cfsa-antigravity 3.0.2 → 3.1.0

package/template/.codex/skills/write-fe-spec/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: write-fe-spec
+description: Orchestrate frontend spec production from completed BE shards through classify and write passes with mandatory ambiguity and navigation gates
+parameters:
+  - name: shard
+    type: string
+    required: false
+    description: Optional IA/BE shard override; defaults to lowest-numbered FE not-started shard with BE complete
+---
+
+## Overview
+
+Runs FE specification authoring in two shards: classify → write.
+
+
+## Prerequisites
+
+1. BE spec for target shard is complete
+2. `.memory/pipeline/progress/spec-pipeline.md` exists
+3. FE conventions/index files exist under `.memory/wiki/specs/fe/`
+4. Design system and brand guidance are available for visual surfaces
+
+## Step-by-Step
+
+### Step 0 — Pipeline-state shard selection
+
+1. Read `.memory/pipeline/progress/spec-pipeline.md`.
+2. Find shards where BE is `complete` and FE is `not-started`.
+3. Select lowest-numbered eligible shard unless user explicitly overrides.
+4. If none remain, stop and recommend `/plan-phase`.
+
+### Step 1 — Run classify shard
+
+Call skill: `write-fe-spec-classify`
+
+Expected outputs:
+- FE classification + rationale
+- source mapping (BE + IA + cross-refs)
+- accessibility extraction inventory
+- design requirements from brand + design-system inputs
+- FE spec stub created after approval
+
+### Step 2 — Run write shard
+
+Call skill: `write-fe-spec-write`
+
+Expected outputs:
+- Full FE spec file(s) in `.memory/wiki/specs/fe/`
+- Updated `.memory/wiki/specs/fe/index.md`
+- Updated `.memory/pipeline/progress/spec-pipeline.md` FE status
+- Ambiguity + navigation completeness gate outcomes
+
+## Quality Gate
+
+Do not close workflow unless all pass:
+- component props/interfaces are explicit
+- all interactive behaviors are defined
+- BE field mapping is complete for data-driven UI
+- loading/error/empty states defined for all fetch views
+- WCAG 2.1 AA requirements are concretely specified
+- responsive behavior and touch equivalents are specified
+- IA accessibility requirements are consumed explicitly
+- source mapping traceability is complete
+
+## Completion Checklist
+
+- [ ] target shard selected from pipeline state
+- [ ] classify shard completed and approved
+- [ ] write shard completed and approved
+- [ ] FE index updated
+- [ ] FE pipeline tracker updated
+- [ ] ambiguity gate completed
+- [ ] navigation completeness check completed when final FE shard
+- [ ] next valid command recommendation emitted
+
+## Next Steps
+
+- if FE specs remain: `/write-fe-spec`
+- if FE complete, ambiguity audit is clean, and navigation check passes: `/plan-phase`

package/template/.codex/skills/write-fe-spec-classify/SKILL.md

@@ -0,0 +1,77 @@
+---
+name: write-fe-spec-classify
+description: Classify FE target, validate prerequisites, load frontend skills, and build referenced-material inventory
+parameters:
+  - name: shard
+    type: string
+    required: false
+    description: Optional explicit shard or FE spec target
+---
+
+## Overview
+
+
+## Prerequisites
+
+1. Target shard has BE `complete`
+2. Brand-guidelines and design-system prerequisites are resolved
+
+## Step-by-Step
+
+### Step 0 — Pipeline and prerequisite guards
+
+1. Read pipeline tracker and select FE target shard.
+2. Enforce placeholder guard for required frontend stack placeholders.
+3. Verify brand-guidelines values are fully resolved.
+4. Run design-system prerequisite check and fail fast if incomplete.
+
+### Step 1 — Classification and source mapping
+
+1. Classify target as Feature spec or Cross-cutting spec.
+2. Map required upstream sources:
+   - BE spec(s) when feature-driven
+   - IA source shard
+   - cross-shard references
+   - deep dives with FE implications
+3. Present classification + mapping and require explicit user approval.
+
+### Step 2 — Skill loading bundle
+
+1. Load stack-aware FE framework/design/accessibility/state-management skills.
+2. Load technical-writer, testing-strategist, error-handling skills.
+3. Use resolve-ambiguity skill for unresolved requirements.
+
+### Step 3 — Source ingestion and inventories
+
+Read and extract from:
+1. FE and master indexes
+2. BE source specs (for API/data/error contracts)
+3. IA source shard (flows/access/responsive/a11y/edge cases)
+4. cross-shard references and deep dives
+5. cross-cutting FE specs (`00-*`)
+
+Build:
+- Referenced Material Inventory
+- Accessibility extraction inventory (with gate checks)
+- Conditional rendering matrix (role × feature variants)
+
+### Step 4 — Approval and FE seed stub creation
+
+1. Present classification, source mapping, brand/design-system compliance summary.
+2. Require explicit approval before writing phase.
+3. Create FE spec seed stub using FE template after approval.
+
+## Completion Checklist
+
+- [ ] pipeline gate passed and target selected
+- [ ] placeholders/brand/design-system prerequisites validated
+- [ ] classification and source mapping approved
+- [ ] skill bundle loaded
+- [ ] referenced-material inventory complete
+- [ ] accessibility extraction inventory complete
+- [ ] conditional rendering matrix complete
+- [ ] FE seed stub created
+
+## Next Steps
+
+- Run `write-fe-spec-write`

