cfsa-antigravity 2.19.0 → 2.19.2

package/template/.claude/skills/prd-templates/references/engineering-standards-template.md

@@ -0,0 +1,126 @@
+# Engineering Standards Template
+
+Use this template when creating `docs/plans/ENGINEERING-STANDARDS.md`. Fill in concrete values based on tech stack decisions — **no TBDs allowed**.
+
+```markdown
+# [Project Name] — Engineering Standards
+
+> **Architecture**: [link to architecture-design.md]
+> **Date**: YYYY-MM-DD
+> **Status**: Draft | Review | Approved
+
+## Test Coverage
+- Minimum unit test coverage: [e.g., 80%]
+- Integration test requirement: [e.g., every API endpoint]
+- E2E test requirement: [e.g., every critical user flow]
+- Coverage tool: [e.g., vitest coverage-v8]
+
+## Linting & Formatting
+- Linter: [e.g., ESLint with strict config]
+- Formatter: [e.g., Prettier]
+- Type checker: [e.g., TypeScript strict mode]
+- Pre-commit hooks: [yes/no, tool]
+
+## Performance Budgets
+
+> **Baseline**: Budgets target [device tier] on [network condition]. Every threshold must have a named enforcement tool — a threshold without an enforcement tool is incomplete.
+
+### Web Vitals per page type (web/desktop surfaces only)
+
+| Page Type | LCP target | INP target | CLS target | Enforcement Tool |
+|-----------|-----------|-----------|-----------|-----------------|
+| [e.g., Landing] | [e.g., ≤ 2.0 s] | [e.g., ≤ 150 ms] | [e.g., ≤ 0.05] | [e.g., Lighthouse CI] |
+| [e.g., Dashboard] | [e.g., ≤ 2.5 s] | [e.g., ≤ 200 ms] | [e.g., ≤ 0.1] | [e.g., Lighthouse CI] |
+| [e.g., Detail/Form] | [e.g., ≤ 2.0 s] | [e.g., ≤ 100 ms] | [e.g., ≤ 0.05] | [e.g., Lighthouse CI] |
+
+### JS Bundle Size per page type (web/desktop surfaces only)
+
+| Page Type | Initial JS (gzipped) | Total JS (gzipped) | Enforcement Tool |
+|-----------|---------------------|-------------------|-----------------|
+| [e.g., Landing] | [e.g., ≤ 80 KB] | [e.g., ≤ 150 KB] | [e.g., size-limit] |
+| [e.g., Dashboard] | [e.g., ≤ 150 KB] | [e.g., ≤ 300 KB] | [e.g., size-limit] |
+
+### API Response Time per tier
+
+| Tier | Description | p50 | p95 | p99 | Enforcement Tool |
+|------|------------|-----|-----|-----|-----------------|
+| Tier 1 — Cached read | [e.g., Response from cache] | [e.g., ≤ 10 ms] | [e.g., ≤ 30 ms] | [e.g., ≤ 50 ms] | [e.g., k6] |
+| Tier 2 — Uncached read | [e.g., Single-entity DB fetch] | [e.g., ≤ 30 ms] | [e.g., ≤ 80 ms] | [e.g., ≤ 150 ms] | [e.g., k6] |
+| Tier 3 — Write | [e.g., Create, update, delete] | [e.g., ≤ 80 ms] | [e.g., ≤ 200 ms] | [e.g., ≤ 400 ms] | [e.g., k6] |
+| Tier 4 — Background | [e.g., Async jobs, external calls] | [Best-effort] | [e.g., ≤ 1000 ms] | [e.g., ≤ 3000 ms] | [e.g., k6] |
+
+### DB Query Time per tier
+
+| Tier | Description | p50 | p95 | Enforcement Tool |
+|------|------------|-----|-----|-----------------|
+| Tier 1 — Indexed point lookup | [e.g., PK or unique-index fetch] | [e.g., ≤ 5 ms] | [e.g., ≤ 15 ms] | [e.g., pgbench] |
+| Tier 2 — Indexed range scan | [e.g., Range or list on indexed column] | [e.g., ≤ 15 ms] | [e.g., ≤ 50 ms] | [e.g., pgbench] |
