devrites 6.0.3 → 6.1.0

package/pack/generated/omp/skills/rite-frame/SKILL.md

@@ -6,7 +6,7 @@ user-invocable: true
 ---
 
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","rite-frame/reference/failure-modes.md"],"triggers":{"principles":["devrites-lib/reference/standards/principles.md"],"simplify":["devrites-lib/reference/standards/coding-style.md","devrites-lib/reference/standards/patterns.md"],"testing":["devrites-lib/reference/standards/testing.md"]},"workspace":[]} -->
-> Read-set manifest: `devrites-engine context <slug> --phase frame` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --phase frame` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
 # /rite-frame: frame the goal, audit the diff
@@ -71,19 +71,19 @@ map + worked examples: [`reference/failure-modes.md`](reference/failure-modes.md
 
 - [ ] **1 · Silent assumption**: did I pick one reading of an ambiguous ask and run with it?
       Any value, contract, or behavior I *guessed*? → surface it; route material ones through
-      the Spec Drift Guard ([`core.md`](../devrites-lib/reference/standards/core.md) #4; surface per #2/#3).
+      the Spec Drift Guard ([`core.md`](skill://devrites-lib/reference/standards/core.md) #4; surface per #2/#3).
 - [ ] **2 · Overcomplication**: an abstraction / flag / indirection nobody asked for? 200 lines
       where 50 would do? A defensive check inside trusted code? → apply the **deletion test**;
-      simplify ([`coding-style.md`](../devrites-lib/reference/standards/coding-style.md), [`patterns.md`](../devrites-lib/reference/standards/patterns.md), `devrites-audit simplify`).
+      simplify ([`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md), [`patterns.md`](skill://devrites-lib/reference/standards/patterns.md), `devrites-audit simplify`).
 - [ ] **3 · Out-of-scope edit**: did I touch code, comments, or formatting outside the ask?
       "While I'm here" refactors? → revert to the boundary; record the rest as an FYI follow-up
-      ([`core.md`](../devrites-lib/reference/standards/core.md) #7, `touched-files.md`).
+      ([`core.md`](skill://devrites-lib/reference/standards/core.md) #7, `touched-files.md`).
 - [ ] **4 · Unverifiable goal**: is there a command that proves this, run, with output? Or am
       I asserting "it works"? Tautological test that can't fail? → run the FRAME verify command;
-      record command + output ([`testing.md`](../devrites-lib/reference/standards/testing.md), evidence-over-confidence).
+      record command + output ([`testing.md`](skill://devrites-lib/reference/standards/testing.md), evidence-over-confidence).
 - [ ] **Principle check**, if `.devrites/principles.md` exists, does the change break a declared
       invariant? A violation with no recorded, human-approved exception is a **Critical**: the
-      express lane is not a way around a project gate; escalate it, don't ship it ([`principles.md`](../devrites-lib/reference/standards/principles.md)).
+      express lane is not a way around a project gate; escalate it, don't ship it ([`principles.md`](skill://devrites-lib/reference/standards/principles.md)).
 
 The test for each changed line: **it traces directly to the criterion, and the criterion can
 be proven false.** A line that fails either is a finding.

package/pack/generated/omp/skills/rite-frame/reference/failure-modes.md

@@ -8,10 +8,10 @@ reach the normal gates.
 
 | # | Failure mode | The tell in a diff / a reply | Cure already in the pack |
 |---|---|---|---|
-| 1 | **Silent assumption** | A value, contract, edge case, or interpretation was *guessed* and run with: no note, no question. The ask had two readings and one was picked silently. | [`core.md`](../../devrites-lib/reference/standards/core.md) #2 (no silent assumptions) / #3 (no guessing through confusion); the Spec Drift Guard; `devrites-doubt` for a single high-stakes call; `devrites-interview` when the ask is underspecified. |
-| 2 | **Overcomplication** | An abstraction, flag, config knob, or indirection nobody asked for. 200 lines where 50 would do. A single-use factory. Defensive `try/catch` + null checks inside trusted code. A dependency added where an in-repo option exists. | [`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md) (simplicity, reuse-first), [`patterns.md`](../../devrites-lib/reference/standards/patterns.md) (avoid over-engineering), `devrites-audit simplify` (deletion test, Chesterton's Fence), the "over-defensive guarding is slop" anti-pattern. |
-| 3 | **Out-of-scope edit** | Touched code, comments, or formatting outside the ask. A "while I'm here" refactor. Renamed something orthogonal. Reflowed an import block. | [`core.md`](../../devrites-lib/reference/standards/core.md) #7 (feature scope only), the exact paths stated in the writer task, `git diff --name-only` plus `touched-files.md`, and the "it's only a small refactor" anti-pattern. |
-| 4 | **Unverifiable goal** | "It works" with no command, no output, no test. A success criterion that can't be false ("make it better"). A tautological test that passes no matter what. | [`acceptance-criteria.md`](../../rite-spec/reference/acceptance-criteria.md) (measurable acceptance), [`core.md`](../../devrites-lib/reference/standards/core.md) #6 (evidence over confidence), [`testing.md`](../../devrites-lib/reference/standards/testing.md) (assertion strength, see it fail first), the TDD wright. |
+| 1 | **Silent assumption** | A value, contract, edge case, or interpretation was *guessed* and run with: no note, no question. The ask had two readings and one was picked silently. | [`core.md`](skill://devrites-lib/reference/standards/core.md) #2 (no silent assumptions) / #3 (no guessing through confusion); the Spec Drift Guard; `devrites-doubt` for a single high-stakes call; `devrites-interview` when the ask is underspecified. |
+| 2 | **Overcomplication** | An abstraction, flag, config knob, or indirection nobody asked for. 200 lines where 50 would do. A single-use factory. Defensive `try/catch` + null checks inside trusted code. A dependency added where an in-repo option exists. | [`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md) (simplicity, reuse-first), [`patterns.md`](skill://devrites-lib/reference/standards/patterns.md) (avoid over-engineering), `devrites-audit simplify` (deletion test, Chesterton's Fence), the "over-defensive guarding is slop" anti-pattern. |
+| 3 | **Out-of-scope edit** | Touched code, comments, or formatting outside the ask. A "while I'm here" refactor. Renamed something orthogonal. Reflowed an import block. | [`core.md`](skill://devrites-lib/reference/standards/core.md) #7 (feature scope only), the exact paths stated in the writer task, `git diff --name-only` plus `touched-files.md`, and the "it's only a small refactor" anti-pattern. |
+| 4 | **Unverifiable goal** | "It works" with no command, no output, no test. A success criterion that can't be false ("make it better"). A tautological test that passes no matter what. | [`acceptance-criteria.md`](skill://rite-spec/reference/acceptance-criteria.md) (measurable acceptance), [`core.md`](skill://devrites-lib/reference/standards/core.md) #6 (evidence over confidence), [`testing.md`](skill://devrites-lib/reference/standards/testing.md) (assertion strength, see it fail first), the TDD wright. |
 
