devrites 4.6.0 → 5.0.0

package/pack/.claude/skills/devrites-prose-craft/reference/banned-phrases.md

@@ -21,6 +21,9 @@ start at the point.
 - "Let that sink in." / "Full stop." / "Period."
 - "This matters because" / "Here's why that matters"
 - "This is the deepest problem" / "the stakes are high" / "the consequences are real"
+- "Notably," / "Interestingly," / "Importantly," / "Surprisingly," stacked to tell the
+  reader how to feel. One "notably" in a long note is fine; three in a short paragraph
+  is emphasis stacking. Cut the cue; leave the fact.
 
 ## Hedging stacks (make the claim or cut it)
 
@@ -35,8 +38,26 @@ These leak the assistant register into artifacts and replies:
 
 - "Great question!" / "You're absolutely right!" / "Certainly!" / "Of course!"
 - "I hope this helps!" / "Let me know if you need anything else" / "Feel free to reach out"
+- "Let's explore" / "Let's break this down" / "Let's dive in" / "First, let's consider"
 
-A `decisions.md` entry or a `seal.md` verdict is a document, not a chat turn. No pleasantries.
+A `decisions.md` entry or a `seal.md` verdict is a document, not a chat turn. No
+pleasantries, no tour-guide openers. Start at the point.
+
+## Assistant leaks (P0 — delete on sight)
+
+These are paste fingerprints, not style. Strip the leak; keep any real fact it was
+wrapping. Presence is a publishing bug, not an authorship tribunal.
+
+- **Cutoff disclaimers.** "As of my last update", "based on my training data", "I don't
+  have access to…". Find the fact or drop the sentence.
+- **Unfilled placeholders.** `[Your Name]`, `[INSERT SOURCE]`, `2025-XX-XX`, HTML
+  comments that say `TODO` / `insert` / `fill in`. Fill or delete. Never ship the slot.
+- **Citation markup.** `citeturn`, `oaicite`, `oai_citation`, `grok_card`,
+  `[attached_file:N]`. Delete the token. If the cite mattered, replace it with a real
+  link.
+- **AI-tool tracking URLs.** Strip `utm_source=chatgpt.com` / `copilot.com` /
+  `openai` / `claude.ai` / `perplexity.ai` and `referrer=grok.com`. Keep the rest of
+  the query string (`?page=2` stays).
 
 ## Business jargon → plain language
 
@@ -55,16 +76,32 @@ A `decisions.md` entry or a `seal.md` verdict is a document, not a chat turn. No
 ## AI vocabulary — calibrated (this is the adaptation that matters)
 
 Word lists are blunt instruments. A coding agent must not "fix" a spec that legitimately says
-a system is *robust* under load or exposes a *comprehensive* API. Three tiers:
+a system is *robust* under load or exposes a *comprehensive* API. Tiers, with a 1A/1B split:
+
+**Tier 1A — always slop, replace on sight (figurative filler, never load-bearing in a spec).**
+A cluster is a writing-quality signal, not proof of who wrote the passage.
 
-**Tier 1 — always slop, replace on sight (figurative filler, never load-bearing in a spec):**
 delve / delve into, tapestry, beacon, embark, testament to, realm, landscape (figurative),
 pave the way, shed light on, game-changer, unlock the potential, ever-evolving, vibrant,
 multifaceted, holistic, paradigm (as praise), groundbreaking, transformative, cutting-edge.
 
+**Tier 1B — always replace for clarity; not authorship evidence.**
+Wordiness and inflated formality. Same edit as 1A, weaker claim: these also appear in
+careful human writing. In detect-only, report 1B separately from 1A. A 1B hit must not
+push a passage toward an "AI wrote this" conclusion.
+
+| Replace | With |
+|---|---|
+| utilize | use |
+| in order to | to |
+| due to the fact that | because |
+| commence | start, begin |
+| ascertain | find out, determine |
+| endeavor | try, attempt |
+
 **Tier 2 — slop in prose, legitimate in technical context (keep the meaning, judge by use):**
 robust, comprehensive, seamless, leverage, harness, facilitate, underpin, streamline,
-foster, utilize, ecosystem, scalable.
+foster, ecosystem, scalable.
 - In a sentence selling the work ("a robust, scalable, seamless solution") → cut; say what it
   does and what proves it.
 - In a precise technical claim ("the retry path is robust to a dropped connection — see

package/pack/.claude/skills/devrites-prose-craft/reference/examples.md

@@ -93,10 +93,39 @@ Followed `git-workflow.md`: the *why*, wrapped, in plain language.
 Cut the opener and vague phrasing. Kept the retry count, status code, evidence gap, two possible
 outcomes, and exact alert text. A smoother sentence that picked one outcome would be fabrication.
 