+| Tier 3 — Aggregation | [e.g., COUNT, SUM, GROUP BY] | [e.g., ≤ 50 ms] | [e.g., ≤ 150 ms] | [e.g., pgbench] |
+| Tier 4 — Full-text / vector / analytical | [e.g., Search, similarity, reports] | [e.g., ≤ 100 ms] | [e.g., ≤ 300 ms] | [e.g., pgbench] |
+
+### Desktop surfaces (if applicable)
+
+| Metric | Threshold | Enforcement Tool |
+|--------|----------|-----------------|
+| Cold start | [e.g., ≤ 2 s] | [e.g., platform profiler] |
+| Memory (idle) | [e.g., ≤ 200 MB] | [e.g., platform profiler] |
+| Memory (active) | [e.g., ≤ 500 MB] | [e.g., platform profiler] |
+| Installer size | [e.g., ≤ 100 MB] | [e.g., CI size check] |
+
+### Mobile surfaces (if applicable)
+
+| Metric | Threshold | Enforcement Tool |
+|--------|----------|-----------------|
+| Cold launch | [e.g., ≤ 1.5 s] | [e.g., platform profiler] |
+| Warm launch | [e.g., ≤ 0.5 s] | [e.g., platform profiler] |
+| Battery drain (active) | [e.g., ≤ 5 %/hr] | [e.g., platform profiler] |
+| Download size | [e.g., ≤ 50 MB] | [e.g., CI size check] |
+
+### CLI surfaces (if applicable)
+
+| Metric | Threshold | Enforcement Tool |
+|--------|----------|-----------------|
+| Execution time | [e.g., ≤ 500 ms for common operations] | [e.g., hyperfine] |
+| Binary size | [e.g., ≤ 20 MB] | [e.g., CI size check] |
+| Startup latency | [e.g., ≤ 100 ms] | [e.g., hyperfine] |
+
+### CI Enforcement
+
+| Budget Category | Enforcement Tool | Fail Condition | Fail vs. Warn |
+|----------------|-----------------|----------------|---------------|
+| Web Vitals | [e.g., Lighthouse CI] | [e.g., Score below threshold] | [Fail] |
+| Bundle size | [e.g., size-limit] | [e.g., Exceeds per-page-type cap] | [Fail] |
+| API response time | [e.g., k6] | [e.g., p95 exceeds tier target] | [Warn / Fail after baseline] |
+| DB query time | [e.g., pgbench] | [e.g., p95 exceeds tier target] | [Warn / Fail after baseline] |
+| Desktop/mobile | [e.g., platform profiler] | [e.g., Any metric exceeds threshold] | [Warn] |
+
+## Accessibility
+- WCAG level: [e.g., 2.1 AA] (web/mobile)
+- Screen reader testing: [required/optional]
+- Keyboard navigation: [all interactive elements]
+- Platform accessibility APIs: [e.g., UIAccessibility for iOS, AccessibilityNodeInfo for Android]
+
+## Security
+- Dependency audit: [e.g., npm audit on every CI run]
+- Dependency audit enforcement: [e.g., Fail on HIGH/CRITICAL, Warn on MODERATE]
+- Secret scanning: [tool/approach]
+- CSP policy: [strict/relaxed + details] (web surfaces)
+- Code signing: [signing certificate strategy] (desktop/mobile surfaces)
+- Security testing tool: [e.g., OWASP ZAP for web, MobSF for mobile, or none] (surface-specific dynamic security scan)
+
+## Code Quality
+- Max file length: [e.g., 300 lines]
+- Max function length: [e.g., 50 lines]
+- Max cyclomatic complexity: [e.g., 10]
+- Required documentation: [public APIs / all exports / none]
+
+## CI/CD Gates
+- Tests must pass: [yes]
+- Lint must pass: [yes]
+- Type-check must pass: [yes]
+- Build must succeed: [yes]
+- Coverage threshold met: [yes]
+
+## Validation Command
+[The single command that enforces all of the above]
+```