 Karpathy named the first three. The fourth supplies the falsifiable criterion needed
 for an agent to work without repeated human confirmation. FRAME defines that criterion

package/pack/generated/omp/skills/rite-handoff/SKILL.md

@@ -6,7 +6,7 @@ disable-model-invocation: true
 argument-hint: "[what the next session will focus on]"
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","rite-handoff/reference/handoff-template.md","devrites-lib/reference/reply-contract.md"],"triggers":{"hygiene":["devrites-lib/reference/standards/context-hygiene.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-handoff` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --skill rite-handoff` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # /rite-handoff: chat-only context, into a fresh-agent doc
 
@@ -15,7 +15,7 @@ persist (spec, plan, tasks, decisions, evidence, drift, review). This skill capt
 what the **chat** is holding that is **not** in the workspace, so a fresh agent (or
 the same user after `/clear`) can pick the work up without re-reading the transcript.
 
-Read [`core.md`](../devrites-lib/reference/standards/core.md) first: its "Persistence before stopping" discipline is
+Read [`core.md`](skill://devrites-lib/reference/standards/core.md) first: its "Persistence before stopping" discipline is
 exactly what this skill executes. The other rule files load on demand.
 
 Then read the explicit or active workspace's `state.md` directly, and run
@@ -48,8 +48,9 @@ For each of these, write the content into its **canonical home** first, then mer
 - **Assumption** about behaviour / API / user intent → append to `assumptions.md`.
 - **Drift event raised but not fully resolved** → update `drift.md` with the current
   resolution status (open / asked-user / repaired).
-- **Files modified in chat not yet in `touched-files.md`** → append to
-  `touched-files.md`.
+- **Files modified in chat not yet in `touched-files.md`** → no recorded provenance, so
+  record them as drift in `drift.md` (or a `questions.md` entry); never append them to
+  `touched-files.md`, the candidate manifest Ship stages.
 