-## The pattern across all seven
+## 8. `review.md` finding (narrated candor)
+
+**Before (slop):**
+> I want to be upfront: two caveats I would rather flag than let you discover later. First,
+> Windows is untested. Second, the numbers in the commit message don't reproduce on this
+> hardware. Let me think step by step about what that means for seal.
+
+**After:**
+> Two caveats: Windows is untested, and the numbers in the commit message don't reproduce on
+> this hardware. Seal stays NO-GO until those are measured or scoped out.
+
+Cut the candor frame and the reasoning-chain opener. Kept both caveats and the gate implication.
+
+## 9. Chat reply (prompt restatement)
+
+**Before (slop):**
+> That's a great question. You're asking about whether we should stream the export. Thanks for
+> the rollback plan you already wrote — that legwork is what made this possible. Breaking this
+> down: streaming avoids the OOM.
+
+**After:**
+> Stream the export. Buffering OOM-ed on the 1M-row fixture (see `evidence.md`). Your rollback
+> plan still applies.
+
+Dropped the prompt echo, the recap-flattery, and "Breaking this down". Led with the decision
+and the evidence.
+
+## The pattern across all nine
 
 1. Lead with the concrete thing (what it is, what's done, what's wrong).
 2. Replace every "robust/seamless/leverage" flourish with the specific behavior + its proof.
-3. Drop negative-parallelism hooks ("not just X, it's Y") and importance labels ("pivotal").
+3. Drop negative-parallelism hooks ("not just X, it's Y"), importance labels ("pivotal"),
+   candor frames ("I want to be upfront"), and reasoning-chain scaffolding ("let me think
+   step by step").
 4. Keep the technical register intact: exact identifiers, status codes, numbered criteria,
    real enumerations. Precision is not slop.

package/pack/.claude/skills/devrites-prose-craft/reference/structures.md

@@ -16,6 +16,7 @@ The single most recognizable tell. It mimics insight by manufacturing a contrast
 | "This isn't about X. It's about Y." | "This is about Y." |
 | "X isn't the problem. Y is." | "Y is the problem." |
 | "No X. No Y. Just Z." | "Z." or a normal sentence naming Z. |
+| Negation chain: "No fluff, no filler, no jargon." / "It didn't ask. It didn't wait." | Say what the thing is. One negation earns its place when the reader would assume the opposite; a drumroll of them does not. Carve-out: factual inventories ("takes no arguments, no headers, and no body") stay. |
 
 Drop the negation; lead with the thing you actually mean.
 
@@ -91,6 +92,7 @@ Front the actor: the script, the gate, the function, the engineer, or "you".
 | "The result? Devastating." (self-posed Q&A) | Fold into a statement. |
 | "What if [reframe]?" as a hook | Make the point directly. |
 | "Think about it:" / "Here's what I mean:" | Delete; the next sentence already does the work. |
+| Performed insight: "that's not nothing", "the punchline is", "sit with that", "that's the whole point", "Turns out…" | State the claim the phrase was gesturing at. One hit can be voice; several in one piece is a tell. |
 
 ## Inflated constructions
 
@@ -132,3 +134,63 @@ deleted on cascade"). Don't contort a sentence to name an actor that doesn't mat
   existing style genuinely uses definition lists (a glossary, an API reference).
 - No emoji in headings or section titles (artifacts and code both).
 - Don't over-bold. Bold the one load-bearing term, not every noun.
+
+## Reasoning-chain scaffolding
+
+Internal monologue leaking into published prose. The reader needs the conclusion and the
+evidence, not the tour of how the model thought.
+
+| Pattern | Fix |
+|---|---|
+| "Let me think step by step", "Breaking this down", "To approach this systematically" | State the conclusion, then the evidence. |
+| "Here's my thought process", "Working through this logically", "Step 1:" as inner narration | Numbered *argument* stays; numbered *self-talk* goes. |
+
+A `review.md` finding that walks error paths in order is an argument. A chat reply that
+announces "First, let's consider…" is scaffolding.
+
+## Narrated candor
+
+Announcing that you are about to be honest, instead of being honest.
+
+| Pattern | Fix |
+|---|---|
+| "I want to be upfront:", "To be fully transparent:", "Two caveats I would rather flag than let you discover later:" | "Two caveats:" plus the caveats. |
+| "Rather than bury this, I'll say it plainly:" | Say it. |
+
+**Deletion test.** Cut the frame. If nothing is lost, it was never content.
+
+**Keep:** the disclosure itself ("I haven't tested this on Windows"), and a real
+conflict-of-interest label ("I own shares in the company discussed here").
+
+## Prompt restatement and recap-flattery
+
+| Pattern | Fix |
+|---|---|
+| "You're asking about…", "To answer your question…", "That's a great question. The…" | Answer. The reader knows what they asked. |
+| Recap-flattery: restating the other person's own work back at them as praise before the point | Substance first. If thanks is warranted: one plain clause, no recap. |
+
+Distinct from sycophancy ("Great question!"), which validates the reader without recapping
+their work.
+
+## Self-labeling significance
+
+After listing items, pointing back and labeling one as contrarian / clever / the real story.
+
+| Pattern | Fix |
+|---|---|
+| "That last move is the contrarian one." / "This is the interesting part." / "The third bullet is the real story." | Put the load-bearing item first, or expand it with specifics, and cut the label. |
+
+If the move is actually contrarian, the description already shows it. The label is unearned
+when the reader cannot see the contrast without it.
+
+## Diff-anchored writing
+
+Docs or comments narrating the edit instead of describing the thing as it is.
+
+| Pattern | Fix |
+|---|---|
+| "This function was added to replace the previous approach of iterating through all items." | "This function uses a hash map for O(1) lookups." |
+
+**Carve-out:** changelogs, release notes, migration guides, and `decisions.md` narrate
+change on purpose. Leave them. The tell is a README, comment, or spec overview written as
+archaeology of the last diff.