package/template/.claude/skills/prd-templates/references/evolution-layer-guidance.md

@@ -0,0 +1,91 @@
+# Evolution Layer Guidance
+
+Reference for `/evolve-feature-classify` Step 4 and `/evolve-feature-cascade` Step 1 — specifies what to write at each pipeline layer when evolving a feature.
+
+## Entry Point Writing Depth
+
+### Ideation Layer (`docs/plans/ideation/`)
+
+1. **Placement**: Read `ideation-index.md` Structure Map. Identify the domain folder. Create new domain if needed.
+2. **Classification Gate**: Apply Node Classification Gate from `.agent/skills/idea-extraction/SKILL.md` — leaf feature or sub-domain folder.
+3. **Write**: Use `.agent/skills/prd-templates/references/fractal-feature-template.md`. Include:
+   - Feature description (what and why)
+   - Affected personas
+   - Success criteria
+   - Constraints
+   - Role Lens — which personas interact and how
+4. **Update parent index**: Add to parent domain's `*-index.md` children table
+5. **Update CX files**: If cross-domain interactions exist, update parent `*-cx.md` and/or `ideation-cx.md`
+6. **Update `ideation-index.md`**: Add to MoSCoW Summary at appropriate priority
+
+### Architecture Layer (`architecture-design.md`)
+
+- Technical constraint description
+- Affected components
+- Non-functional requirements (performance, scalability, compliance)
+- Integration points
+
+### IA Layer (specific IA shard)
+
+- Domain interactions (new/modified user flows)
+- Contracts (new/modified API contracts)
+- Data models (new entities, fields, relationships)
+- Access control (RBAC implications)
+
+### BE Layer (BE spec)
+
+- New API endpoints
+- Updated schemas
+- Middleware requirements
+- Validation rules
+
+### FE Layer (FE spec)
+
+- New components
+- State management updates
+- New routes
+- Accessibility requirements
+
+### Phase Plan
+
+- New slices or updated slice acceptance criteria
+
+## Cascade Layer Guidance
+
+When cascading through downstream layers in `/evolve-feature-cascade`:
+
+| Layer | What to Add |
+|-------|------------|
+| Architecture | New components, system diagram references, NFRs, integration points |
+| IA | New domain interactions, updated contracts, data model changes, access control updates |
+| BE | New API endpoints, updated schemas, middleware requirements, validation rules |
+| FE | New components, state management updates, new routes, accessibility requirements |
+| Phase plan | New slices or updated slice acceptance criteria |
+
+## Impact Assessment Format
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Implementation Impact
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+In-progress slices affected:              [list or "none"]
+Completed slices that may need revisiting: [list or "none"]
+New slices needed:                        [list or "none"]
+Phase plan update required:               [yes/no]
+
+Recommended action: [specific next step]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+## Completion Summary Format
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Feature Evolution Complete
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Entry point:       [document]
+Layers updated:    [list]
+New content:       [summary]
+Implementation:    [impact summary]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```

package/template/.claude/skills/prd-templates/references/expansion-modes.md

@@ -0,0 +1,27 @@
+# Expansion Mode Options
+
+Present these options after engagement tier selection. All input types see the same options.
+
+| # | Mode | When to Recommend | Description |
+|---|------|-------------------|-------------|
+| 1 | **Full exploration** | 3+ domains | Breadth-before-depth with Deep Think |
+| 2 | **Process as-is** | Thin input where user is confident | Proceed with what's captured |
+| 3 | **Expand vertically** | Domains exist but are shallow | Drill deeper into existing features |
+| 4 | **Expand horizontally** | Domains are deep but coverage gaps exist | Add new domains |
+| 5 | **Cross-cutting concerns** | Domains mapped but interactions unexplored | Map feature interactions |
+| 6 | **Combination** | User has specific priorities | User specifies dimensions and order |
+| 7 | **Audit ambiguity first** | Unclear whether depth or breadth is needed | Inline ambiguity check before deciding |
+
+## Default Recommendations
+
+| Input Type | Default |
+|---|---|
+| Rich document (≥3 domains) | Full exploration |
+| Rich document (<3 domains) | Expand vertically |
+| Thin document | Full exploration |
+| Verbal / one-liner | Full exploration |
+| Re-run (continue) | Audit ambiguity first |
+
+## Recording
+
+Write the selected mode to `ideation-index.md` under `## Expansion Mode` immediately after user selection.

package/template/.claude/skills/prd-templates/references/fe-classification-procedures.md

