devrites 4.4.2 → 4.5.0

package/pack/generated/codex/skills/devrites-lib/reference/visual-playbooks/index.md

@@ -55,3 +55,14 @@ Home: `.devrites/work/<slug>/visual/`. Optional artifact; never a new lifecycle
 - [ ] CDN dependencies (if any) listed for the outline
 - [ ] Claims cite real repo paths when they touch the tree
 - [ ] After write: inventory ids present in HTML (`open-visual` warns inventory → HTML mismatches; HTML-only decorative ids are ignored)
+
+## Anti-slop triggers (load polish / playbooks)
+
+When HTML/visual work shows **two or more** of: generic Inter/system font with no
+brief justification, hero-only layout, purple/blue gradient CTA with no brand token,
+lorem or placeholder copy in shipped states, or identical card grid with no product
+hierarchy — load [`rite-polish`](../../../rite-polish/SKILL.md) **ux_coverage** and
+craft axes before sign-off.
+
+**Failing case:** visual ships with three slop patterns and no axis record → Review
+Important finding.

package/pack/generated/codex/skills/devrites-lib/reference/workspace-artifact-schema.md

@@ -61,7 +61,7 @@ Readers continue to accept safe legacy basenames; no ordinary phase renames one.
 | `drift.md` | `DRIFT-###` spec/plan drift and resolution | 160 lines |
 | `touched-files.md` | sole candidate manifest plus a concern-ordered `## Review trail` of `path:line` stops for human review | 160 lines |
 | `design-brief.md` | UI design direction, states, interaction model | 160 lines |
-| `handoff.md` | cold-resume guide: current objective, last completed slice, next action, blockers, read-next links | 120 lines |
+| `handoff.md` | cold-resume guide: objective, last slice, next action, blockers, read-next. Sections carry content or `Nothing yet`; unevidenced recollections go under `Not tried yet`, never as results | 120 lines |
 
 When emitting `visual/` HTML+outline pairs, open matching playbooks via
 [`visual-playbooks/index.md`](visual-playbooks/index.md) (progressive load; do not

package/pack/generated/codex/skills/rite-adopt/SKILL.md

@@ -12,12 +12,20 @@ parallel convention system.
 
 ## Workflow
 
+0. **Pre-flight (workspace anchor).** Resolve the active `.devrites/work/<slug>/` path
+   and confirm `state.md` is writable. Missing slug, wrong repo root, or unreadable
+   workspace blocks Adopt before inspection. **Failing case:** adopt starts without a
+   confirmed workspace slug → stop; do not infer from cwd alone.
+
 1. Read core; resolve repository/sub-area and next objective. Ask once only if material.
 2. Follow [`reference/adoption.md`](reference/adoption.md): inspect current
    behavior, architecture and placement, callers, reusable seams, repository/CI
    commands, visible code/test patterns, non-obvious constraints, and any touched
-   load-bearing seam that needs `characterize-before-modify`. Read existing
-   `AGENTS.md`, `CLAUDE.md`, product, and design guidance.
+   load-bearing seam that needs **characterize-before-modify** (record disposition:
+   `characterized` with see-it-fail stub, or `deferred` with evidence why safe).
+   **Failing case:** plan touches auth middleware with no characterize row → Adopt
+   fails until disposition is recorded. Read existing `AGENTS.md`, `CLAUDE.md`, product,
+   and design guidance.
 3. Create the workspace and write `spec.md`, `decisions.md`, `assumptions.md`,
    `questions.md`, and `state.md`. The spec separates the current baseline from
    the measurable next objective.

package/pack/generated/codex/skills/rite-build/SKILL.md

@@ -43,6 +43,9 @@ Wright applies anti-slop; root verifies returns and never patches source.
 - Evidence beats confidence. Never weaken tests, skip TDD, widen writers, or
   self-approve. Drift → [`spec-drift-guard.md`](reference/spec-drift-guard.md);
   checkpoint → [`checkpoint.md`](reference/checkpoint.md).
+- Async readiness waits during slice work follow
+  [`debug-recovery.md`](../devrites-lib/reference/standards/debug-recovery.md)
+  (bounded poll + last-signal artifact; no blind sleep as primary strategy).
 