package/template/.codex/skills/write-fe-spec-write/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: write-fe-spec-write
+description: Author FE spec files, update indexes/tracker, run deepening and ambiguity gates, and enforce navigation completeness before plan-phase handoff
+parameters:
+  - name: spec_file
+    type: string
+    required: false
+    description: Optional explicit FE spec filename
+---
+
+## Overview
+
+
+## Prerequisites
+
+1. FE spec seed stub exists with classification and source inventories
+2. Classify shard has explicit user approval
+
+## Step-by-Step
+
+### Step 1 — Re-run handling and FE spec authoring
+
+1. Detect existing authored content and handle continue vs targeted redo.
+2. Write FE spec sections using FE template and conventions.
+3. Include split-group metadata for split-origin specs when applicable.
+
+### Step 2 — Complexity gate
+
+Apply line-count thresholds:
+- <=600 pass
+- 601-800 warn
+- >800 hard stop and split recommendation
+
+### Step 3 — Index and tracker updates
+
+1. Update `.memory/wiki/specs/fe/index.md` status.
+2. Update FE completion state in `.memory/pipeline/progress/spec-pipeline.md` via protocol.
+
+### Step 4 — Iterative deepening passes
+
+Run multi-pass refinement:
+1. state synchronization and source-of-truth behavior
+2. degraded network behavior and retry semantics
+3. user-flow sequencing and persistence behavior
+4. responsive/touch interaction gap analysis
+5. optional convergence pass (loop guard enforced)
+
+### Step 5 — Cross-reference + ambiguity gates
+
+1. Verify links to BE source, IA source, and related FE specs.
+2. Verify citations for cross-shard material.
+3. Run micro/macro ambiguity checks + two-implementer + devil's-advocate passes.
+4. If final FE spec, run `/audit-ambiguity fe` before plan-phase recommendation.
+
+### Step 6 — Dependency/bootstrap, ledger, and navigation completeness
+
+1. Detect new FE dependencies and run bootstrap + verification when needed.
+2. Update feature ledger FE coverage when ledger exists.
+3. If all FE specs complete, run navigation completeness check and resolve orphan routes.
+
+### Step 7 — Graph refresh, review request, and constrained next-step recommendation
+
+1. Run Protocol 8 fully, including mandatory `memory_compile` graph refresh after tracker verification.
+2. Present:
+- spec link(s)
+- cross-reference verification status
+- ambiguity gate status
+- spec graph refresh confirmation
+- pipeline state and allowed next command
+
+## Completion Checklist
+
+- [ ] FE spec fully authored
+- [ ] complexity gate handled
+- [ ] FE index updated
+- [ ] pipeline tracker updated
+- [ ] deepening passes completed
+- [ ] ambiguity gate completed
+- [ ] dependency bootstrap checks handled
+- [ ] feature ledger FE coverage updated (if present)
+- [ ] navigation completeness check passed when final FE spec
+- [ ] spec graph refreshed via `memory_compile`
+- [ ] review requested with constrained next-step options
+
+## Next Steps
+
+- if FE specs remain: `/write-fe-spec`
+- if FE complete and all gates pass: `/plan-phase`