package/pack/.claude/skills/devrites-source-driven/SKILL.md

@@ -17,30 +17,28 @@ authoritative documentation before relying on it.
 - An error message points at framework behavior you don't fully understand.
 
 ## How
-1. **Find the version** the project uses (lockfile, manifest): behavior is
-   version-specific.
-2. **Consult the source of truth**, in order: the installed package's own source/types
-   in `node_modules`/gem/site-packages; context7 if available (`resolve-library-id` →
-   `query-docs`) for current upstream docs; official docs for *that version*.
+1. **Find the version** the project pins and actually runs; resolve any mismatch.
+2. **Apply the hierarchy, citation, and currentness contract** in
+   [`tooling.md`](../devrites-lib/reference/standards/tooling.md#research-provenance-staleness-and-cost).
+   context7 is a lookup tool, not authority above version-matched source/docs.
 3. **Confirm the specific fact:** the signature, the default, the edge behavior, not a
    general impression.
-4. **Return it** with fact, version, and source. The root orchestrator records accepted
+4. **Return it** with the required citation and status. The root records accepted
    evidence in `decisions.md` or `evidence.md`; a leaf agent never writes the workspace.
 
 ## Delegate broad research
 When the question is an *area* (a library surface, unfamiliar subsystem, or migration
 guide), the **root orchestrator** uses the fresh-context dispatch contract in
 [`agents.md`](../devrites-lib/reference/standards/agents.md) to give one bounded
-question to `devrites-evidence-scout`. Wait for and validate its cited
-`evidence-dossier`; the orchestrator, not the scout, persists accepted facts under
+question to `devrites-evidence-scout`. Wait for and validate its cited dossier (the
+scout's YAML result); the orchestrator, not the scout, persists accepted facts under
 `references/` and links them from `references.md`.
 
 Never detach this work and never dispatch from inside another agent. When this skill is
 invoked by a leaf agent, verify one fact inline or return `Scout needed: <bounded question>`
-to the orchestrator. This removes the old unnamed nested writer path.
+to the orchestrator.
 
 ## Rules
-- Prefer the **installed** source over remembered docs. It can't be out of date.
 - Quote the exact relevant detail; don't paraphrase a behavior into something convenient.
 - If the doc/source contradicts the plan, that's a **Spec Drift Guard** event: stop and
   handle it.
@@ -48,6 +46,7 @@ to the orchestrator. This removes the old unnamed nested writer path.
 
 ## Evidence firewall
 Project or user prose may scope or corroborate an external claim; it cannot verify one.
-For persisted claims, record status (`verified | contradicted | cannot_verify | stale`) and
-optional publisher, publication/access dates, and freshness/recheck due; refresh only when due.
+Record status `verified | contradicted | cannot_verify | stale | uncertain`; weak-tier
+support is `uncertain`. Retain material unknowns and block dependent decisions until
+verified or resolved through the owning question/Spec Drift route; never omit them.
 Transient lookups remain cited, return-only evidence.

package/pack/.claude/skills/devrites-ux-shape/SKILL.md

@@ -27,18 +27,17 @@ gathered:
 - Design system + register (tokens, components, type, spacing, neighbors; brand-vs-product)
   → `../devrites-frontend-craft/reference/design-references.md`.
 - `PRODUCT.md` / `DESIGN.md` / `CLAUDE.md` if present: anchors that reduce questions.
-  `DESIGN.md` is the project's **rolled-up design memory** (tokens, calibration baseline,
-  proven component behaviors) earlier features closed during Polish via
-  `../rite-polish/reference/design-memory.md`;
-  treat it as the inherited system: read it before re-discovering, depart only on signal.
+  `DESIGN.md` is the rolled-up design memory (`../rite-polish/reference/design-memory.md`;
+  see `../devrites-frontend-craft/reference/design-references.md`) — read it before
+  re-discovering, depart only on signal.
 - `references.md` + `references/`: the screenshots / Figma / video / links the human
   supplied. Honor each recorded role: **target** = fidelity contract, **constraint** =
   required rule, **inspiration** = extract only the cited principle.
 