 ## Workflow Artifact branch
 
@@ -62,3 +65,12 @@ approved fail-on-red proof, record, AFK accounting, and stop. Use
 [`reply contract`](../devrites-lib/reference/reply-contract.md). HITL never starts
 the next slice automatically; AFK chains only within its durable remaining
 budget; Prove starts only after all slices are built.
+
+## Phase exit (observable)
+
+**Complete when:** the dispatched wright returns green proof for the slice,
+`git diff --name-only` ⊆ allowlist, independent test analysis admits no Critical
+gap, and `state.md` cursor advances with recorded evidence paths.
+
+**Failing case:** wright reports "done" but proof command was not executed or
+failed → slice incomplete; do not advance cursor.

package/pack/generated/codex/skills/rite-converge/SKILL.md

@@ -21,7 +21,9 @@ prerequisite skill to run.
 > review use `$rite-review`; to prove a finished feature use `$rite-prove`.
 
 ## Rules consulted (read on demand from `.agents/skills/devrites-lib/reference/standards/`)
+
 Pull on demand:
+
 - `principles.md`: the project invariants (`.devrites/principles.md`); code that violates a
   MUST principle is the highest-severity gap and produces a remediation slice.
 - `spec-grammar.md`: buildable acceptance criteria vs `## Success metrics` (outcome KPIs the
@@ -34,6 +36,7 @@ Pull on demand:
   triggered applicability rows; missing failure/recovery behavior is partial or absent.
 
 ## Operating rules
+
 - **APPEND-ONLY, never rewrite.** The only write to `tasks.md` is **appending** new
   `SLICE-###` entries. Never rewrite, renumber, reorder, or delete an existing slice
   (including slices a prior convergence appended). Never edit `spec.md` or `plan.md`. Never
@@ -58,6 +61,7 @@ Pull on demand:
   workspace changes.
 
 ## Workflow
+
 0. **Read `.agents/skills/devrites-lib/reference/standards/core.md`** first (the always-on
    operating rules), then resolve the active slug, require its `state.md`, and
    read the cursor directly.
@@ -103,10 +107,25 @@ Pull on demand:
    `$rite-prove` if the code already
    converged).
 