package/template/.factory/README.md

@@ -9,12 +9,11 @@ This directory contains the CFSA (Constraint-First Specification Architecture) p
 ├── skills/              # All pipeline skills (workflows, utilities, rules, setup)
 ├── skill-library/       # Stack-specific skills provisioned by bootstrap
 ├── instructions/        # Template files with {{PLACEHOLDER}} markers
-├── progress/            # Pipeline progress tracking
-│   └── memory/          # Legacy migration input only
 └── kit-sync.md          # Upstream sync tracking
 
 Project root:
-└── .memory/             # Canonical shared memory root for all runtimes via a shared project-local MCP daemon
+└── .memory/
+    └── pipeline/progress/ # Canonical pipeline progress tracking for all runtimes
 
 Factory should connect as an MCP client to the shared daemon rather than spawning its own memory server.
 

package/template/.factory/instructions/workflow.md

@@ -6,7 +6,7 @@ Before taking any action on a task:
 - Read the agent config file at project root (`AGENTS.md` for Antigravity, `GEMINI.md` for Gemini CLI, or equivalent for your agent)
 - Read relevant `.factory/instructions/` files for the task type
 - Check [Engineering Standards](../../.memory/wiki/specs/ENGINEERING-STANDARDS.md) for quality bar — if this file doesn't exist yet, the pipeline hasn't reached /create-prd; run /ideate then /create-prd first
-- **Session Resumption**: If `.factory/progress/index.md` exists, read `.factory/skills/session-continuity/protocols/01-session-resumption.md` and follow the **Session Resumption Protocol** to load cross-session context and identify the resumption point
+- **Session Resumption**: If `.memory/pipeline/progress/index.md` exists, read `.factory/skills/session-continuity/protocols/01-session-resumption.md` and follow the **Session Resumption Protocol** to load cross-session context and identify the resumption point
 
 ## 2. Check Skills
 - Scan `.factory/skills/` for applicable skills
@@ -38,7 +38,7 @@ Do NOT mark a task complete until all validations pass.
 After completing a workflow or substantial task:
 
 - **Pattern Extraction**: Read `.factory/skills/session-continuity/protocols/04-pattern-extraction.md` and follow the **Pattern Extraction Protocol**. Reflect on what worked, what didn't, and log reusable patterns to `.memory/wiki/patterns.md`. Skip only if the task was trivial (routine, nothing new learned).
-- **Session Close**: Read `.factory/skills/session-continuity/protocols/05-session-close.md` and follow the **Session Close Protocol**. Write a session log to `.factory/progress/sessions/` so the next session can resume cleanly.
+- **Session Close**: Read `.factory/skills/session-continuity/protocols/05-session-close.md` and follow the **Session Close Protocol**. Write a session log to `.memory/pipeline/progress/sessions/` so the next session can resume cleanly.
 - **Unified Memory First**: Treat `.memory/` as the canonical project memory root. When shared memory is needed, prefer the `cfsa-memory` MCP bridge over runtime-local silos so all runtimes see the same memory.
 
 > These steps are **not optional**. They are what differentiate a pipeline that gets
@@ -47,7 +47,7 @@ After completing a workflow or substantial task:
 ## 6. Recommend Next Step (MANDATORY)
 
 Before reporting completion via `notify_user`:
-- Check the pipeline progress state (`.factory/progress/spec-pipeline.md` or equivalent)
+- Check the pipeline progress state (`.memory/pipeline/progress/spec-pipeline.md` or equivalent)
 - Propose the next valid pipeline command to the user
 - If multiple valid next steps exist, list them with brief context
 - Never end a conversation without telling the user what to do next

package/template/.factory/kit-sync.md

@@ -1,6 +1,6 @@
 # Kit Sync State
 
 upstream: https://github.com/RepairYourTech/cfsa-antigravity
-last_synced_commit: 63c31d9113ccb3f828aeb5c8a4902483cbbc2e8a
-last_synced_at: 2026-04-15T09:10:27Z
-kit_version: 3.0.2
+last_synced_commit: 41065b8165f7ea05b56a48f029eabcca52aa3049
+last_synced_at: 2026-05-03T19:45:21Z
+kit_version: 3.1.0

package/template/.factory/skills/completion-checklist/SKILL.md

@@ -33,7 +33,7 @@ A unit of work is only DONE when:
 