@@ -0,0 +1,47 @@
+# FE Classification — Accessibility & Conditional Rendering Procedures
+
+Procedures used during `/write-fe-spec-classify` Step 4c to build accessibility inventories and conditional rendering matrices.
+
+---
+
+## Accessibility Extraction Gate
+
+Build an accessibility inventory table for every interactive component or interaction in this feature:
+
+| Component/Interaction | WCAG Req | Keyboard Nav | Screen Reader | IA Source |
+|-----------------------|----------|-------------|--------------|-----------|
+| [component name] | [WCAG level + criterion] | [key bindings + focus order] | [aria-label / role / live region] | [IA shard § section] |
+| [interaction name] | [WCAG level + criterion] | [key bindings + focus order] | [aria-label / role / live region] | [IA shard § section] |
+
+**Thin a11y coverage flag**: If an interactive feature has **< 3 accessibility specifications** in the IA shard (fewer than 3 rows in the inventory table for a feature with interactive elements), flag it:
+
+> ⚠️ **Thin accessibility coverage** for [feature name]: only [N] a11y specs found in IA shard. Options:
+> 1. Resolve now — add missing WCAG requirements to the IA shard before proceeding
+> 2. Accept thin coverage — proceed with what exists and flag as tech debt
+
+**Wait for the user's choice before proceeding.**
+
+**Carry-forward instruction**: The accessibility inventory table becomes inline annotations in the `## Component Inventory` section during `/write-fe-spec-write`. Each component's specification must include its WCAG requirements, keyboard navigation, and screen reader behavior directly — not as a separate accessibility section.
+
+---
+
+## Conditional Rendering Enumeration (Step 4c.5)
+
+Read the IA shard's `## Access Control` section. Build a **role × feature rendering matrix** for every feature-level component or interaction:
+
+| Feature/Component | Free | Paid | Creator | Guardian | Junior | Business | Staff | Admin |
+|-------------------|------|------|---------|----------|--------|----------|-------|-------|
+| [component name] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] | [hidden/locked/read-only/full] |
+
+**Values**: `hidden` (not rendered), `locked` (visible but disabled with upgrade prompt), `read-only` (visible, non-interactive), `full` (full access).
+
+**Variant mapping**: Every non-trivial cell (any value other than `full` for the majority role) becomes a **named variant** in the component's `variants` spec in the FE spec. For example, if `Creator` gets `read-only` access to a component while `Paid` gets `full`, the component spec must include a `readOnlyCreator` variant (or equivalent named variant).
+
+**Unspecified role × feature combinations**: If the IA shard's `## Access Control` does not specify the rendering state for a particular role × feature combination, flag it explicitly:
+
+> ⚠️ **Unspecified role × feature combination**: [component] × [role] is not defined in the IA shard's access control.
+> Options:
+> 1. Define it now — specify the rendering state
+> 2. Apply closest-tier default — inherit from the nearest tier (e.g., Free inherits from the most restrictive, Admin inherits `full`)
+
+**Do not assume.** Every cell must be explicitly defined or explicitly defaulted with user confirmation.

