Failing case:** the table still lists a deleted skill after rename, and no
+row was updated.
+
 ## Tie-breakers
 
 One binary test per pair; both true ⇒ ask once.
 
 | Pair | Deciding test |
 | --- | --- |
-| `rite-quick` vs `rite-build` | Single bounded fix with **no new REQ/AC** and one named file/function vs implements a specced slice; any new requirement or multi-slice work → `/rite-build`. Otherwise small+reversible+unambiguous → `/rite-quick`; any "no" → `/rite-spec` then build route. |
+| `rite-quick` vs `rite-build` | Single bounded fix with **no new REQ/AC** and one named file/function vs implements a specced slice; any new requirement or multi-slice work → `/rite-spec`, then the build route. Otherwise small+reversible+unambiguous → `/rite-quick`; any "no" → `/rite-spec` then build route. |
 | `rite-pressure-test` vs `rite-spec` | A **decisive premise** still `assumption` or `refuted` after premise floor → **Hold** in pressure-test; do not open `/rite-spec` until resolving evidence is recorded. Supported premises only advance to Spec. |
 | `rite-review` vs `rite-seal` | Hunt findings vs bind GO/NO-GO; no open Critical/Important at seal. |
 | `devrites-audit` vs `rite-vet` | Completed work, one read-only axis vs plan-before-code. Plan → vet. |
 | `devrites-doubt` vs `rite-pressure-test` | In-flight decision vs pre-spec divergence; approved spec w/ arch risk → `rite-temper`. |
+| `rite-polish` vs `rite-review` | Candidate still being changed/hardened vs verdict-only findings pass; polish edits, review judges. |
+| `devrites-frontend-craft` vs `rite-polish` | Building new UI vs finishing built UI; craft sets standards at build, polish runs the catch pass. |
+| `devrites-ux-shape` vs `rite-spec` | Interaction/state/flow design question vs behavior-contract gap; shaped UX feeds the spec. |
+| `devrites-prose-craft` vs `devrites-frontend-craft` | Long-form prose (docs/README/replies) vs visible product copy; boundary lives in `browser-proof-checklist.md`. |
+| `rite-frame` vs `rite-quick` | Ask underspecified/vague vs small, reversible, unambiguous; frame first when the ask cannot name its outcome. |
+| `devrites-interview` vs `rite-pressure-test` | No stated idea yet (extract intent) vs idea exists (stress-test it). |
+| `rite-handoff` vs `rite-status` | Syncing chat-only context into the workspace for a fresh agent vs read-only current-state report. |
+| `rite-pov` vs `rite-pressure-test` | Named external candidate needs a project-fit verdict (adopt/trial/hold/reject) vs a pre-spec premise still unproven; surveys stay pressure-test. |
+| `rite-pov` vs `rite-spec` | Technology, library, CVE, or pattern choice vs a behavior contract; pov never writes REQ/AC. |
 
 Wrong-skill fire: stop, admit it, switch rites.
 
@@ -28,8 +50,9 @@ Wrong-skill fire: stop, admit it, switch rites.
 | --- | --- | --- |
 | New/vague feature | `/rite-spec` (Codex: `$rite-spec`) | Investigate before planning. |
 | Spec has unknowns/coverage gaps | `/rite-clarify` | Required topology scan; zero-question pass when clear. |
-| Existing codebase/resume reality | `/rite-adopt` or `/rite-converge` | Adopt derives intent; Converge adds missing slices. |
-| Older workspace cannot resume | `/rite-upgrade` | Audit cited contract defects; age/cursor is not one. Route normal owners; preserve history; no synthetic proof or migrator. |
+| Derive intent from existing code without an active feature contract | `/rite-adopt` | Establish the brownfield contract. |
+| Reconcile implementation with an active feature contract | `/rite-converge` | Identify gaps and add missing slices. |
+| Older workspace cannot resume | `/rite-upgrade` | Audit cited current-contract defects; age alone is no defect. Route semantic repairs to normal owners; preserve history without synthetic proof. |
 | Review plan before code | `/rite-vet` | Every plan; depth scales to risk. |
 | Small safe fix | `/rite-quick` | Escalates auth, migration, public API, destructive, ambiguous, or multi-slice work. |
 | Prove UI/runtime | `/rite-prove` + `devrites-browser-proof` | Capture real evidence. |
@@ -38,3 +61,4 @@ Wrong-skill fire: stop, admit it, switch rites.
 | Decide ship readiness | `/rite-seal` | Decides; never mutates Git. |
 | Execute ship after GO | `/rite-ship` | Requires GO/type-GO. |
 | Unattended lifecycle | `/rite-autocomplete` | Clean baseline/checkpoints; hard gates stop. |
+| Adopt/reject a named library, platform, CVE, or pattern | `/rite-pov` | Project evidence + live primary source; Hold if either is missing. |