 1. **The Code**: Implementation meets the contract and acceptance criteria.
 2. **The Tests**: All tests pass (validation step is green).
-3. **The Tracking**: Progress markdown files in `.factory/progress/` are updated.
+3. **The Tracking**: Progress markdown files in `.memory/pipeline/progress/` are updated.
    - Acceptance criteria marked `[x]`
    - Slice/Task marked `[x]`
    - Phase progress fractions updated (e.g., `3/10` → `4/10`)
@@ -44,10 +44,10 @@ A unit of work is only DONE when:
    - `decisions.md` — Any non-trivial decisions logged per Protocol 06
    - `blockers.md` — Any blockers hit logged with status and impact
    - See rule: `memory-capture` for triggers and format
-6. **The Session Log**: A session close log exists in `.factory/progress/sessions/`.
+6. **The Session Log**: A session close log exists in `.memory/pipeline/progress/sessions/`.
    - Follow `.factory/skills/session-continuity/protocols/05-session-close.md` — write what was accomplished, deferred, and where the next session should start
 7. **The Next Step**: The user is told what comes next in the pipeline.
-   - Read the pipeline progress file (`.factory/progress/spec-pipeline.md` or equivalent)
+   - Read the pipeline progress file (`.memory/pipeline/progress/spec-pipeline.md` or equivalent)
    - Propose the next valid pipeline command based on current state
    - If multiple options exist, present them as a numbered list with brief context
    - If the pipeline stage is complete, say so explicitly

package/template/.factory/skills/parallel-agents/SKILL.md

@@ -162,4 +162,4 @@ Enter parallel mode when the slice's tasks contain surface tags (`BE`, `FE`, `QA
 
 ### Progress Logging
 
-Log each dispatch phase to `.factory/progress/slices/phase-NN-slice-NN.md` under `## Dispatch Log`.
+Log each dispatch phase to `.memory/pipeline/progress/slices/phase-NN-slice-NN.md` under `## Dispatch Log`.

package/template/.factory/skills/plan-phase/SKILL.md

@@ -16,7 +16,7 @@ Runs phase planning in two shards: preflight → write.
 ## Prerequisites
 
 1. IA, BE, and FE spec layers are fully complete
-2. Phase progression state exists in `.factory/progress/`
+2. Phase progression state exists in `.memory/pipeline/progress/`
 3. Architecture phasing section and spec indexes are available
 
 ## Step-by-Step
@@ -44,7 +44,7 @@ Call skill: `plan-phase-write`
 Expected outputs:
 - `.memory/wiki/specs/phases/phase-N.md`
 - `.memory/wiki/specs/phases/phase-N-draft.md`
-- generated progress files in `.factory/progress/`
+- generated progress files in `.memory/pipeline/progress/`
 - verified bootstrap/map completeness for planning prerequisites
 
 ## Completion Checklist

package/template/.factory/skills/plan-phase-preflight/SKILL.md

@@ -14,13 +14,13 @@ parameters:
 ## Prerequisites
 
 1. Approved IA/BE/FE specs exist
-2. Progress state files exist under `.factory/progress/`
+2. Progress state files exist under `.memory/pipeline/progress/`
 
 ## Step-by-Step
 
 ### Step 0 — Phase sequencing gate
 
-1. Read `.factory/progress/index.md` for current phase number.
+1. Read `.memory/pipeline/progress/index.md` for current phase number.
 2. If planning Phase N>1, verify Phase N-1 is complete and has passing `/validate-phase`.
 3. Run architecture map freshness warning gate for N>1 (warning + user resolution).
 

package/template/.factory/skills/session-continuity/SKILL.md

@@ -2,7 +2,7 @@
 name: session-continuity
 description: >
   Cross-session progress tracking, pattern extraction, and session resumption.
-  Gives agents memory across sessions using markdown files in `.factory/progress/`.
+  Gives agents memory across sessions using markdown files in `.memory/pipeline/progress/`.
   Subsumes self-improving-agent — handles both implementation tracking AND
   experiential learning in one skill. Workflows invoke specific protocols by name.
 triggers:
@@ -24,7 +24,7 @@ Without this skill, agents lose all context between sessions. Work restarts from
 scratch, implementations drift without spec accountability, and hard-won patterns
 evaporate. This skill fixes that with five protocols that workflows invoke by name.
 