 The handoff doc itself then says "synced N entries into decisions.md", not the entries
 themselves. The workspace is the canonical store; the handoff is the chat-only delta.
@@ -94,7 +95,7 @@ themselves. The workspace is the canonical store; the handoff is the chat-only d
 Loaded on demand from [`reference/handoff-template.md`](reference/handoff-template.md).
 Fill in each section and write to `.devrites/work/<slug>/handoff.md` (or to a temp
 file when no active feature). Then use the compact reply contract
-([`devrites-lib/reference/reply-contract.md`](../devrites-lib/reference/reply-contract.md)):
+([`devrites-lib/reference/reply-contract.md`](skill://devrites-lib/reference/reply-contract.md)):
 
 ```
 Done: handoff written for <slug | session>.
@@ -110,7 +111,7 @@ Print the absolute path in `Record:` so the user or next agent can open it witho
 
 ## Session hygiene
 Close with the one-line hygiene advisory + the single resume command. This skill *is* the
-pre-`/clear` bridge, so it's where the advisory matters most ([`context-hygiene.md`](../devrites-lib/reference/standards/context-hygiene.md)):
+pre-`/clear` bridge, so it's where the advisory matters most ([`context-hygiene.md`](skill://devrites-lib/reference/standards/context-hygiene.md)):
 ```
 ↻ Hygiene: /clear
 ```

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

@@ -6,7 +6,7 @@ user-invocable: true
 disable-model-invocation: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/documentation.md","devrites-lib/reference/standards/tooling.md"],"workspace":["state.md","decisions.md","drift.md","evidence.md","review.md","seal.md","questions.md"],"workspaceByRole":{"retrospector":["state.md","decisions.md","drift.md","evidence.md","review.md","seal.md","questions.md"]},"triggers":{"agents":["devrites-lib/reference/standards/agents.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-learn` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --skill rite-learn` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # /rite-learn: review durable lessons
 
@@ -20,7 +20,7 @@ of one authority; it cannot promote a rule alone.
 
 ## Workflow
 
-1. Read [durable promotion](../devrites-lib/reference/standards/documentation.md#promote-durable-guidance).
+1. Read [durable promotion](skill://devrites-lib/reference/standards/documentation.md#promote-durable-guidance).
    Before bounding, fixed-string search all of `.devrites/archive/` and active
    `decisions.md` for `rite-learn: accepted` and `rite-learn: declined`; read every hit
    whole. Then bound the archive; inspect applicable `AGENTS.md`/`CLAUDE.md`, accepted ADRs, and relevant `.devrites/archive/*/{decisions,drift,review,seal}.md`.
@@ -28,15 +28,15 @@ of one authority; it cannot promote a rule alone.
 2. Broad mode dispatches exact fresh/read-only `devrites-retrospector`; reconcile its claims against cited files.
    A missing, failed, timed-out, or malformed result reports `Candidate: NOT-RUN
    (unavailable: <reason>)` as a gap, never `Candidate: none`; an unavailable role stops
-   for HITL per [`agents.md`](../devrites-lib/reference/standards/agents.md) (trigger `agents`).
-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.
+   for HITL per [`agents.md`](skill://devrites-lib/reference/standards/agents.md) (trigger `agents`).
+3. Keep corrections repeated in two features (a `## Carry-forward constraints` rule recurring in two archived `decisions.md` qualifies), a judgement call made twice, or a defect class seen twice; drop one-off preferences, task-specific detail, generic advice.
    Broad mode also proposes **retirements**: a rule found via a `rite-learn: accepted`
    marker whose cited failing case or owner no longer exists in live source, whose
    review-by date passed unverified, or that is a model-default no-op. Zero is valid but
    names the searched scope; a rule still guarding a live failing case is never retired.
 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 a dated citation per
-   [[`tooling.md`](../devrites-lib/reference/standards/tooling.md) § Research provenance](../devrites-lib/reference/standards/tooling.md#research-provenance-staleness-and-cost).
+   [[`tooling.md`](skill://devrites-lib/reference/standards/tooling.md) § Research provenance](skill://devrites-lib/reference/standards/tooling.md#research-provenance-staleness-and-cost).
    **Failing case:** "best practice is X" with no source → reject promotion.
 5. Apply durable promotion's recoverability test; search same/contrary rules, choose one existing owner (nearest instruction/standard, 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.
@@ -63,7 +63,7 @@ of one authority; it cannot promote a rule alone.
   owner → human approval of the exact edit. A skipped stage is no promotion.
 - **Recurrence ⇒ mechanism.** When `Authority: existing <path>` already holds the violated
   rule, the candidate is a check, gate, template slot, or default at that owner
-  ([`skill-authoring.md`](../devrites-lib/reference/standards/skill-authoring.md#match-form-to-failure) § Match form to failure),
+  ([`skill-authoring.md`](skill://devrites-lib/reference/standards/skill-authoring.md#match-form-to-failure) § Match form to failure),
   never a reworded, bolder, or relocated copy; otherwise record `no mechanical form
   possible: <reason>` and narrow the proposal. An unwired or broken existing check is
   itself the candidate. **Failing case:** a round accepts a bolder copy of an `AGENTS.md`

package/pack/generated/omp/skills/rite-plan/SKILL.md

@@ -6,7 +6,7 @@ user-invocable: true
 ---
 
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","devrites-lib/reference/standards/tooling.md","devrites-lib/reference/standards/agents.md","rite-plan/reference/slicing.md","rite-plan/reference/replan-and-repair.md","rite-plan/reference/dependency-graph.md","rite-plan/reference/task-breakdown.md","rite-plan/reference/anti-patterns.md","rite-define/reference/plan-template.md"],"triggers":{"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"one-shot":["devrites-lib/reference/standards/one-shot-actions.md"],"assumption-delta":["devrites-lib/reference/standards/assumption-checkpoints.md"],"workflow":["devrites-lib/reference/standards/development-workflow.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","drift.md"],"workspaceByRole":{"plan-drafter":["brief.md","spec.md","plan.md","tasks.md","decision-coverage.md","questions.md","decisions.md","assumptions.md","architecture.md","state.md","drift.md"]}} -->