package/pack/generated/claude/skills/devrites-lib/reference/orchestration-profiles.md

@@ -17,6 +17,11 @@ ownership, relaxes a gate, or authorizes an irreversible action. Missing or
 incompatible exact roles stop for HITL; the root never substitutes a generic
 agent or performs the specialist's work inline.
 
+A child result is a claim. Admit it only against observations (`git diff
+--name-only`, recorded commands, artifact existence) — never against the
+child's prose. **Failing case:** a wright reports "done" and the parent
+advances without comparing touched paths to the path contract.
+
 The complete 17-role catalog and source-writing boundary live in
 [`standards/agents.md`](standards/agents.md). Review-specific applicability
 lives in [`parallel-dispatch.md`](parallel-dispatch.md).

package/pack/generated/claude/skills/devrites-lib/reference/parallel-dispatch.md

@@ -19,6 +19,10 @@ Review: Spec/Code; Seal: all applicable roles.
 Also: `devrites-simplifier-reviewer`, `devrites-doubt-reviewer`,
 `devrites-strategy-reviewer`, `devrites-plan-reviewer`, or `devrites-retrospector`.
 
+If the candidate diff has no matching surfaces, record
+`Not-applicable: no relevant paths in diff` for `frontend-reviewer`,
+`security-auditor`, and `performance-reviewer`; do not dispatch them.
+
 ## Dispatch contract
 
 1. Freeze one candidate; give each reviewer the same spec, paths, and diff.
@@ -27,7 +31,13 @@ Also: `devrites-simplifier-reviewer`, `devrites-doubt-reviewer`,
    usually is; pressure requires batches or serial work.
 2. Ask for each exact named agent in fresh context; omit native syntax and
    `agent_type`/`task_name`/`fork_turns` from the instruction.
-3. Wait for all applicable results before reconciling.
+3. Every dispatch reaches a terminal classification before reconciliation:
+   `Outcome: findings`, `Outcome: no-findings`, `Outcome: gap`, or
+   `unavailable: <reason>` when the step could not run at all. Reconciling over a
+   partial roster is forbidden; an unavailable conditional step is recorded with its
+   marker in `review.md`/`seal.md` — an omitted sub-step reads as a clean run.
+   Findings later withdrawn at reconciliation stay visible: the account records
+   `withdrawn: <n> (<reason>)` rather than silently dropping them.
 4. Apply [`agents.md` § Result admission](standards/agents.md#result-admission)
    and dedupe by evidence/root cause. Account for all seven in
    `review.md`/`seal.md`: `Outcome:` plus admitted account, or
@@ -37,8 +47,28 @@ Also: `devrites-simplifier-reviewer`, `devrites-doubt-reviewer`,
    infer approval or substitute inline review.
 