package/template/.claude/skills/prd-templates/references/fe-spec-template.md

@@ -0,0 +1,90 @@
+# FE Spec Template
+
+Use this template when writing FE specs to `docs/plans/fe/[NN-feature-name].md`.
+
+```markdown
+# [Feature] — Frontend Specification
+
+> **BE Source**: [link to BE spec(s), or N/A for cross-cutting]
+> **IA Source**: [link to IA shard, or N/A for cross-cutting]
+> **Status**: Draft | Review | Complete
+
+## Split Group _(include only if this spec resulted from a split)_
+
+> **Split origin**: [IA shard that was split, e.g., `09-messaging`]
+> **Companion specs**: [sibling FE spec files, e.g., `09b-agent-flow-ui.md`]
+> **Shared entities**: [data models shared across companions, e.g., `Message`, `Thread`]
+
+## Source Map
+
+| FE Spec Section | Source | Section/Lines |
+|-----------------|--------|---------------|
+| Component Inventory | [be-spec.md or conventions] | § Response Contracts |
+| Page/Route Definitions | [ia-shard.md or conventions] | § User Flows |
+| Interactions | [ia-shard.md or conventions] | § User Flows + § Edge Cases |
+| Accessibility | [ia-shard.md or conventions] | § Accessibility (lines N–M) |
+| Responsive Behavior | [ia-shard.md or conventions] | § Device Strategy |
+| Data Mapping | [be-spec.md or conventions] | § Request/Response Contracts |
+
+## Design Requirements
+**Direction**: [from brand-guidelines — confirmed direction]
+**Typography**: [font/size/weight per text element]
+**Colors**: [primary/secondary/accent for default, hover, active, disabled, error states]
+**Motion**: [animation/transition behavior, or "none"]
+**Anti-patterns**: [what AI slop looks like for this component and how to avoid it]
+
+## Design System Compliance
+**Page archetype(s)**: [name the archetype(s) from design-system.md]
+**Navigation**: [confirm which nav elements this spec uses from the global component inventory]
+**Loading states**: [confirm skeleton vs. spinner — cite design-system.md rule]
+**Error states**: [confirm inline/toast/full-page/boundary — cite design-system.md rule for each context]
+**Empty states**: [confirm illustration style and copy tone from design-system.md]
+
+## Component Inventory
+[Tree with props interfaces]
+
+## Page/Route Definitions
+[URL patterns, guards, redirects]
+
+## State Management
+[Server state, client state, URL state, loading/error/empty]
+
+## Interaction Specification
+[Click, hover, keyboard, form validation matching {{CONTRACT_LIBRARY}}]
+
+## Responsive Behavior
+[Breakpoints, component behavior per breakpoint]
+
+## Accessibility
+[ARIA roles, keyboard nav, screen reader, WCAG compliance]
+
+## Data Mapping
+[Which BE response fields map to which component props]
+
+## Open Questions
+
+## Changelog
+
+| Date | Change | Workflow | Sections Affected |
+|------|--------|----------|-------------------|
+| [date] | Initial creation | /write-fe-spec | All |
+```
+
+## Quality Gates Checklist
+
+Apply after writing every FE spec:
+
+- [ ] Every component has a props interface
+- [ ] Every interactive element has defined behavior
+- [ ] Every data field maps to a BE response field (if applicable)
+- [ ] Loading, error, and empty states defined for every data-fetching view
+- [ ] Accessibility requirements meet WCAG 2.1 AA
+- [ ] Responsive behavior specified for all breakpoints
+- [ ] IA shard's accessibility section fully consumed (not re-derived from BE spec)
+- [ ] IA shard's user flows reflected in interaction specification
+- [ ] Account-tier conditional rendering rules from IA access model included
+- [ ] Source Map is complete — no FE spec section lacks a traceable source
+- [ ] Design Requirements section filled from brand-guidelines (not placeholders)
+- [ ] Page archetype named and matches design-system.md
+- [ ] All loading/error/empty states use the confirmed design language from design-system.md
+- [ ] No global component re-invented (consuming from global inventory, not re-implementing)

package/template/.claude/skills/prd-templates/references/feature-ledger-protocol.md