-> Read-set manifest: `devrites-engine context <slug> --phase plan` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --phase plan` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
 # /rite-plan: (re)plan an active feature
@@ -18,11 +18,11 @@ artifact-only**: reconcile
 editing source code.
 
 ## Rules consulted (read on demand from `.omp/skills/devrites-lib/reference/standards/`)
-Pull [`development-workflow.md`](../devrites-lib/reference/standards/development-workflow.md) via `Read` when reshaping slice cadence or DoD
+Pull [`development-workflow.md`](skill://devrites-lib/reference/standards/development-workflow.md) via `Read` when reshaping slice cadence or DoD
 criteria.
-Load [`repository-topology.md`](../devrites-lib/reference/standards/repository-topology.md), [`data-integrity.md`](../devrites-lib/reference/standards/data-integrity.md), or [`integration-reliability.md`](../devrites-lib/reference/standards/integration-reliability.md)
+Load [`repository-topology.md`](skill://devrites-lib/reference/standards/repository-topology.md), [`data-integrity.md`](skill://devrites-lib/reference/standards/data-integrity.md), or [`integration-reliability.md`](skill://devrites-lib/reference/standards/integration-reliability.md)
 when the spec applicability map or observed drift triggers them.
-Load [`assumption-checkpoints.md`](../devrites-lib/reference/standards/assumption-checkpoints.md) (trigger `assumption-delta`)
+Load [`assumption-checkpoints.md`](skill://devrites-lib/reference/standards/assumption-checkpoints.md) (trigger `assumption-delta`)
 when scope introduces a second case, an optional field, or a chosen-over-derived value.
 Before classifying any Reslice, read `.omp/skills/devrites-lib/reference/standards/acceptance-preserving-reslice.md`.
 
@@ -43,7 +43,7 @@ Before classifying any Reslice, read `.omp/skills/devrites-lib/reference/standar
   the irreducible complexity. Honor each slice's `depends_on:`: the next *buildable* slice is the
   lowest pending one whose dependencies are all built. This preserves one-slice-at-a-time execution.
 - **Root writes; drafter proposes.** Follow
-  [`agents.md`](../devrites-lib/reference/standards/agents.md). The controlling chat owns
+  [`agents.md`](skill://devrites-lib/reference/standards/agents.md). The controlling chat owns
   human questions, decisions, reconciliation, and planning writes.
 - **Nested repair preserves its caller.** When `state.md` contains a valid
   technical-backtracking return cursor, preserve any valid return cursor
@@ -85,7 +85,7 @@ Before classifying any Reslice, read `.omp/skills/devrites-lib/reference/standar
    builds its bundle with `--slice <SLICE-ID>` per affected slice. Await one atomic, read-only
    the drafter's `candidate_files` bundle; human choices return separately.
    When the observed failure is missing or ambiguous consumptive-action evidence,
-   require the drafter to apply [`one-shot-actions.md`](../devrites-lib/reference/standards/one-shot-actions.md) and return the bounded
+   require the drafter to apply [`one-shot-actions.md`](skill://devrites-lib/reference/standards/one-shot-actions.md) and return the bounded
    diagnostic-amplification design, injective boundary map, per-seam fixtures, and
    collision mutant. Past evidence loss is not terminal. The drafter supplies no bodies.
    A repair candidate carries a delta self-check scoped to what the patch
@@ -123,10 +123,10 @@ Before classifying any Reslice, read `.omp/skills/devrites-lib/reference/standar
    auto-declared.
    Bind exact active `.devrites/work/<slug>/` targets and executable contract; after Vet READY, root
    materializes the exact vetted workflow-artifact paths under
-   [`workflow-artifacts.md`](../devrites-lib/reference/standards/workflow-artifacts.md)
+   [`workflow-artifacts.md`](skill://devrites-lib/reference/standards/workflow-artifacts.md)
    without dispatching the product wright.
 3. Reason about dependencies: [dependency-graph](reference/dependency-graph.md).
-   Reconcile the horizon register against `../rite-define/reference/plan-template.md`.
+   Reconcile the horizon register against `skill://rite-define/reference/plan-template.md`.
    Preserve every `HZN-###` and unresolved item. Cite evidence when reclassifying the earliest
    honest decision point; resolution or supersession also needs evidence. Never silently delete
    an item. Planning choices resolve from source evidence or become bounded risk spikes with

package/pack/generated/omp/skills/rite-plan/reference/anti-patterns.md

@@ -3,7 +3,7 @@
 Load this when standing a non-trivial re-plan decision, or when the agent
 feels reluctance toward asking the user before a behavior change.
 
-Pack-wide rationalizations + red flags: see [standards/anti-patterns.md](../../devrites-lib/reference/standards/anti-patterns.md).
+Pack-wide rationalizations + red flags: see [standards/anti-patterns.md](skill://devrites-lib/reference/standards/anti-patterns.md).
 
 Authority: `.omp/skills/devrites-lib/reference/standards/acceptance-preserving-reslice.md`.
 

package/pack/generated/omp/skills/rite-plan/reference/replan-and-repair.md

@@ -29,6 +29,8 @@ A drift event stopped the build. Steps:
 1. Read the `drift.md` entries and their classifications. Fold EVERY open entry
    and accepted finding for the affected artifacts in ONE pass, never serially.
 2. If the user answered a drift question, encode that decision in `decisions.md`.
+   Fold each `decisions.md` carry-forward constraint into `Prior-slice learnings`
+   of the remaining slices it affects.
 3. Update `spec.md` (only the affected sections) and `plan.md`/`tasks.md` to match
    reality. Adjust acceptance criteria if they were wrong.
    **Write the pointer, not the history.** Name the findings a fold closes by ID, one line
@@ -90,7 +92,7 @@ relocation only, by the phase owner when `orient` reports `over: true`.
 
 Unchanged acceptance/behavior with non-equivalent `proposed_coverage` is a
 contradictory input: the canonical classifier blocks it — there is no fourth
-route (see [`acceptance-preserving-reslice.md`](../../devrites-lib/reference/standards/acceptance-preserving-reslice.md)).
+route (see [`acceptance-preserving-reslice.md`](skill://devrites-lib/reference/standards/acceptance-preserving-reslice.md)).
 
 **Budget relocation** (authorized as above): move checkpoint narrative, historical fold text and
 closed-round accounts verbatim from `state.md`/`tasks.md`/`plan.md`/`architecture.md`/