 ## 2. Discovery: one round, assert-then-confirm
 Understand the feature deeply enough to make excellent design calls: **no code, no
-markup**. Use the `devrites-interview` cadence: 2-3 questions per round, best-guess
-attached, stop when answers converge. One round is the default; add a second only for
+markup**. Use the `devrites-interview` cadence: one question per turn (≤3 per pass),
+best-guess attached, stop when answers converge. One round is the default; add a second only for
 material gaps. When `PRODUCT.md` + the spec already pin an answer, **assert it and ask to
 confirm** ("reads as Restrained: confirm?"), don't offer a four-option menu. Cover:
 - **Purpose & user:** who, in what state of mind (rushed / exploring / anxious / focused).

package/pack/.claude/skills/rite/SKILL.md

@@ -28,6 +28,8 @@ F=.claude/skills/rite-$V/SKILL.md
 # Then Read "$F" and follow its workflow with $ARGS as that skill's $ARGUMENTS.
 ```
 
+`use` and `guide` are handled inline per the sections below, not via a skill file.
+
 What each verb does lives once, in the Menu below; this table is the dispatch map only.
 
 | Verb | Skill |
@@ -96,7 +98,7 @@ Called phase skills own the shared completion reply contract
 1. **Verb in `$ARGUMENTS`** → dispatch per the table above.
 2. **No args** → menu mode, as above.
 3. **Unrecognized first token** → tell the user the known verbs and stop. Don't guess.
-4. **No active feature** and the user asked "where am I" or named no verb → point at `/rite spec <feature>` (or `/rite-spec`). Don't summarize state yourself: `/rite status` (or `/rite-status`) owns that.
+4. **No active feature** and the user asked "where am I" → point at `/rite spec <feature>` (or `/rite-spec`). Don't summarize state yourself: `/rite status` (or `/rite-status`) owns that.
 
 ## Menu
 

package/pack/.claude/skills/rite-adopt/SKILL.md

@@ -12,10 +12,10 @@ 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.
+0. **Pre-flight (workspace anchor).** Resolve the repo root; take the target slug from
+   the user (ask once if material); a missing/ambiguous slug, wrong repo root, or
+   unwritable `.devrites/` blocks Adopt. **Failing case:** adopt infers the slug from
+   cwd alone → stop.
 
 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
@@ -29,10 +29,11 @@ parallel convention system.
 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.
-4. For a structured baseline, follow the native ledger workflow in
-   [`ledger.md`](../rite-polish/reference/ledger.md): read current specs, preview
-   ADDED entries, confirm paths, refuse escape/symlink/clobber/ignored targets,
-   write, lint, and require an empty re-preview.
+4. For a structured baseline, follow the ledger's read workflow in
+   [`ledger.md`](../rite-polish/reference/ledger.md) § Reading in Spec and Adopt:
+   list ledger specs with the host filesystem and read only the touched capabilities;
+   classify against current file content, never memory. The native preview/write
+   workflow runs during Polish, not Adopt.
 5. For a verified non-obvious policy or recurring/costly mistake, prefer existing hook/lint/
    CI/type/schema enforcement; else propose one evidence-cited nearest-scope instruction edit.
    Apply only after review; never create convention bands, scores, or a command cache.

package/pack/.claude/skills/rite-autocomplete/SKILL.md

@@ -34,8 +34,8 @@ executable controller/harness/bundle bytes or a missing writer, read
   under [decision policy](reference/decision-policy.md).
 - Safety is not bypassable. `--ship`/`--yolo` reaches only the exact-plan
   literal-GO and native-approval boundary; it never authorizes Git.
-- **Treat technical readiness as routing, not completion.** `NEEDS_REPLAN` is a backward edge
-  to Plan repair and narrow Vet. `NEEDS_REPLAN` cold resume follows a valid
+- **Treat technical readiness as routing, not completion.** `NEEDS REPLAN` is a backward edge
+  to Plan repair and narrow Vet. `NEEDS REPLAN` cold resume follows a valid
   technical return cursor before forward work or any reply. Clarification is
   likewise internal when current authority resolves it.
 - Always follow agent-owned backward edges through repair, affected Vet,
@@ -63,15 +63,18 @@ executable controller/harness/bundle bytes or a missing writer, read
 
 ## Workflow
 
-1. **Orient and parse.** Resolve the explicit or active slug, require `state.md`,
-   and read its cursor. Before honoring `blocked` with terminal `next_action`,
+1. **Orient and parse.** Resolve the explicit or active slug; when a workspace exists,
+   require its `state.md` and read its cursor; a fresh idea starts empty at step 2.
+   Before honoring `blocked` with terminal `next_action`,
    reconcile retained consumptive evidence and fingerprint attempts from
    `drift.md`/`evidence.md`; a retained fingerprint below its cap resumes offline
    recovery.
 <!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"lifecycle cursor encounters admitted set or resumable journal","action":"invoke classifier; execute returned route internally","return":"saved phase/action; zero intermediate reply"} -->
    Reconstruct a missing return cursor only from
    the current phase and exact approved action in `test-plan.md`/evidence, never
-   from chat. Normalize current arguments to idea, `ship_preflight: yes|no`,
+   from chat. After compaction or a resumed session, read `.devrites/ACTIVE`, then
+   the `state.md` cursor, `questions.md`, `decisions.md`, and `test-plan.md`/`evidence.md`.
+   Normalize current arguments to idea, `ship_preflight: yes|no`,
    `max_slices: N|default`, `profile: standard|full`, and `cross_model: yes|no`.
    **Completion:** normalized state is unambiguous and no sentinel or workspace file has been written.
 2. **Specify and clarify.** Run `devrites-interview`, `/rite-spec`, and
@@ -111,7 +114,7 @@ Use one terse line:
 