@@ -0,0 +1,149 @@
+# Feature Tracking Ledger Protocol
+
+> **Purpose**: Track every ideation feature through the entire pipeline — from birth in ideation to final slice assignment. Catches dropped features that per-stage reconciliation tables miss.
+
+## Ledger Location
+
+`docs/plans/feature-ledger.md`
+
+## Ledger Format
+
+```markdown
+# Feature Tracking Ledger
+
+> Auto-generated by `/ideate-validate`. Updated by each pipeline stage.
+> Each column is populated by the stage that owns it (see Column Ownership below).
+
+| Feature ID | Feature Name | Domain | MoSCoW | IA Shard | IA Status | BE Spec | BE Status | FE Spec | FE Status | Phase | Slice |
+|-----------|-------------|--------|--------|----------|-----------|---------|-----------|---------|-----------|-------|-------|
+```
+
+## Column Ownership
+
+| Column(s) | Populated By | Stage |
+|-----------|-------------|-------|
+| Feature ID, Feature Name, Domain, MoSCoW | `/ideate-validate` Step 11.5 | Discovery |
+| IA Shard, IA Status | `/decompose-architecture-validate` | Design |
+| BE Spec, BE Status | `/write-be-spec-write` | Specification |
+| FE Spec, FE Status | `/write-fe-spec-write` | Specification |
+| Phase, Slice | `/plan-phase-write` Step 2.5 | Planning |
+
+## Status Values
+
+| Status | Meaning |
+|--------|---------|
+| ✅ | Covered — spec exists and includes this feature |
+| ⚠️ deferred | Explicitly deferred with documented reason |
+| ❌ missing | Not covered — no spec addresses this feature |
+| — | Column not yet populated (upstream stage hasn't run) |
+
+## Step 1 — Ledger Creation (`/ideate-validate`)
+
+**When**: After Step 11 (compile vision), before Step 12 (request review).
+
+**Procedure**:
+
+1. Read `ideation-index.md` → Structure Map → get all domain paths
+2. For each domain, read `{domain}-index.md` → Children table
+3. For each leaf-level child (type = `feature`), create one ledger row:
+   - **Feature ID**: `{domain-name}/{feature-file-basename}` (e.g., `inventory/01-categories`)
+   - **Feature Name**: from the Children table Name column
+   - **Domain**: domain name
+   - **MoSCoW**: from `ideation-index.md` MoSCoW Summary (match by feature name), or from the feature's own priority field if available
+4. All other columns → `—` (not yet populated)
+5. Write to `docs/plans/feature-ledger.md`
+
+> **Context management**: Read domain indexes one at a time, extract features, move on. Same pattern as the deep-ideation-loading protocol.
+
+## Step 2 — IA Assignment (`/decompose-architecture-validate`)
+
+**When**: After shard boundaries are approved and shard skeletons exist.
+
+**Procedure**:
+
+1. Read `docs/plans/feature-ledger.md`
+2. For each IA shard skeleton in `docs/plans/ia/`:
+   - Read the shard's `## Sub-features` or features list
+   - For each feature, find the matching row in the ledger (match by Feature ID or Feature Name)
+   - Set **IA Shard** = shard name (e.g., `02-inventory`)
+   - Set **IA Status** = `✅`
+3. **Orphan check**: Any row where IA Shard is still `—` after processing all shards → set IA Status = `❌ missing`
+4. Write updated ledger
+
+**If orphans are found**:
+> ⚠️ **Feature ledger orphan check**: [N] features from ideation have no IA shard assignment:
+> - `{Feature ID}`: {Feature Name}
+>
+> Options:
+> 1. Add to an existing shard
+> 2. Create a new shard
+> 3. Mark as explicitly deferred (with reason)
+
+**STOP** — wait for user decision on each orphan.
+
+## Step 3 — BE Coverage (`/write-be-spec-write`)
+
+**When**: After each BE spec is written.
+
+**Procedure**:
+
+1. Read `docs/plans/feature-ledger.md`
+2. Read the newly written BE spec's endpoint list
+3. For each endpoint, identify which Feature ID(s) it serves (from the IA shard → feature mapping)
+4. For each matched Feature ID, set **BE Spec** = spec file name, **BE Status** = `✅`
+5. Write updated ledger
+
+> **Note**: Not all features produce BE endpoints (e.g., purely client-side UI features). These should have BE Status = `⚠️ deferred` with reason "client-only".
+
+## Step 4 — FE Coverage (`/write-fe-spec-write`)
+
+**When**: After each FE spec is written.
+
+**Procedure**:
+
+1. Read `docs/plans/feature-ledger.md`
+2. Read the newly written FE spec's component list
+3. For each component, identify which Feature ID(s) it serves
+4. For each matched Feature ID, set **FE Spec** = spec file name, **FE Status** = `✅`
+5. Write updated ledger
+
+## Step 5 — Slice Assignment (`/plan-phase-write`)
+
+**When**: After Step 2.5 (spec coverage verification).
+
+**Procedure**:
+
+1. Read `docs/plans/feature-ledger.md`
+2. For each slice, identify which Feature ID(s) it covers (from its spec source map)
+3. For each matched Feature ID, set **Phase** = phase number, **Slice** = slice ID
+4. Write updated ledger
+
+## Verification Gate (`/plan-phase-preflight`)
+
+**When**: During the cross-layer consistency check.
+
+**Procedure**:
+
+1. Read `docs/plans/feature-ledger.md`
+2. Count features by completeness:
+   - **✅ Complete**: All columns through FE Status are ✅ or ⚠️ deferred
+   - **⚠️ Partial**: Some columns filled, some still `—`
+   - **❌ Orphaned**: IA Status or BE Status or FE Status = `❌ missing`
+3. Report:
+
+> **Feature Ledger Verification**:
+> - ✅ Complete: [N] features
+> - ⚠️ Partial: [N] features (columns not yet populated by upstream stages)
+> - ❌ Orphaned: [N] features (dropped between stages)
+
+4. **If any ❌ orphans** → **BLOCKING GATE**: "Feature ledger shows [N] orphaned features. Resolve before planning."
+5. **If any ⚠️ partial** → **WARNING**: "Feature ledger shows [N] features with incomplete coverage. These may be from stages not yet run."
+
+## Anti-Patterns
+
+| ❌ Wrong | ✅ Right |
+|---------|---------|
+| Skipping ledger updates "because it's just bookkeeping" | Every stage updates its columns — it's the only global tracking |
+| Marking orphaned features as ⚠️ deferred without a reason | Orphans are ❌ missing until explicitly deferred with documented reasoning |
+| Regenerating the ledger from scratch at each stage | Updating existing rows — the ledger is cumulative |
+| Ignoring the orphan check at plan-phase-preflight | Blocking on orphans — they represent dropped features |