package/pack/generated/omp/skills/rite-plan/reference/slicing.md

@@ -27,7 +27,7 @@ files may serve one inseparable capability. Full feature `/rite-prove` follows a
 slices; slice proof never replaces final integration or acceptance proof.
 
 For `Complexity` and irreducible boundaries, use the canonical
-[`tasks.md` slice grammar](../../devrites-lib/reference/workspace-artifact-schema.md#canonical-slice-grammar).
+[`tasks.md` slice grammar](skill://devrites-lib/reference/workspace-artifact-schema.md#canonical-slice-grammar).
 Keep the smallest cut that stands alone end-to-end; do not add slices or gates for
 fragments that can only pass together. No slice size guarantees first-pass correctness.
 
@@ -51,7 +51,7 @@ a 12-criterion feature is however many thin end-to-end cuts those 12 need.
 
 The derived count is also a size signal. A decomposition that cannot fit the
 `tasks.md` / `plan.md` / `traceability.md` budgets in
-[`workspace-artifact-schema.md`](../../devrites-lib/reference/workspace-artifact-schema.md)
+[`workspace-artifact-schema.md`](skill://devrites-lib/reference/workspace-artifact-schema.md)
 (about ten canonical slices) is an epic: every Vet/Doubt/Build review re-reads the
 whole surface, each round finds new material, and the loop never converges.
 `Budget override` never covers slice or acceptance-criteria count.
@@ -150,7 +150,7 @@ product:
 - What is full-surface here is the **review**: reviewers see the whole product diff.
   Re-proof stays targeted — this milestone's product ACs, everything a later milestone
   touched, and any uncertain closure. Milestone evidence is cited only under
-  [evidence validity](../../devrites-lib/reference/candidate-integrity.md#evidence-validity)
+  [evidence validity](skill://devrites-lib/reference/candidate-integrity.md#evidence-validity)
   with explicit unchanged-input/dependency justification and a link to the original
   account; a blind re-proof of every milestone AC is a recorded decision, not a default.
 
@@ -165,4 +165,6 @@ while pivoting is still cheap.
 
 ## Slice independence
 Order by dependency, but minimize coupling. A slice that needs three other slices first
-is a smell: look for a thinner cut that stands alone.
+is a smell: look for a thinner cut that stands alone. An edge exists only when this slice
+reads something the other produces: write it as `SLICE-001 (via <interface>)`. If you
+cannot name what crosses, drop the edge; a shallow, wide graph runs in parallel.

package/pack/generated/omp/skills/rite-plan/reference/task-breakdown.md

@@ -5,7 +5,7 @@ How to turn a spec into ordered, vertical slices in `tasks.md`.
 ## Each slice is one task
 
 Use the complete canonical grammar in
-[`workspace-artifact-schema.md`](../../devrites-lib/reference/workspace-artifact-schema.md#canonical-slice-grammar).
+[`workspace-artifact-schema.md`](skill://devrites-lib/reference/workspace-artifact-schema.md#canonical-slice-grammar).
 This reference owns decomposition; the shared schema owns field names and meanings.
 
 ## Process

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

@@ -6,7 +6,7 @@ user-invocable: true
 ---
 
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/candidate-integrity.md","rite-polish/reference/code.md","rite-polish/reference/anti-patterns.md","rite-polish/reference/anti-ai-slop.md","rite-polish/reference/harden-checklist.md","rite-polish/reference/ledger.md","rite-build/reference/checkpoint.md"],"triggers":{"adr":["rite-polish/reference/adr-promotion.md"],"agents":["devrites-lib/reference/standards/agents.md"],"backend":["rite-polish/reference/backend-polish.md"],"coding":["devrites-lib/reference/standards/coding-style.md","devrites-lib/reference/standards/duplicate-code.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"ui":["rite-polish/reference/ui.md","rite-polish/reference/design-memory.md","rite-polish/reference/design-system-discovery.md","rite-polish/reference/browser-polish-evidence.md","devrites-lib/reference/standards/browser-proof-checklist.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","evidence.md","touched-files.md","design-brief.md","browser-evidence.md","polish-report.md"],"workspaceByRole":{"slice-wright":["spec.md","architecture.md","plan.md","tasks.md","test-plan.md","state.md","decisions.md","design-brief.md"]}} -->
-> Read-set manifest: `devrites-engine context <slug> --phase polish` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --phase polish` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
 # /rite-polish: finish before review
@@ -27,7 +27,7 @@ read only the phase in scope.
 - **Functionality complete first.** Polish runs after `/rite-prove` (full
   feature proven).
 - Follow the shared
-  [`candidate-integrity.md`](../devrites-lib/reference/candidate-integrity.md).
+  [`candidate-integrity.md`](skill://devrites-lib/reference/candidate-integrity.md).
   Polish owns every candidate-affecting correction and durable rollup before Review.
 - Feature scope only.
 - For UI, **normalize before polishing**. Do not add decoration on top of drift.
@@ -38,7 +38,7 @@ read only the phase in scope.
 - **Root selects; wright edits.** The controlling chat assesses and reconciles, but every
   accepted source/test correction is dispatched to the sole writer,
   `devrites-slice-wright`, through
-  [`agents.md`](../devrites-lib/reference/standards/agents.md). Never edit source inline or
+  [`agents.md`](skill://devrites-lib/reference/standards/agents.md). Never edit source inline or
   run two correction writers concurrently.
 
 ## Polish axes (C3 — completeness vs craft)
@@ -57,7 +57,7 @@ Incomplete comparison is **not** agreement. Record axis deltas in `polish-report
 ## Orchestration
 
 0. **Read** `.omp/skills/devrites-lib/reference/standards/core.md` first (the always-on operating rules). The
-   per-phase rule files ([`coding-style.md`](../devrites-lib/reference/standards/coding-style.md), [`error-handling.md`](../devrites-lib/reference/standards/error-handling.md), …) load on demand
+   per-phase rule files ([`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md), [`error-handling.md`](skill://devrites-lib/reference/standards/error-handling.md), …) load on demand
    from `reference/code.md` / `reference/ui.md` when their phase runs; for UI scope also read
    `.omp/skills/devrites-lib/reference/standards/browser-proof-checklist.md`.
    Then read the explicit or active workspace's `state.md` directly.