 On exhaustion/contention: stop spawning; collect running results; batch/serialize.
-Never restart/orphan the cohort or infer approval.
+Never restart/orphan the cohort or infer approval. Reviewers are read-only;
+accounts store evidence, never telemetry. Same-file writers stay serial.
+Capacity rejection is backpressure: retry batches; never shrink a roster.
+
+## Scale limits
+
+Review rosters are bounded by the role table above, not by agent count. Beyond
+roughly four concurrent read-only reviewers (eight only when each owns disjoint
+paths and resources), added reviewers re-read the same material, return
+overlapping findings, and make reconciliation the bottleneck: cost grows linearly,
+discriminable signal does not. DevRites therefore refuses unbounded swarms — more
+agents never substitute for a required role, and a task needing "more reviewers"
+needs a sharper scope or a second bounded pass instead. **Failing case:** an
+eight-agent mesh with no per-agent path ownership returns conflicting edits and
+duplicated findings that no roster can reconcile.
+
+## Children are tools, not peers
 
-Reviewers are read-only; accounts store evidence, never telemetry.
+A dispatched agent is a tool invocation: the parent owns the prompt, the
+expected artifact, and admission. Reviewers do not negotiate with each other
+or with the implementer. A mesh without a parent is not a DevRites profile.
+**Failing case:** two reviewers agree a compromise in a shared channel and the
+parent records that compromise as independent review.
 
-Scale: past 3–4 compatible readers per wave, coordination cost outruns findings — batch serially. Capacity rejection is backpressure, not failure (collect running results; retry batches; never silently shrink a roster). Arbitration/independence → [agents.md § Independence](standards/agents.md#independence); writer batches → [`parallel-batch.md`](../../rite-build/reference/parallel-batch.md).
+Arbitration/independence → [agents.md § Independence](standards/agents.md#independence); writer batches → [`parallel-batch.md`](../../rite-build/reference/parallel-batch.md).

package/pack/generated/claude/skills/devrites-lib/reference/reply-contract.md

@@ -6,9 +6,9 @@ artifact.
 
 Keep the reply compact and evidence-backed:
 
-When an active rite is the controlling caller, Intermediate `NEEDS_REPLAN`, a
-nested phase `STOP`, and a routine Plan/Vet `Next step` are not eligible completion
-states. Return them to the caller without a user-facing reply. Autocomplete may
+When an active rite is the controlling caller, Intermediate `NEEDS_REPLAN` (the reply
+token for the workspace's `NEEDS REPLAN` readiness value), a nested phase `STOP`, and a
+routine Plan/Vet `Next step` are not eligible completion states. Autocomplete may
 use the shapes below only after its requested rest point or a shared genuine
 human/safety/access/exhausted-recovery stop is reached.
 
@@ -21,6 +21,10 @@ Next: <one recommended action>
 Record: <primary durable artifact path>
 ```
 
+Pre-send check: delete an opening sentence that only announces ("I'll now…") and a
+closing sentence that only recaps; then apply the two-line test — a reader seeing only
+the first and last lines must know what happened and what to do next.
+
 If a required decision, proof, or invariant is missing, use one of these states
 instead of `Done`:
 
@@ -79,3 +83,6 @@ No runnable recovery command: unchanged reinvocation remains blocked
 Next: none — requires new evidence or changed failure conditions
 Record: <artifact path>
 ```
+
+The terminal cursor marker is `Next: none` exactly as shown; a stored `Next step: none`
+names the same exhausted state.

package/pack/generated/claude/skills/devrites-lib/reference/standards/README.md

@@ -43,11 +43,18 @@ topic's owner.
 | `afk-hitl.md` | A pause, question, resume, or AFK decision is possible. |
 | `one-shot-actions.md` | A proof/action may be attempted once, needs fresh retry authorization, consumes external state/quota, or can delete its own failure evidence. |
 | `tooling.md` | Structural lookup, current external facts, or architecture memory is needed. |
+| `code-navigation.md` | Choosing graph, LSP, grep, or read routes before cross-file edits. |
 | `skill-authoring.md` | Creating, editing, routing, evaluating, or pruning a DevRites skill. |
 | `definition-of-done.md` | Prove, Seal, Ship, or Quick must decide whether work is finished. |
 | `review-checklist.md` | A compact review pass/fail sweep is enough. |
 | `test-proof-checklist.md` | Test and evidence quality needs a compact sweep. |
 | `browser-proof-checklist.md` | UI behavior needs browser proof. |
 | `security-checklist.md` | Auth, input, data, or integration work needs a compact security sweep. |
+| `acceptance-preserving-reslice.md` | Classifying or reviewing a Reslice in Plan, Vet, or Autocomplete. |
+| `debug-recovery.md` | Waiting on async readiness (server start, job completion, browser signal) needs a bounded condition-based poll. |
+
+The table is a load trigger, not an exemption. [`core.md` § Rule summary](core.md#rule-summary-load-the-full-file-when-in-scope)
+makes every *applicable* owner mandatory. **Failing case:** a security or data-integrity
+gate is skipped because the standard is "on-demand / modular."
 