 ```text
 Autocomplete: <slug>
-spec <done|stopped> · clarify <clear|stopped> · temper <done|skipped|stopped> · define <done|stopped> · vet <ready|stopped> · build <n/N|stopped> · prove <done|stopped> · polish <done|stopped> · review <done|stopped> · seal <GO|NO-GO|stopped>
+spec <done|stopped> · clarify <clear|stopped> · temper <done|stopped> · define <done|stopped> · vet <ready|stopped> · build <n/N|stopped> · prove <done|stopped> · polish <done|stopped> · review <done|stopped> · seal <GO|NO-GO|stopped>
 ```
 
 Final state is `Shipped`, `Stopped`, `Awaiting human`, `NO-GO`, or `GO`; do not

package/pack/.claude/skills/rite-build/SKILL.md

@@ -9,15 +9,18 @@ user-invocable: true
 
 Build and prove one slice. HITL stops; a later user invocation starts the next.
 Explicit `.devrites/AFK` alone lets the controlling root chain pending slices
-serially under green proof, caps, and pause rules. Every wright returns after it.
+serially under green proof, caps, and pause rules. Every wright returns after one slice.
 **Opt-in:** `/rite-build --parallel N` (2≤N≤3; N=1≡serial) follows
-[`reference/parallel-batch.md`](reference/parallel-batch.md).
+[`reference/parallel-batch.md`](reference/parallel-batch.md)
+([`one-slice-cycle.md`](reference/one-slice-cycle.md)).
 
 Root owns gates/bookkeeping. Fresh
 [`devrites-slice-wright`](../../agents/devrites-slice-wright.md) writes product
 source/tests. Workflow Artifact paths use
 [`workflow-artifacts.md`](../devrites-lib/reference/standards/workflow-artifacts.md).
-Execute [`reference/phase-contract.md`](reference/phase-contract.md); dispatch uses
+Execute [`reference/phase-contract.md`](reference/phase-contract.md)
+([`one-slice-cycle.md`](reference/one-slice-cycle.md),
+[`afk-discipline.md`](reference/afk-discipline.md)); dispatch uses
 [`reference/wright-dispatch.md`](reference/wright-dispatch.md).
 
 ## Required rules

package/pack/.claude/skills/rite-build/reference/afk-discipline.md

@@ -47,7 +47,7 @@ The controlling root owns the cap:
 Use this stop message:
 