@@ -79,7 +79,7 @@ Incomplete comparison is **not** agreement. Record axis deltas in `polish-report
    (code polish)**; if backend was touched, assess **Phase 2 (backend polish)** from
    the same file. Reconcile the findings, then send accepted corrections as one bounded
    wright contract: build its read-set with
-   `devrites-engine context <slug> --phase polish --role slice-wright`, run the
+   `devrites-engine context --skills-root .omp/skills <slug> --phase polish --role slice-wright`, run the
    single-agent wave through `devrites-engine dispatch <slug> open|start|seal|return`
    (auto-records dispatch/return metrics), and gate returned paths
    with `devrites-engine check diff-scope <slug> --allow <contract-paths>` before
@@ -110,7 +110,7 @@ Incomplete comparison is **not** agreement. Record axis deltas in `polish-report
    manifest. Record a **`Re-verification:`** line in `polish-report.md`. Close
    the candidate for Review only after these checks are green. Then checkpoint
    remaining candidate diffs per
-   [`checkpoint.md`](../rite-build/reference/checkpoint.md).
+   [`checkpoint.md`](skill://rite-build/reference/checkpoint.md).
 7. **Aggregate output:** each phase appends to the single `polish-report.md`.
 
 ## Refinement modes

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

@@ -19,7 +19,7 @@ a declared token, brief line or nearest neighbour (cite both locations), or it h
 measured user consequence (contrast ratio, overflow, CLS, lost or hidden focus). Otherwise
 it is an AES proposal under "Proposals (non-blocking)": never a Visual Verdict FAIL, never
 scored, capped at Suggestion, never blocking unless `design-brief.md` adopts it (then
-DS). Act on clusters per [`prose-style.md`](../../devrites-lib/reference/standards/prose-style.md).
+DS). Act on clusters per [`prose-style.md`](skill://devrites-lib/reference/standards/prose-style.md).
 A broken task, data loss or misleading state is reported and fixed before any AES item.
 **Failing case:** `tokens.css` declares Inter and a 20 px card radius, yet review files
 "reflex font" and "balloon radius" as Important; or three eyebrows on six sections become
@@ -46,7 +46,7 @@ routes to `devrites-prose-craft`; translation catalogs stay untouched without th
   micro-copy (badges, eyebrows); never for sentences.
 - [AES] **Em dashes in UI copy** are a lead, not a ban: DS only where the project's
   style guide bans them; otherwise no rule applies to product copy, because
-  [`prose-style.md`](../../devrites-lib/reference/standards/prose-style.md) governs DevRites
+  [`prose-style.md`](skill://devrites-lib/reference/standards/prose-style.md) governs DevRites
   prose, not product UI.
 - [AES] **Cards inside cards** — nested bordered/elevated containers.
 - [AES] **Identical card grids** for everything, regardless of content.
@@ -62,7 +62,7 @@ routes to `devrites-prose-craft`; translation catalogs stay untouched without th
 - [AES] **Modal-first thinking** — reaching for a modal as the answer to every interaction.
 - [AES] **Ghost-card** — a `1px` border *and* a soft (blur ≥16px) shadow on the same element.
   Borders separate; shadows lift — pick one
-  ([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md) — Materiality).
+  ([`quality-standards.md`](skill://devrites-frontend-craft/reference/quality-standards.md) — Materiality).
 - [AES] **Balloon radius** — `border-radius` above ~16px on cards, inputs, panels. Cards top
   out around 12–16px; full pills are for tags and buttons only.
 - [AES] **Uppercase tracked eyebrow above every section** — one named kicker is voice; one per
@@ -109,9 +109,9 @@ second one catches what the first one misses.
   teal", "fintech → navy + gold", "AI tool → black with a violet accent",
   "crypto → neon on black" — the styling is on the first training-data
   reflex. Rework the scene sentence
-  ([`design-references.md`](../../devrites-frontend-craft/reference/design-references.md)) and the
+  ([`design-references.md`](skill://devrites-frontend-craft/reference/design-references.md)) and the
   colour-commitment strategy
-  ([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md)) until the
+  ([`quality-standards.md`](skill://devrites-frontend-craft/reference/quality-standards.md)) until the
   answer isn't obvious from the domain.
 - **Second-order:** if a stranger looked at the surface with *no copy
   visible* and confidently said "this is a CRM / fitness tracker / fintech
@@ -144,10 +144,10 @@ its cap is a lead for the admission rule, not a failure:
   hop with no value. Inline or remove.
 - **Over-engineered abstractions** for trivial problems — a factory + interface + plugin
   registry for a 10-line function. **Don't add abstraction before two real callers**
-  (see [`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md), [`patterns.md`](../../devrites-lib/reference/standards/patterns.md)).
+  (see [`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md), [`patterns.md`](skill://devrites-lib/reference/standards/patterns.md)).
 - **Convention-blind** code — ignores the repo's naming, file layout, error patterns,
   validation style. "Generic good code" beats the project's idiom; reuse first (see
-  [`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md)).
+  [`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md)).
 - **Going beyond the spec** — features/options/configs/flags the spec didn't ask for.
   Implement exactly what was specified; flag extras as follow-ups.
 - **Comment noise — the most common code tell.** Default to **zero** comments; the code and
@@ -197,14 +197,14 @@ its cap is a lead for the admission rule, not a failure:
   account/provider/test ID inline with no name or source. Give it a name (a const) or a home
   (config/env). The mirror image of premature config, and just as much a tell.
 - **Copy-paste duplication** — a near-identical block pasted and tweaked instead of reused.
-  Reuse → extend → build new ([`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md), [`patterns.md`](../../devrites-lib/reference/standards/patterns.md)); duplication beats the *wrong*
+  Reuse → extend → build new ([`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md), [`patterns.md`](skill://devrites-lib/reference/standards/patterns.md)); duplication beats the *wrong*
   abstraction, but pasted clones are slop, not a deliberate AHA call.
 
 ## Why banned, what instead
 They signal model-generated rather than team-designed work: they ignore register and