 These guide judgment; workflows and engine gates enforce.

package/pack/generated/claude/skills/devrites-lib/reference/standards/afk-hitl.md

@@ -6,6 +6,23 @@ callers are `/rite-build`, `/rite-status`, `/rite-resolve`, and
 
 The contract uses one sentinel, one queue, and one resume verb.
 
+## Contents
+
+- [Run modes](#run-modes)
+- [The sentinel: `.devrites/AFK`](#the-sentinel-devritesafk)
+- [Unattended resource envelope](#unattended-resource-envelope)
+- [The four gates](#the-four-gates)
+- [Option set: how every gap is presented](#option-set-how-every-gap-is-presented)
+- [Decision ownership: search before asking](#decision-ownership-search-before-asking)
+- [Irreversible-risk list (always pause)](#irreversible-risk-list-always-pause)
+- [`questions.md` schema](#questionsmd-schema)
+- [`state.md` `Awaiting human` block](#statemd-awaiting-human-block)
+- [The resume verb: `/rite-resolve`](#the-resume-verb-riteresolve)
+- [AFK exception for discretionary pauses](#afk-exception-for-discretionary-pauses)
+- [Retry cap, no-progress loops, and self-resolve](#retry-cap-no-progress-loops-and-self-resolve)
+- [What the rule does NOT cover](#what-the-rule-does-not-cover)
+- [Cross-reference](#cross-reference)
+
 ## Run modes
 