package/template/.claude/skills/prd-templates/references/folder-seeding-protocol.md

@@ -0,0 +1,77 @@
+# Folder Seeding Protocol
+
+Rules for creating the `docs/plans/ideation/` folder structure during `/ideate-extract`.
+
+## Additive-Only Rule
+
+The `docs/plans/ideation/` directory already exists in the kit with `.gitkeep` and `README.md`. You are ADDING files into this existing directory.
+
+- Do NOT delete, overwrite, or replace the directory itself
+- Do NOT remove any existing files (`.gitkeep`, `README.md`)
+- Create new files alongside what already exists
+
+## Base Structure (All Project Shapes)
+
+After seeding, the folder should contain kit-shipped files PLUS new pipeline files:
+
+```
+docs/plans/ideation/
+├── .gitkeep                ← KIT-SHIPPED — do not touch
+├── README.md               ← KIT-SHIPPED — do not touch
+├── ideation-index.md       ← NEW: super-index (from ideation-index-template)
+├── ideation-cx.md          ← NEW: global cross-cuts (from ideation-crosscut-template)
+└── meta/                   ← NEW: created by this step
+    ├── problem-statement.md
+    ├── personas.md
+    ├── competitive-landscape.md
+    └── constraints.md
+```
+
+For multi-product projects, additionally create `surfaces/` with sub-folders per surface.
+
+## Templates
+
+Read these templates when creating files:
+
+- `.agent/skills/prd-templates/references/ideation-index-template.md` (super-index)
+- `.agent/skills/prd-templates/references/ideation-crosscut-template.md` (global CX)
+- `.agent/skills/prd-templates/references/fractal-node-index-template.md` (node index)
+- `.agent/skills/prd-templates/references/fractal-cx-template.md` (node CX)
+- `.agent/skills/prd-templates/references/fractal-feature-template.md` (feature file)
+
+## Domain Seeding Rules
+
+Domains come from the **confirmed classification table** (Step 1.4.5), NOT from source headings.
+
+### Placement by Structural Classification
+
+| Classification | Placement |
+|---|---|
+| Single-surface | `docs/plans/ideation/{NN}-{slug}/` |
+| Hub-and-spoke | Surface-exclusive in `surfaces/{surface}/{NN}-{slug}/`, shared in hub surface |
+| Peer | Surface-exclusive in `surfaces/{surface}/{NN}-{slug}/`, shared in `shared/{NN}-{slug}/` |
+
+### Node Type → Action
+
+| Gate Result | Action |
+|---|---|
+| **Domain** | Create domain folder with `{slug}-index.md` + `{slug}-cx.md` |
+| **Sub-domain** | Create sub-domain folder nested inside parent domain |
+| **Feature** | Create feature file inside parent domain or sub-domain |
+| **Cross-cut** | Add entries to appropriate CX files (domain-level or global) |
+| **Not-a-product-domain** | Add notes to `meta/constraints.md` for `/create-prd` |
+
+After all nodes are created, update `ideation-index.md` structure map with paths.
+
+## Content Seeding by Input Type
+
+| Input Type | Content Strategy |
+|---|---|
+| **Rich document** | Seed each node with content from source using classification table citations. Run fidelity check: every major concept in source must map to SOMETHING in the output. Add `> Source: path/to/original.md` to index. |
+| **Chat transcript** | Noise filter → extract signal → seed domain folders with structured output |
+| **Thin document** | Create domain folders with depth markers on feature files |
+| **Verbal / one-liner** | Create domain folders with scaffolding. Feature files are `[SURFACE]`. |
+
+## Post-Seeding Verification Gate
+
+After creating all files, verify that `docs/plans/ideation/.gitkeep` and `docs/plans/ideation/README.md` still exist. If EITHER file is missing → **STOP**: "Kit-shipped files were destroyed during seeding. Restore `.gitkeep` and/or `README.md` to `docs/plans/ideation/` before continuing."