 idiom, add noise, hide bugs (defensive catches), bloat diffs, and often fail a11y or
 correctness review. Instead: project tokens/components, validate at trust boundaries,
-catch narrow and rethrow, one clear name per concept, reuse first ([`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md)),
+catch narrow and rethrow, one clear name per concept, reuse first ([`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md)),
 implement exactly the spec. If the project intentionally uses one of these, follow the
 project — consistency beats the rule. A check or abstraction you can't justify in one
 sentence is slop: delete it or ask.

package/pack/generated/omp/skills/rite-polish/reference/anti-patterns.md

@@ -5,7 +5,7 @@ skip normalize, polish without Chesterton's Fence, or cite clean lint/build
 as proof of quality.
 
 Pack-wide rationalizations + red flags (incl. lint-pass-as-quality): see
-[standards/anti-patterns.md](../../devrites-lib/reference/standards/anti-patterns.md).
+[standards/anti-patterns.md](skill://devrites-lib/reference/standards/anti-patterns.md).
 
 ## Phase-specific rationalizations
 

package/pack/generated/omp/skills/rite-polish/reference/backend-polish.md

@@ -22,7 +22,7 @@ schemas. Polishes the **server side** to ship-quality before review, the way UI
       errors; not 200 with `{ error: ... }`).
 - [ ] **Custom error classes** (or equivalent) so callers can distinguish error kinds.
 - [ ] **Fail closed** on auth/permission/transaction errors: deny + roll back; never
-      default to allow or partial commit ([`error-handling.md`](../../devrites-lib/reference/standards/error-handling.md), [`security.md`](../../devrites-lib/reference/standards/security.md)).
+      default to allow or partial commit ([`error-handling.md`](skill://devrites-lib/reference/standards/error-handling.md), [`security.md`](skill://devrites-lib/reference/standards/security.md)).
 - [ ] **Narrow `catch`**: no blanket `catch (e) {}` swallows. If you catch, recover or
       rethrow with context.
 
@@ -52,7 +52,7 @@ schemas. Polishes the **server side** to ship-quality before review, the way UI
       keys).
 - [ ] **Pagination, sorting, filtering** consistent with neighboring endpoints.
 - [ ] **Validation at the boundary**: type/length/format/range on untrusted input;
-      reject what doesn't match (see [`security.md`](../../devrites-lib/reference/standards/security.md) three-tier).
+      reject what doesn't match (see [`security.md`](skill://devrites-lib/reference/standards/security.md) three-tier).
 
 ### Performance (measure first)
 - [ ] Hot-path work measured; obvious wins (cache, batch, hoist) applied; perf claims

package/pack/generated/omp/skills/rite-polish/reference/browser-polish-evidence.md

@@ -6,7 +6,7 @@ in `polish-report.md`).
 
 ## Required when a browser can run
 - Screenshots of the polished UI at the canonical viewport set
-  ([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md) § Responsive — currently
+  ([`quality-standards.md`](skill://devrites-frontend-craft/reference/quality-standards.md) § Responsive — currently
   320 / 768 / 1024 / 1440).
   **Open each screenshot and describe what's visible**: a path is not proof.
 - All key interaction states captured or exercised: hover, focus, active, disabled,

package/pack/generated/omp/skills/rite-polish/reference/code.md

@@ -5,12 +5,12 @@ code polish (Phase 1) and, when backend is touched, backend polish (Phase 2).
 
 ## Rules consulted (read on demand from `.omp/skills/devrites-lib/reference/standards/`)
 
-- [`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md): Phase 1 (simplify, dead code, naming, comments).
-- [`patterns.md`](../../devrites-lib/reference/standards/patterns.md): Phase 1 simplification: avoid over-engineering.
-- [`duplicate-code.md`](../../devrites-lib/reference/standards/duplicate-code.md): Phase 1 dedupe — `check dup` leads, triage verdicts, ignore ledger.
-- [`error-handling.md`](../../devrites-lib/reference/standards/error-handling.md): Phase 2 backend (no silent catches, consistent errors).
-- [`performance.md`](../../devrites-lib/reference/standards/performance.md): Phase 2 backend (N+1s, query bounds).
-- [`documentation.md`](../../devrites-lib/reference/standards/documentation.md): keep touched docs current; record polish-time decisions.
+- [`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md): Phase 1 (simplify, dead code, naming, comments).
+- [`patterns.md`](skill://devrites-lib/reference/standards/patterns.md): Phase 1 simplification: avoid over-engineering.
+- [`duplicate-code.md`](skill://devrites-lib/reference/standards/duplicate-code.md): Phase 1 dedupe — `check dup` leads, triage verdicts, ignore ledger.
+- [`error-handling.md`](skill://devrites-lib/reference/standards/error-handling.md): Phase 2 backend (no silent catches, consistent errors).
+- [`performance.md`](skill://devrites-lib/reference/standards/performance.md): Phase 2 backend (N+1s, query bounds).
+- [`documentation.md`](skill://devrites-lib/reference/standards/documentation.md): keep touched docs current; record polish-time decisions.
 
 ## Operating rules
 
@@ -38,7 +38,7 @@ feature only.
   feature added. Run `devrites-engine check dup <slug>` (mode matching the
   candidate diff: `--base <ref>` when committed, `--worktree`/`--staged` when
   not) for near-duplicate leads and give each reported cluster a verdict per
-  [`duplicate-code.md`](../../devrites-lib/reference/standards/duplicate-code.md)
+  [`duplicate-code.md`](skill://devrites-lib/reference/standards/duplicate-code.md)
   (merge / keep-with-reason / watch).
 - **Chesterton's Fence:** understand *why* something exists before removing it.
   If you can't explain a check, branch, or wrapper, you may not remove it:
@@ -70,7 +70,7 @@ feature only.
   beat a cryptic one.
 - **Done when:** every touched change passes the comprehension test, every anti-slop charter
   item in the touched code is cleared (the AI-tells do-not list: [anti-ai-slop.md](anti-ai-slop.md)
-  Code section, [`coding-style.md`](../../devrites-lib/reference/standards/coding-style.md)) **and** the feature's targeted tests + build re-run green.
+  Code section, [`coding-style.md`](skill://devrites-lib/reference/standards/coding-style.md)) **and** the feature's targeted tests + build re-run green.
   An open charter item or a red check means Phase 1 isn't done.
 
 ## Phase 2: Backend polish *(if BE touched)*

package/pack/generated/omp/skills/rite-polish/reference/design-memory.md