 - **HITL (default):** human is present. At a gap/checkpoint the skill **asks inline** via
@@ -40,7 +57,7 @@ max_review_queue: 8                  # unresolved review/gate items admitted bef
 expires_at: "<ISO-8601 UTC timestamp>" # absolute unattended-authority expiry
 # max_tokens: 200000                 # optional stricter host-observed token cap
 # max_cost_usd: 10                   # optional stricter host-observed cost cap
-notify: "ntfy.sh/my-topic"           # shell command run on awaiting_human transition
+notify: "ntfy.sh/my-topic"           # shell command; examples: rite-build/reference/afk-discipline.md
 allow_gates: [advisory, validating]  # gate severities AFK auto-handles (auto-picks the recommended option)
 ```
 
@@ -66,7 +83,8 @@ counter is the effective remaining budget even when the read-only sentinel omits
 
 AFK writer admission needs a bounded input queue, effective slice cap, and valid
 `max_agents`, `max_minutes`, `max_review_queue`, and `expires_at`. Existing sentinels
-missing/malforming these fail closed; cold resume keeps the state-owned slice counter.
+that declare writer admission but miss/malform these fail closed; cold resume keeps the
+state-owned slice counter.
 Read-only watchers use equivalent native caps from [`loop-operations.md`](loop-operations.md).
 
 `max_agents` counts every leaf in the native activation, including failures and
@@ -84,9 +102,8 @@ for a genuinely new activation. Slices, recovery attempts, absolute expiry, and
 review queue remain durable/recomputed across wakes. Persist each activation stop and
 checkpoint before notification.
 
-New sentinels use: `max_slices: 10`, `max_agents: 32`, `max_minutes: 120`,
-`max_review_queue: 8`, `expires_at: <arming + 4h>`, `allow_gates: [advisory]`, and no
-notification/token/cost cap. Post-Vet pending count may lower slices. Existing files
+New sentinels default `expires_at` to arming + 4h with no notification/token/cost cap.
+Post-Vet pending count may lower slices. Existing files
 never receive missing defaults implicitly.
 
 To leave AFK, delete the file. The next skill invocation reverts to HITL.
@@ -120,7 +137,7 @@ Wherever a gap, checkpoint, or non-trivial decision surfaces (`/rite-spec`, `/ri
 - **2-4 concrete options**, the **recommended one first**, labelled `(Recommended)`.
 - Each option has a **one-line, dimension-tagged rationale**: `logic · infra · business ·
   architecture` (add `security` / `UX` / `risk` in scope) and trade-off.
-- Always include an escape hatch (`Something else — I'll describe it`).
+- Always include an escape hatch (`Something else — describe it`).
 - With more than four materially distinct choices, first ask a discriminating question or use
   sequential packets, then obtain final confirmation. Materially distinct options MUST NOT
   be silently dropped, merged, or preselected to fit the UI.
@@ -244,6 +261,11 @@ When `/rite-resolve` does resume a stopped session, the skill does **not** auto-
 `devrites-doubt` and similar skills that "ask the user" follow this rule when
 `.devrites/AFK` exists:
 
+Ceiling comparison order: Suggestion/Nit/FYI < Important < Critical; gates advisory <
+validating < blocking < escalating; a finding is ≤ the ceiling when its severity's gate
+class (Suggestion/Nit/FYI→advisory, Important→validating, Critical→blocking) is at or
+below the slice's gate.
+
 - Finding severity ≤ slice's gate ceiling (slice's `Gate:` plus `.devrites/AFK`
   `allow_gates`) → log to `questions.md` as `gate: advisory`, record the trade-off in
   `decisions.md`, proceed.
@@ -290,15 +312,11 @@ changes, not a request for permission to retry.
   Do not emit `/rite-plan unblock`, another phase command, a question, or
   `/rite-resolve`. Reinvocation with the unchanged fingerprint remains blocked
   and never resets the retry cap.
-- **Reassess no-progress loops:** After repeated attempts without progress, stop and
-  reassess the failure and approach rather than continuing blindly.
 - **Resolve agent-owned questions first.** Before raising a question, try to answer it from the code, the docs,
   or `decisions.md`. Communicate only for a blocked environment, a deliverable to hand over,
-  critical info you genuinely can't access, or a credential / permission you lack. This narrows
-  needless pauses and never weakens the blocking / escalating / irreversible gates.
-- **Use human intervention only for human-owned work.** A `human_intervention` pause is for what the agent
-  literally cannot do (create a cloud account, click a console button): never for writing code,
-  writing tests, or reviewing. The agent's own work is not a valid human gate.
+  critical info you genuinely can't access, or a credential / permission you lack — never for
+  writing code, writing tests, or reviewing; the agent's own work is not a valid human gate.
+  This narrows needless pauses and never weakens the blocking / escalating / irreversible gates.
 