 ```text
-AFK cap reached. Raise `state.md` `AFK slices remaining` or remove the sentinel to continue.
+AFK cap reached. Raise `state.md` `afk_slices_remaining`/`AFK slices remaining` or remove the sentinel to continue.
 ```
 
 `max_slices` itself is read-only and never rewritten. No exit-code command
@@ -122,7 +122,7 @@ DevRites does not implement notifications; the configured hook does.
 Drop the sentinel before:
 
 - A new feature when `/rite-build` has not yet completed successfully on this codebase
-  in HITL. Ralph's progression is HITL first → refine prompt → AFK after validation.
+  in HITL.
 - A risky slice you marked `Mode: HITL` and want to walk through interactively even if
   the gate is technically `validating`.
 - Any time you'd rather review per-slice than batch-resolve afterwards.

package/pack/.claude/skills/rite-build/reference/checkpoint.md

@@ -29,7 +29,9 @@ BODY
 ## Restore
 After a crash, a fresh session may read the last `WIP(<slug>)` body as crash context.
 Authoritative state remains in `.devrites/`: validate the body against that workspace;
-never reconstruct, overwrite, or advance state from the commit body alone.
+never reconstruct or advance state from the commit body. Reload per
+[`context-hygiene.md`](../../devrites-lib/reference/standards/context-hygiene.md)
+(`.devrites/ACTIVE`, `state.md`, `questions.md`, `decisions.md`, `test-plan.md`/`evidence.md`).
 
 ## Collapse at ship
 WIP commits are scratch and never reach shared history. `/rite-ship` folds them into the

package/pack/.claude/skills/rite-build/reference/output.md

@@ -5,7 +5,7 @@
 ```text
 Done: built slice <n> — <name>.
 Changed: <files>; state.md, touched-files.md, evidence.md
-Evidence: acceptance met; tests <cmd->pass>; browser <summary|n/a>; drift <none|handled>
+Evidence: acceptance met; tests <cmd> → pass; browser <summary|n/a>; drift <none|handled>
 Open: <none|blockers|questions>
 Next: /rite-build
 Record: .devrites/work/<slug>/evidence.md
@@ -17,7 +17,7 @@ Record: .devrites/work/<slug>/evidence.md
 ```text
 Done: built slice <n> — <name>; all slices built.
 Changed: <files>; state.md, touched-files.md, evidence.md
-Evidence: acceptance met; tests <cmd->pass>; browser <summary|n/a>; drift <none|handled>
+Evidence: acceptance met; tests <cmd> → pass; browser <summary|n/a>; drift <none|handled>
 Open: <none|blockers|questions>
 Next: /rite-prove
 Record: .devrites/work/<slug>/evidence.md

package/pack/.claude/skills/rite-build/reference/parallel-batch.md

@@ -21,11 +21,12 @@ duplicates, absolutes, `.devrites/**`. Empty pairwise intersection required.
 
 **SSOT:** `devrites-engine check path-disjoint [--root <dir>] [<json-file>|-]`
 (N≥2 only; pass `--root`). Exit `0` → fan-out; else force serial. Inspect-time
-overlap → sibling **gap** → abort.
+overlap → sibling **gap** → abort. **Failing case:** two parallel wrights share a
+path and fan-out proceeds without that check.
 
 ## Control vs workers
 
-Control owns `.devrites/work/<slug>/` (`parallel-lease.md` + bookkeeping).
+Control owns `.devrites/work/<slug>/` (lease + bookkeeping).
 Workers: `.scratch/parallel-wt/<batch>/<slice>/` on
 `devrites/parallel/<slug>/<batch>/<slice>` @ base `B`. Wrights never write
 `.devrites/**`.
@@ -57,6 +58,22 @@ devrites-engine parallel lease-write|lease-read|lease-clear
 
 Go is SSOT. Skill calls the engine — never ad-hoc git/bash orchestration.
 
+## Runtime isolation
+
+Each parallel worktree must own isolated runtime resources. Before fan-out,
+assign per-slice env (document in the lease or worktree README):
+
+| Resource | Pattern |
+| --- | --- |
+| HTTP port | `PORT=<base+N>` or `DEVRITES_PARALLEL_PORT_<slice>` |
+| Compose | `COMPOSE_PROJECT_NAME=devrites-<slug>-<batch>-<slice>` |
+| SQLite/DB file | separate path under the worktree or `/tmp` |
+| Dev server | one process per worktree; never share a listener |
+
+Reusing the control worktree's running server, DB, or compose stack across
+siblings causes cross-slice pollution and flaky proof. Abort if isolation cannot
+be established.
+
 ## Host
 
 Claude: N concurrent Task wrights (`acceptEdits`, cwd=worktree). Codex: require

package/pack/.claude/skills/rite-build/reference/phase-contract.md

@@ -25,14 +25,14 @@ Opt-in `--parallel N` uses [`parallel-batch.md`](parallel-batch.md) instead of s
    dispatch the exact `devrites-slice-wright` fresh. Root never writes those product
    paths, wright never widens, and a missing profile stops.
 <!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"Build gate enters or resumes transaction","action":"invoke canonical operation table; reconcile exact result","return":"same slice/checkpoint cursor or Plan/Vet route"} -->
-1. **Inspect the return.** Wait; compare its file list and `git diff --name-only`
+4. **Inspect the return.** Wait; compare its file list and `git diff --name-only`
    with the contract. Reject stale, partial, malformed, or out-of-scope work.
    Preserve user work; source restoration uses the same bounded wright.
-2. **Challenge stood decisions.** For each stood decision, run exact
+5. **Challenge stood decisions.** For each stood decision, run exact
    `devrites-doubt-reviewer` fresh/read-only and record accepted or resolved-rejected
    in `decisions.md`. A missing verdict, principle breach, scope change, or
    irreversible risk blocks.
-3. **Prove without guessing.** Against the frozen pre-slice candidate, inspect
+6. **Prove without guessing.** Against the frozen pre-slice candidate, inspect
    test hunks for deletion, skipping/focus, tautology, or weaker expectations. Dispatch exact
    `devrites-test-analyst` on that immutable diff; missing account or adverse criterion
    verdict is Critical. Run only `test-plan.md` repository/CI commands, capture output,
@@ -48,14 +48,14 @@ Opt-in `--parallel N` uses [`parallel-batch.md`](parallel-batch.md) instead of s
    is progress; a different Critical/Important invariant gets its own fingerprint.
    Ask humans only for product decisions,