package/template/.claude/skills/prd-templates/references/fractal-cx-template.md

@@ -0,0 +1,58 @@
+# {Node Name} — Cross-Cuts
+
+> **Level**: {surface | domain | sub-domain}
+> **Scope**: Connections between children of [{parent}](../{parent}-index.md)
+
+## Cross-Cut Map
+
+| # | Source | Target | Relationship | Roles Affected | Confidence | Evidence |
+|---|--------|--------|--------------|----------------|------------|----------|
+| CX-01 | [child-A](./path) | [child-B](./path) | _what the interaction is_ | Tech, Owner | High | _specific evidence from exploration_ |
+| CX-02 | [child-C](./path) | [{external-node}](../../path) | _cross-level interaction_ | Tech | Medium | _evidence_ |
+
+> **Confidence levels:** High (confirmed with evidence), Medium (strong signal, needs validation), Low (hypothesis)
+>
+> **Cross-level references:** When a cross-cut spans levels (e.g., a feature in one surface touches a domain in another), record it here at the HIGHER level with a link path to the specific lower-level item. The detail of HOW they interact lives in the LOWER-level CX file.
+>
+> **Cross-references:** When referencing a CX entry from another file, use format `{filename}#CX-NN` (e.g., `ai-assistant-cx.md#CX-03`)
+
+---
+
+## Cross-Cut Details
+
+### CX-01: {Source} ↔ {Target}
+
+**Relationship**: _Detailed description of how these two children interact. What data flows between them? What triggers what?_
+
+**Role scoping**:
+- **{Role 1}**: _what this role experiences at this intersection_
+- **{Role 2}**: _what this role experiences_
+- **{Role 3}**: _not affected / no visibility_
+
+**Synthesis questions answered**:
+1. **Shared state conflict**: _Who owns the entity? What's the merge strategy if both sides modify it?_
+2. **Trigger chain**: _Does A trigger B? What happens if B fails — rollback? Compensating action? Is it sync or async?_
+3. **Permission intersection**: _Does a permission in A affect what you can do in B?_
+4. **Notification fan-out**: _Does an event in A notify actors in B?_
+5. **State transition conflict**: _Can A and B race? What's the consistency impact?_
+
+---
+
+_Repeat the Cross-Cut Details section for each CX entry in the map._
+
+---
+
+## Rejected Pairs
+
+| # | Source | Target | Reason for Rejection |
+|---|--------|--------|---------------------|
+| R-01 | _{child-A}_ | _{child-B}_ | _No shared state, no trigger dependency, independent lifecycles_ |
+
+> **Notes for agents:**
+> - This template is used at EVERY folder level in the fractal structure
+> - CX files ONLY connect children at their own level — a surface CX connects domains, a domain CX connects sub-domains, a sub-domain CX connects features
+> - CX entries use sequential `CX-NN` numbering within each file, starting at CX-01
+> - Always include role scoping — every cross-cut affects specific roles, not all roles equally
+> - Rejected pairs are valuable — they show the agent considered the interaction and dismissed it with reasoning
+> - The 5 synthesis questions should be answered for EVERY confirmed cross-cut (CX entries with High confidence)
+> - For Medium/Low confidence entries, the synthesis questions can be deferred to later drilling passes