 ## What the rule does NOT cover
 
@@ -317,8 +335,9 @@ AFK changes which decisions are automatic. It changes nothing else.
 
 - Skill: `/rite-resolve` (`.claude/skills/rite-resolve/SKILL.md`).
 - Workflow integration: `/rite-build` (`.claude/skills/rite-build/SKILL.md`),
-  workflow steps 0 + 2a (readiness / HITL pre-flight) and steps 4-6 (doubt / fail-on-red /
-  record) on the wright's return.
+  the readiness / HITL pre-flight stages before dispatch, and the DOUBT → PROVE
+  (fail-on-red) → RECORD stages on the wright's return
+  (`reference/one-slice-cycle.md`).
 - Render contract: `.claude/skills/rite-build/reference/checkpoint-protocol.md`.
 - Loop discipline: `.claude/skills/rite-build/reference/afk-discipline.md`.
 - Gate taxonomy: `.claude/skills/rite-define/reference/gates.md`.

package/pack/generated/claude/skills/devrites-lib/reference/standards/agents.md

@@ -38,6 +38,7 @@ Files own briefs; [`parallel-dispatch.md`](../parallel-dispatch.md) owns rosters
 Skills name exact fresh roles, omit native fields;
 hosts spawn/wait/deliver. Root MUST NOT advance/claim completion before admitting required results;
 running/orphaned/unavailable = `gap` — no root/generic substitute.
+Workflow-named skills (e.g. devrites-source-driven) are invoked inline in the root context, never dispatched as agents.
 
 ## Source-writing boundary
 
@@ -52,7 +53,7 @@ Each job gets objective/exclusions, exact paths/immutable candidate, rubric/resu
 - A fresh result sees scope/paths-diff/rubric only — never another result's or the root's conclusions, severities, expected verdicts, or edited context; seeding voids the packet.
 - A parent-context pass contributes attributed evidence but is not independent: exclude it from independent accounting and name the lost coverage.
 - Final severity is set at reconciliation after re-verifying the claimed consequence at the cited site (reviewer severity advisory); dismissals record a reason, and true facts about neighboring code route elsewhere instead of being dismissed.
-- Conflicting required results are arbitrated by re-verifying evidence at the site; the deciding evidence is recorded, truly unresolved conflicts stay open blockers.
+- Conflicting required results are arbitrated by re-verifying evidence at the site; the deciding evidence is recorded, truly unresolved conflicts stay open blockers. Two results describing the same defect merge only when both defect and fix path match; otherwise the more conservative classification stands, and severity never widens without new site evidence — an overridden or demoted finding stays visible with the reason, never silently merged away.
 
 ## Result admission
 
@@ -64,10 +65,12 @@ Each required reviewer/analyst/auditor starts with exactly one:
 ```text
 Outcome: <findings | no-findings | gap>
 Finding: <severity> | <file:line or artifact section> | <observed quote/result> | <impact> | <minimum fix>
+Basis: <files read · commands run to reach this finding>
 ```
 
 - **`findings`:** each row uses the shape above; confidence 1–10 on Critical/Important.
-  Critical/Important requires 7+, exact evidence, and concrete impact.
+  Critical/Important requires 7+, exact evidence, concrete impact, and a non-empty
+  `Basis` — a correct verdict reached by an unrecorded inspection path is unproven.
 - **`no-findings`:** `No-findings:` names checks and inspected evidence. Bare
   pass, empty list, or “looks good” is malformed.
 - **`gap`:** names missing/unreadable/stale input; skipped/failed required check;
@@ -78,13 +81,18 @@ against candidate. Missing fields become
 `Unverified: <claim> — missing <proof>` and stay `gap` until verified/rejected
 with evidence—never silently dropped/demoted. Null/timeout/failure/malformed
 output is `gap`, never `no-findings`. Conditional `Not-applicable` must name the
-inspected scope and why its trigger did not fire.
+inspected scope and why its trigger did not fire. **Failing case:** parent admits a
+wright "done" with no `git diff --name-only` ⊆ path-contract (allowlist) observation.
 
 ## Reconciliation
 
 Root rejects stale/out-of-scope work, dedupes by root cause, records
-accepted conclusions, and reruns only affected proof/review. Route defects before
-correction: product/acceptance → Spec Drift Guard/Clarify;
+accepted conclusions, and reruns only affected proof/review. Reconciliation runs
+only after every dispatch reaches a terminal classification
+([parallel-dispatch.md](../parallel-dispatch.md)); findings that do not survive stay
+visible as `withdrawn: <n> (<reason>)` in the account rather than being silently
+dropped, so a later reader can audit what was discarded and why.
+Route defects before correction: product/acceptance → Spec Drift Guard/Clarify;
 architecture/slicing/proof → Plan/Vet; source/test → wright;
 external/pre-existing → blocker/defer. Never patch downstream to hide an upstream
 defect.