+## Completion evidence (fail-closed)
+
+Before reporting "clean" or recommending `$rite-prove`, confirm:
+
+- [ ] Every buildable AC/REQ in the assessment inventory has a built/partial/absent
+      classification with live-code citation
+- [ ] `tasks.md` is byte-for-byte unchanged when clean, or append-only when gaps exist
+- [ ] `traceability.md` updated only for appended slices
+- [ ] No narrative "done" without the checklist above
+
+**Failing case:** all units marked built but one AC lacks a test or runtime citation →
+report partial, append slice, route `$rite-vet`.
+
 ## Appended slice format
+
 Use the complete
 [`canonical slice grammar`](../devrites-lib/reference/workspace-artifact-schema.md#canonical-slice-grammar)
 with one added `Convergence:` field after `Satisfies:`:
+
 ```markdown
 <!-- Convergence 2026-07-07: slices below appended by $rite-converge — live code assessed against intent. -->
 ## SLICE-014 <name of the unmet capability>

package/pack/generated/codex/skills/rite-define/reference/plan-template.md

@@ -44,6 +44,16 @@ List vertical `SLICE-###` increments, AC coverage, and risk-first order within d
 tiers. Wide refactors use expand → green migrate batches → contract, or an integration
 branch + final verify slice.
 
+## Architecture admission
+
+Promote to ADR only **irreversible cross-boundary** choices (public contract,
+security invariant, migration that cannot roll back). Reversible config, helper
+placement, library version, or env default stays in `plan.md` / `decisions.md` as
+implementation-local or planning-owned — not architecture.
+
+**Failing case:** "Use env `FOO=bar` as default" recorded under Architecture decisions
+→ Vet requests downgrade to implementation-local horizon with observable trigger.
+
 ## Architecture decisions
 Decisions + rationale (mirror to `decisions.md`). Prefer reuse and invariants over
 scaffolding. Medium+ entries add `Binds:`/`Prevents:`. Interfaces name invariants, I/O,

package/pack/generated/codex/skills/rite-learn/SKILL.md

@@ -18,26 +18,24 @@ of one authority; it cannot promote a rule alone.
 
 ## Workflow
 
-1. Read [durable promotion](../devrites-lib/reference/standards/documentation.md#promote-durable-guidance).
-   Bound the archive; inspect applicable
-   `AGENTS.md`/`CLAUDE.md`, accepted ADRs, and relevant
-   `.devrites/archive/*/{decisions,drift,review,seal}.md` files.
-2. In broad mode, dispatch exact `devrites-retrospector` fresh/read-only; reconcile its
-   claims against cited files.
-3. Keep a correction repeated in two features or one explicit durable product/architecture
-   decision with rationale. Drop one-off, generic, or stale items.
-4. Verify claims against live authoritative repository sources. State the currentness signal,
-   applies/does-not-apply scope, and `unknown` where unverifiable.
-5. Search guidance for the same/contrary rule. Choose one existing canonical owner: nearest
-   instruction/standard, architecture ADR, or feature `decisions.md`; name discovery.
-6. Show the exact edit and duplicate/conflict/supersession disposition. Update, narrow,
-   replace, or retire contradictions; apply only after user approval of the exact edits.
+1. Read [durable promotion](../devrites-lib/reference/standards/documentation.md#promote-durable-guidance);
+   bound the archive; inspect applicable `AGENTS.md`/`CLAUDE.md`, accepted ADRs, and relevant `.devrites/archive/*/{decisions,drift,review,seal}.md`.
+2. Broad mode dispatches exact fresh/read-only `devrites-retrospector`; reconcile its claims against cited files.
+3. Keep corrections repeated in two features, a judgement call made twice, or a defect class seen twice; drop one-off preferences, task-specific detail, generic advice.
+4. Verify claims against live authoritative sources; state currentness signal, applies/does-not-apply scope, `unknown` where unverifiable.
+   **Research promotion requires:** each external claim carries **URL + retrieval date
+   (ISO)** in the proposal. A finding without dated URL fails learn promotion.
+   **Failing case:** "best practice is X" with no source → reject promotion.
+5. Search guidance for same/contrary rules; choose one existing canonical owner (nearest instruction/standard, architecture ADR, or feature `decisions.md`) and name discovery.
+6. Show the exact edit + duplicate/conflict/supersession disposition; update/narrow/replace/retire contradictions; apply only after user approval of exact edits.
 
 ## Rules
 
 - Live repository evidence outranks memory; unverifiable is unknown, not false.