@@ -6,7 +6,7 @@ copy proven, reusable design rules into the project-level `DESIGN.md` for later
 features.
 
 `devrites-ux-shape` §1 and
-[`design-references.md`](../../devrites-frontend-craft/reference/design-references.md) read `DESIGN.md` when present.
+[`design-references.md`](skill://devrites-frontend-craft/reference/design-references.md) read `DESIGN.md` when present.
 This step writes that file from real feature evidence before Review.
 
 ## When it runs
@@ -14,8 +14,8 @@ This step writes that file from real feature evidence before Review.
 - **During Polish, after initial proof and before candidate closure.** Any update
   enters the candidate manifest and is proved and reviewed with the feature.
 - **Opt in and confirm.** A project-wide artifact is outside feature scope
-  ([`core.md`](../../devrites-lib/reference/standards/core.md) rule 7), so never write it silently. Present a ranked option set
-  (see [`afk-hitl.md`](../../devrites-lib/reference/standards/afk-hitl.md), "Option set");
+  ([`core.md`](skill://devrites-lib/reference/standards/core.md) rule 7), so never write it silently. Present a ranked option set
+  (see [`afk-hitl.md`](skill://devrites-lib/reference/standards/afk-hitl.md), "Option set");
   **default is skip**. The user opts to persist.
 - **AFK:** first-time `DESIGN.md` creation is a `validating` gate because it adds a
   persistent project artifact. Propose and queue it; do not create it automatically. An append to an

package/pack/generated/omp/skills/rite-polish/reference/design-system-discovery.md

@@ -1,7 +1,7 @@
 # Design-system discovery
 
 Use the canonical discovery and register rules in
-[`design-references.md`](../../devrites-frontend-craft/reference/design-references.md#discover-these).
+[`design-references.md`](skill://devrites-frontend-craft/reference/design-references.md#discover-these).
 
 Polish-specific decision: preserve the discovered identity by default. Depart only when
 the design brief or the user explicitly targets this surface for redesign. Completion:

package/pack/generated/omp/skills/rite-polish/reference/harden-checklist.md

@@ -56,7 +56,7 @@ might miss.
   feedback; reading order matches visual order.
 - **Reduced motion:** `prefers-reduced-motion` removes non-essential motion
   (no auto-carousel, no spring entrances); auto-moving content over 5 s pauses under any
-  preference ([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md) § Motion).
+  preference ([`quality-standards.md`](skill://devrites-frontend-craft/reference/quality-standards.md) § Motion).
 - **High zoom:** 200% text zoom; layout doesn't break, nothing overflows.
 
 ## 4. Localisation / i18n

package/pack/generated/omp/skills/rite-polish/reference/ledger.md

@@ -8,7 +8,7 @@ Host filesystem I/O; no engine command.
 
 A feature spec may group deltas under capability-tagged H2s (`## ADDED
 Requirements — capability: <c>`, `MODIFIED`, or `REMOVED`); see
-[`spec-grammar.md`](../../devrites-lib/reference/standards/spec-grammar.md).
+[`spec-grammar.md`](skill://devrites-lib/reference/standards/spec-grammar.md).
 
 | Delta | Rule |
 |---|---|
@@ -41,7 +41,7 @@ Run during Polish before Review so ledger edits enter the proved candidate.
 2. **Preview, do not write.** Show exact target paths; every delta with before/after
    header; full requirement order; and changed files. Apply the table to current
    bytes and the preservation rule to MODIFIED and REMOVED. Conflicts stop.
-3. **Check feature grammar.** Apply [`spec-grammar.md`](../../devrites-lib/reference/standards/spec-grammar.md)'s Native grammar re-read
+3. **Check feature grammar.** Apply [`spec-grammar.md`](skill://devrites-lib/reference/standards/spec-grammar.md)'s Native grammar re-read
    checklist to the saved feature spec. Any miss stops. Step 2's native comparison owns delta reconciliation; an
    already-applied empty preview remains a no-op.
 4. **Confirm.** Name exact paths and deltas. A later Seal or Ship approval does
@@ -52,7 +52,7 @@ Run during Polish before Review so ledger edits enter the proved candidate.
    bytes/order, and apply only previewed replacements or empty-file deletion.
    **Failing case:** Polish rewrites feature `spec.md` acceptance criteria "to match
    code." Capability fold is the non-trigger; feature `spec.md` stays sealed
-   ([`core.md`](../../devrites-lib/reference/standards/core.md) rule 4).
+   ([`core.md`](skill://devrites-lib/reference/standards/core.md) rule 4).
 6. **Verify.** Re-read targets; require unrelated blocks byte-identical and the
    same preview empty. Apply the same Native grammar re-read checklist to each
    resulting capability spec.

package/pack/generated/omp/skills/rite-polish/reference/ui.md

@@ -100,7 +100,7 @@ path isn't polish.
 ### Measurable bar (2026)
 
 Polish verifies against the frontend quality standards
-([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md)), measured not assumed:
+([`quality-standards.md`](skill://devrites-frontend-craft/reference/quality-standards.md)), measured not assumed:
 - Core Web Vitals (p75): **LCP ≤ 2.5 s · INP ≤ 200 ms · CLS ≤ 0.1**.
 - WCAG 2.2 AA: semantic HTML, keyboard-operable, visible focus ≥ 3:1, no drag-only.
 - Responsive at the canonical viewport set (quality-standards § Responsive — currently

package/pack/generated/omp/skills/rite-pov/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[candidate/link/question]"
 user-invocable: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/tooling.md"],"workspace":["decisions.md"]} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-pov` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --skill rite-pov` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # /rite-pov: project-grounded external verdict
 
@@ -23,7 +23,7 @@ named outside candidate.
    confirmed absence. No profile cache.
 3. Verify the external claim from current primary documentation, source,
    advisory, or release notes, cited with URL, version or advisory id, and
-   retrieval date ([`tooling.md`](../devrites-lib/reference/standards/tooling.md) citation contract). A CVE verdict also needs the
+   retrieval date ([`tooling.md`](skill://devrites-lib/reference/standards/tooling.md) citation contract). A CVE verdict also needs the
    installed version from the lockfile (`path:line`) checked against the
    advisory's affected range, and a call-site search for the affected API
    (`reachable` / `unreachable` / `unknown`). Known exploitation (a KEV listing)