    irreversible risk, or genuinely human-only access.
-4. **Record.** After green proof, upsert `touched-files.md`'s authoritative candidate
+7. **Record.** After green proof, upsert `touched-files.md`'s authoritative candidate
    manifest from the actual scoped diff with explicit `present`/`deleted` rows;
    update `state.md`, `evidence.md`, and applicable UI/browser evidence. The manifest
    stays mutable until Polish closes it.
    Record stood decisions/dead ends in `decisions.md`; update checked assumptions'
    status/evidence, never leaving a disproved row live. If code reveals a durable
    project rule, propose a reviewed `AGENTS.md`/nearest-doc update, not a scored ledger.
-5. **AFK and reply.** Under `afk-discipline.md`, root charges
+8. **AFK and reply.** Under `afk-discipline.md`, root charges
    exactly once after each green built slice, never below zero; stop before another dispatch at zero, and fail closed
    on malformed budget. Use the reply contract; name the next pending slice or, only
    when all slices are built, `/rite-prove`. Emit no decorative progress renderer or

package/pack/.claude/skills/rite-build/reference/tdd.md

@@ -18,8 +18,9 @@ produce evidence:
 - Capture the new behavior the same way. The before/after pair *is* the proof.
 
 ## Rules
-- Use the project's existing test framework and commands (discovered in `spec.md` →
-  "Commands discovered"). Don't introduce a new test runner to prove a slice.
+- Use the project's existing test framework and commands (per the discovery contract
+  `rite-prove/reference/test-command-discovery.md`). Don't introduce a new test runner
+  to prove a slice.
 - One behavior per test; name it for the behavior, not the function.
 - A green test you never saw fail proves nothing: always see red first.
 - Don't delete or weaken a failing test to "pass". If it's wrong, that may be drift.

package/pack/.claude/skills/rite-build/reference/wright-dispatch.md

@@ -34,10 +34,9 @@ run approved proof, record evidence, then let host remove worktree.
 
 Conflict, extra/missing commit, moved base, or cleanup failure is `gap`/STOP:
 preserve the worktree and commit. Without explicit reconciliation, use same-worktree serial.
-Parallel writer work remains forbidden until this serial pilot measures transfer,
-conflict, proof, and review outcomes on both hosts. Opt-in `/rite-build --parallel N`
-(2≤N≤3) is the only exception: path-disjoint fan-out, abort-batch, and control
-`parallel-lease.md` under [`parallel-batch.md`](parallel-batch.md). Same-worktree multi-writer / root-emulated
+Parallel isolated-writer worktrees remain forbidden until this serial pilot measures
+transfer, conflict, proof, and review outcomes on both hosts; opt-in `/rite-build --parallel N`
+(2≤N≤3) path-disjoint fan-out is the only sanctioned parallel mode. Same-worktree multi-writer / root-emulated
 worktrees stay forbidden.
 
 ## Prepare
@@ -56,7 +55,8 @@ worktrees stay forbidden.
    A new path requires a new bounded contract; the wright cannot widen the task.
 3. Record `git diff --name-only` before dispatch so unrelated work remains
    distinguishable. For an isolated pilot, also record committed base SHA and exact
-   baseline status before asking the host for isolation.
+   baseline status before asking the host for isolation. **Failing case:** paths that
+   were dirty at that baseline are listed as slice-owned after dispatch.
 
 ## Run
 
@@ -68,8 +68,8 @@ Opt-in `/rite-build --parallel N` fans out only under [`parallel-batch.md`](para
 ## Inspect and prove
 
 1. Compare the returned file list and `git diff --name-only` with task paths.
-   Reject a result that omits any required key, including empty-or-filled
-   bookkeeping arrays, or adds a path. Restore only through the same bounded
+   Reject a result that omits any required key — the bookkeeping arrays count
+   whether empty or filled — or adds a path. Restore only through the same bounded
    wright; root never widens scope or edits source.
 2. Inspect the test diff for deletion, skipping, focus markers, or loosened
    assertions. Dedicated test analysis treats weakening as Critical.

package/pack/.claude/skills/rite-clarify/SKILL.md

@@ -17,7 +17,7 @@ Reuse [`devrites-interview`](../devrites-interview/SKILL.md) in `/clarify mode`.
 
 ## Rules consulted
 
-Read `devrites-lib/reference/standards/core.md`, its `afk-hitl.md`, and
+Read [`core.md`](../devrites-lib/reference/standards/core.md), its `afk-hitl.md`, and
 [`reference/decision-coverage.md`](reference/decision-coverage.md). Fresh evidence
 dispatch uses
 [`agents.md`](../devrites-lib/reference/standards/agents.md).
@@ -53,8 +53,9 @@ dispatch uses
    the scan until no blocking Partial/Missing row or unowned material assumption
    remains.
 5. **Write the verdict.** Write `Decision coverage: CLEAR` only after re-reading all inputs and confirming
-   every material row has current evidence and an owner. Normal flow sets `Phase: clarify` and
-   `Next step: /rite-temper`. A contract-neutral later-phase return uses
+   every material row has current evidence and an owner. Normal flow sets `phase=clarify` and
+   `next_action=/rite-temper`. A low-stakes spec — the significance trigger temper itself
+   skips (rite-temper step 1) — sets `next_action=/rite-define` instead. A contract-neutral later-phase return uses
    the native restore below; changed behavior or acceptance routes to
    `/rite-plan repair` instead. Stop without starting the next phase.
 
@@ -89,9 +90,9 @@ Done: decision coverage closed for <slug>; <n> topology surfaces scanned.
 Changed: decision-coverage.md, spec.md, decisions.md, assumptions.md, questions.md
 Evidence: Decision coverage: CLEAR; human packets <n>; agent-owned facts <n>
 Open: none blocking; deferred-nonblocking <n>
-Next: /rite-temper
+Next: /rite-temper (or /rite-define for a low-stakes spec temper skips)
 Record: .devrites/work/<slug>/decision-coverage.md
-↻ Hygiene: /clear before /rite-temper
+↻ Hygiene: /clear before /rite-temper (or /rite-define)
 ```
 