-- Never create a learning ledger/index/queue, score, timeline, or parallel authority.
-- Rejected directions return only when evidence changes their rationale.
+- Never create a learning ledger/index/queue, score, timeline, or parallel authority; rejected directions return only when evidence changes their rationale.
+- A declined lesson persists as a declined decision entry (reason recorded) in the nearest owning decisions file — not re-litigated without new evidence.
+- Contradiction outranks staleness: actively misleading guidance outranks merely old guidance.
+- ≤3 accepted lessons per round; proposals extend/narrow but never lower an existing bar (revisions show old text beside new); duplicates consolidate into one canonical edit — simplification (deletions/merges) counts toward the cap.
 
 ## Output
 

package/pack/generated/codex/skills/rite-polish/SKILL.md

@@ -26,6 +26,19 @@ live in `reference/code.md` and `reference/ui.md`; read only the phase in scope.
   [`agents.md`](../devrites-lib/reference/standards/agents.md). Never edit source inline or
   run two correction writers concurrently.
 
+## Polish axes (C3 — completeness vs craft)
+
+Score **separately**; conflating them hides gaps:
+
+| Axis | Question | Failing case |
+| --- | --- | --- |
+| **ux_coverage** | Did we compare every stated alternative/state? | Omitted empty/error state treated as agreement |
+| **completeness** | Are required states, copy, and flows present? | Hero-only layout with no loading/error |
+| **craft / anti-slop** | Does the UI avoid generic template patterns? | Inter + purple gradient hero with no product-specific hierarchy |
+| **distinction** | Is there one intentional signature detail? | Polished but indistinguishable from a template |
+
+Incomplete comparison is **not** agreement. Record axis deltas in `polish-report.md`.
+
 ## Orchestration
 
 0. **Read** `.agents/skills/devrites-lib/reference/standards/core.md` first (the always-on operating rules). The

package/pack/generated/codex/skills/rite-polish/reference/anti-ai-slop.md

@@ -90,6 +90,8 @@ Each is pass/fail by counting or grep, not judgment:
 - **Layout families** (hero, image+text split, card grid, bento, table…): no family more
   than twice per page; never 3 consecutive image+text zigzags.
 - **Icons**: 0 emoji-as-icon; exactly one icon set imported.
+- **State presence in code**: default+hover+focus-visible+active+disabled for every interactive element; loading/error/empty where data delays or fails — an unreachable state's screenshot proves nothing.
+- **Form inputs**: no border-width shifts between states; focus ring from outline/ring (not border swap); consistent control height; reserved helper slot; disabled beyond opacity alone.
 
 ## Code anti-slop (UI **and** backend)
 - **Over-defensive checks** — `if (x && x.length > 0)` repeated, layered null guards,

package/pack/generated/codex/skills/rite-pressure-test/SKILL.md

@@ -12,6 +12,7 @@ Use when the idea—not only requirements—is rough. Compare directions before
 first and write only workspace/ticket artifacts.
 
 ## Diverge (widen)
+
 - Search `decisions.md`, accepted ADRs, and relevant archives for rejected directions;
   revive one only with evidence that answers its recorded reason, citing both.
 - Generate 3-5 different shapes, including obvious, smaller, and different-boundary/data/
@@ -20,6 +21,7 @@ first and write only workspace/ticket artifacts.
 - For each, name concrete entities/flows/surfaces, optimization, rough cost, and main risk.
 
 ## Converge (commit)
+
 - Weigh options against the goal, constraints, and existing codebase conventions.
 - Prefer felt pain over nice-to-have. Rank differentiation: new capability > 10× gain >
   new audience > new context > better UX > cheaper; do not dress a vitamin as a painkiller.
@@ -33,10 +35,13 @@ If the hinge is an uncertain material fact, freeze at most three questions for
 `unavailable`, never support. Record claim, support, strongest contrary evidence, and
 `supported | assumption | refuted`. Refutation changes the recommendation; an assumption
 advances only when non-decisive with bounded downside. Weak/conflicting decisive evidence
-returns **Hold** with the resolving evidence, never `$rite-spec`. Do not research preferences
+returns **Hold** with the resolving evidence, never `$rite-spec`. Tie-breaker:
+see [`intent-map.md`](../devrites-lib/reference/intent-map.md) (`rite-pressure-test`
+vs `rite-spec`). Do not research preferences
 or reversible implementation choices.
 
 ## Boundaries
+
 - This is exploration, not specification. Output a **direction**, not a finished spec:
   `$rite-spec` writes the spec.
 - Don't over-explore: 3-5 options, one pass of convergence. If the user already knows

package/pack/generated/codex/skills/rite-prove/SKILL.md

@@ -111,3 +111,12 @@ test changes.
 
 > Do not claim an unobserved pass, skip browser proof, or proceed with pending
 > slices. Load `reference/anti-patterns.md` when tempted to do so.
+
+## Phase exit (observable)
+
+**Complete when:** every criterion in `acceptance-proof.md` has discriminating
+evidence bound to the current candidate digest, both independent validators admit
+accounts, and `state.md` records Prove complete with no open `cannot_verify` rows.
+
+**Failing case:** narrative "all tests passed" without `evidence.md` binding and
+proof-runner admission → phase not complete; Seal blocks.

package/pack/generated/codex/skills/rite-prove/reference/acceptance-proof.md

@@ -14,6 +14,16 @@ filtered, pending, zero-test, assertion-free, tautological, or unexecuted result
 do not count. Build/compile/typecheck/lint prove only their static criterion;
 discriminating shell assertions and golden/text comparisons may prove text/CLI.
 
+## Silent-failure probe
+
+When tests pass but error paths, dropped results, or partial success could hide
+failure, require at least one **discriminating** check that would fail if the silent
+path regressed (assert the failure surface, not only the happy path).
+
+**Failing case:** handler returns success while logging or swallowing internally; the
+suite stays green → map `cannot_verify` unless a test asserts the user-visible or
+contract failure outcome.
+
 ## Backstop disposition
 
 A `backstop` passes only on its spec-named independent held-out,

package/pack/generated/codex/skills/rite-review/SKILL.md

@@ -20,7 +20,9 @@ tell the user to run `$rite-spec <feature>`.
 all workflow-named roles remain mandatory at every depth.
 
 ## Rules consulted (read on demand from `.agents/skills/devrites-lib/reference/standards/`)
+
 Pull these via `Read` when the diff demands them:
+
 - `code-review.md`: small PRs, severity labels, tests-first review focus.
 - `review-checklist.md`: compact pass/fail sweep before reporting the verdict.
 - `principles.md`: declared project invariants (`.devrites/principles.md`); a diff that violates one with no recorded exception is a Critical, blocking finding.
@@ -33,9 +35,13 @@ Pull these via `Read` when the diff demands them:
 - `performance.md`: only when perf is relevant or a regression risk is visible.
 
 ## Operating rules
+
 - **Feature scope only.** Review touched files + the diff. **NO whole-project refactors,
   NO drive-by cleanup.** DO NOT delete suspected dead code outside this feature without
   asking. Spec Drift Guard applies.
+- **Silent-failure hunt:** when the suite is green, require proof that error paths and
+  partial-success branches would fail tests if broken. **Failing case:** tests pass but
+  handler returns success on internal error → Critical until an asserting test exists.
 - **Review the finished product.** `$rite-polish` has already simplified code and
   normalized or polished UI. If review finds a remaining complexity issue, record it as
   a finding rather than rerunning a simplification pass.
@@ -49,6 +55,7 @@ Pull these via `Read` when the diff demands them:
   route to `devrites-slice-wright`.
 
 ## Workflow
+
 0. Read `.agents/skills/devrites-lib/reference/standards/core.md` first (the always-on operating rules); pull the
    on-demand rules above as the diff demands them.
    Then read the explicit or active workspace's `state.md` directly.
@@ -129,6 +136,7 @@ Pull these via `Read` when the diff demands them:
    correction has affected proof plus a fresh Review.
 
 ## Finding labels
+
 - **Critical:** must fix before seal (correctness/security/data loss).
 - **Important:** should fix before seal (likely bug, real maintainability risk).
 - **Suggestion:** worth doing, not blocking.
@@ -141,6 +149,7 @@ change is already small: a pure noise-economics lever). Only a **`blocking` Crit
 seal; a `non-blocking` / `if-minor` finding is recorded, not a stop.
 
 ## Confidence and signal-to-noise
+
 Apply [`agents.md` § Result admission](../devrites-lib/reference/standards/agents.md#result-admission).
 Suppress unverifiable ≤4 hypotheses, require 7+ plus exact proof for
 Critical/Important, and make every silent/unusable account a blocking gap. Roll

package/pack/generated/codex/skills/rite-spec/reference/spec-checklists.md

@@ -11,7 +11,7 @@ Emit `.devrites/work/<slug>/checklists/<domain>.md` per covered domain; skip
 `none`. Each domain maps gaps to a `devrites-interview` dimension:
 
 | Domain file | Tests the prose of |
-|---|---|
+| --- | --- |
 | `functional.md` | Functional requirements + scenarios: is each capability stated, bounded, testable? |
 | `data-model.md` | Key entities / data model: shapes, fields, lifecycle, relationships (skip if "none"). |
 | `interaction.md` | API / UI impact + UX states: every screen state and contract named (skip if no UI/API). |
@@ -39,6 +39,7 @@ undefined stated-flow edge, or contradictory requirements. Other vague prose is
 ## Question bank
 
 Each question checks one requirement-prose failure mode:
+
 - **Measurability:** every "good / fast / prominent / simple / secure" carries a number, a budget,
   or a named reference. No adjective stands in for a threshold.
 - **Completeness:** every enumeration is closed (no "etc."); every requirement with a precondition
@@ -64,6 +65,8 @@ Each question checks one requirement-prose failure mode:
 - **Preservation:** each material brownfield outcome appears in `Existing behavior
   to preserve` with preserving REQ/AC and current evidence. Missing/vague “no
   regressions” or unjustified `none` is CRITICAL.
+  **Failing case:** brownfield login still works but the table has no evidence column
+  → CRITICAL until a test path, command, or observed contract is named.
 - **Backstops:** each row names an independent held-out, property/metamorphic, or
   direct behavioral check and the failure it discriminates; confidence/presence/self-review fail.
 - **Non-functional:** each NFR names affected REQ/AC IDs or a bounded `global` scope;
@@ -80,6 +83,7 @@ unchecked**. A spec without checklists is not yet checked, so define stops and r
 back here.
 
 ## Discipline
+
 - Score honestly. Do not soften a checklist question to pass a weak spec.
 - Don't pad. Five real questions that find one CRITICAL beat thirty rubber-stamped rows.
 - If a question needs a function name, it belongs in `$rite-vet`'s `test-plan.md`.

package/pack/generated/codex/skills/rite-spec/reference/spec-template.md

@@ -33,6 +33,12 @@ No implementation detail. True greenfield: `none — no existing behavior in the
 | --- | --- | --- |
 | <outcome that must not regress> | REQ-001 / AC-001 | <current evidence> |
 
+Each preservation row **must** cite current evidence (test, runtime, contract, or
+observed behavior). An empty or vague evidence cell blocks Spec readiness.
+
+**Failing case:** row lists REQ-001 with evidence "none" or "TBD" → readiness gate
+fails until evidence is named or the outcome is removed from scope.
+
 ## Stakeholders and priorities
 | Actor/stakeholder | Observable outcome | Conflict / priority rule |
 | --- | --- | --- |

package/pack/generated/codex/skills/rite-vet/SKILL.md

@@ -40,6 +40,12 @@ plan declares a root-authored executable workflow file, read
   unverified or confidence ≤4 findings under `review-axes.md`.
 - Auth, migration, public API, and data-model changes use maximum caution and the
   irreversible-risk stop. Project principles never become trade-offs.
+- **Governance-protected paths** (`.devrites/**`, pack skill/agent trees,
+  `NOTICE.md` generator regions, CI/hook config named in repo docs) require explicit
+  human approval before plan slices may edit them. A slice touching a protected path
+  without approval → Vet **NEEDS CLARIFICATION**.
+  **Failing case:** plan edits another feature's `state.md` without recorded approval →
+  fail closed.
 - Use the lowest axis band; never average or round thin to ready. Search before
   asking and resolve reversible technical choices. Ask only human-owned choices.
 - Preserve a valid technical return cursor. Agent-owned `NEEDS REPLAN` returns
@@ -138,3 +144,11 @@ plan declares a root-authored executable workflow file, read
 
 > Do not replace interactive review with artifacts, change acceptance through
 > hardening, score without source evidence, or ignore unexplained complexity.
+
+## Phase exit (observable)
+
+**Complete when:** `eng-review.md` records exactly one readiness verdict, readiness
+binding SHA-256 passes, and every required reviewer account is admitted.
+
+**Failing case:** READY written while a required reviewer returned `Outcome: gap` →
+not complete; restore NEEDS REPLAN or dispatch missing reviewer.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "devrites",
-  "version": "4.4.2",
+  "version": "4.5.0",
   "description": "DevRites: a disciplined senior-engineer workflow pack for Claude Code and Codex",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/ViktorsBaikers/DevRites#readme",