 If not clear, name the exact rows and next genuine decision packet. An objective spec defect

package/pack/.claude/skills/rite-converge/SKILL.md

@@ -77,21 +77,22 @@ Pull on demand:
    get built); from `tasks.md`: existing slices + their `Satisfies:`; from
    `.devrites/principles.md`: the invariants.
    **Completion:** every buildable criterion, touch-point, slice output, and principle is in the assessment inventory.
-3. **Reconcile the map, then read the code.** Compare `spec.md`, `tasks.md`, and
-   `traceability.md` directly: every buildable AC/REQ maps to an existing slice, every slice maps
-   back to real acceptance, and the mapped prose preserves the requirement's meaning. Record
-   orphaned, invented, duplicate, or contradictory mappings as gaps. Then read the live code
+3. **Reconcile the map, then read the code.** Compare `spec.md`, `tasks.md`,
+   `test-plan.md`, and `traceability.md` directly: every buildable AC/REQ maps to an
+   existing slice, every slice maps back to real acceptance, every slice's recorded
+   proof still agrees with its `test-plan.md` row, and the mapped prose preserves the
+   requirement's meaning. Record orphaned, invented, duplicate, or contradictory
+   mappings as gaps. Then read the live code
    (code-intelligence index per `tooling.md`); artifact mappings never prove implementation.
 4. **Assess each unit as built / partial / absent** against the live code (the rubric is in
    [`reference/convergence-assessment.md`](reference/convergence-assessment.md)): every
    acceptance criterion / scenario, every plan touch-point, and every existing slice's stated
    Produces. A principle violated in the current code is its own top-severity gap.
    Dispatch up to three independent inventory partitions to `devrites-evidence-scout` on the
-   same frozen candidate, await their dossiers, then reconcile the cited facts in the root
+   same live-code snapshot, await their dossiers, then reconcile the cited facts in the root
    context. **Completion:** every inventory unit is classified once with live-code evidence.
 5. **Enqueue the remainder as new slices.** For each *partial* or *absent* unit, append a
-   `## SLICE-###` (continue the numbering after the highest existing id) in the `rite-define`
-   slice grammar, each with a `Satisfies:` line tracing to the AC/REQ it closes and a
+   `## SLICE-###` (continue the numbering after the highest existing id), each with a `Satisfies:` line tracing to the AC/REQ it closes and a
    `Convergence: <iso>` marker line. Dependency-order them after the existing slices; a
    principle-remediation slice sorts first. **If every unit is built → append nothing.**
    **Completion:** every partial/absent unit has one traceable appended slice, or the file is byte-for-byte unchanged.