-Runtime progress remains local to `.factory/progress/`, but canonical cross-runtime memory now lives in `.memory/` and should be read/written through the shared memory files or the `cfsa-memory` MCP bridge.
+Progress state is shared at `.memory/pipeline/progress/`. Cross-runtime memory lives in `.memory/wiki/` and should be read/written through the shared memory files or the `cfsa-memory` MCP bridge.
 
 ### What This Skill Does
 
@@ -52,10 +52,10 @@ This skill defines each protocol with exact steps, file formats, and rules.
 
 ## Directory Structure
 
-All progress state lives in `.factory/progress/`:
+All progress state lives in `.memory/pipeline/progress/`:
 
 ```
-.factory/progress/
+.memory/pipeline/progress/
 ├── index.md                      # Master checklist — phases + overall %
 ├── spec-pipeline.md              # Spec completion tracker (IA/BE/FE per shard)
 ├── phases/
@@ -93,7 +93,7 @@ for complex ones.
 
 ### Steps
 
-1. **Check if `.factory/progress/index.md` exists**
+1. **Check if `.memory/pipeline/progress/index.md` exists**
    - If no: this is a fresh project with no tracked progress. Skip resumption.
    - If yes: continue.
 
@@ -462,7 +462,7 @@ have IA specs, BE specs, and FE specs completed.
 
 1. **Read the IA index** — `.memory/wiki/specs/ia/index.md` — to get the list of shards.
 
-2. **Create `.factory/progress/spec-pipeline.md`**:
+2. **Create `.memory/pipeline/progress/spec-pipeline.md`**:
    ```markdown
    # Spec Pipeline Progress
 

package/template/.factory/skills/session-continuity/protocols/01-session-resumption.md

@@ -10,7 +10,7 @@
 
 ## Steps
 
-1. **Check if `.factory/progress/index.md` exists**
+1. **Check if `.memory/pipeline/progress/index.md` exists**
    - If no: this is a fresh project with no tracked progress. Skip resumption.
    - If yes: continue.
 

package/template/.factory/skills/session-continuity/protocols/02-progress-generation.md

@@ -12,7 +12,7 @@
 
 1. **Read the phase plan** that was just created (the output of `/plan-phase`).
 
-2. **Create or update `.factory/progress/index.md`**:
+2. **Create or update `.memory/pipeline/progress/index.md`**:
    ```markdown
    # Implementation Progress
 
@@ -27,7 +27,7 @@
    | Phase 1: {{NAME}} | not-started | 0/{{N}} | [→](phases/phase-01.md) |
    ```
 
-3. **Create `.factory/progress/phases/phase-NN.md`**:
+3. **Create `.memory/pipeline/progress/phases/phase-NN.md`**:
    ```markdown
    # Phase {{N}}: {{NAME}}
 
@@ -55,7 +55,7 @@
    - `files:` blocks are NOT written during generation — only during claim (Protocol 9)
    - Subtasks under tagged tasks inherit the parent's surface ownership
 
-4. **Create `.factory/progress/slices/phase-NN-slice-NN.md`** for each slice with ≥3 criteria:
+4. **Create `.memory/pipeline/progress/slices/phase-NN-slice-NN.md`** for each slice with ≥3 criteria:
    ```markdown
    # Phase {{P}} / Slice {{S}}: {{NAME}}
 

package/template/.factory/skills/session-continuity/protocols/03-progress-update.md

@@ -10,9 +10,9 @@
 
 ## Steps
 
-1. **Mark tasks and acceptance criteria `[x]`** in the slice's tracking location (use the exact files in the `.factory/progress/` directory, NEVER guess the path):
-   - If slice has its own file: update `.factory/progress/slices/phase-NN-slice-NN.md`
-   - If inline: update `.factory/progress/phases/phase-NN.md`
+1. **Mark tasks and acceptance criteria `[x]`** in the slice's tracking location (use the exact files in the `.memory/pipeline/progress/` directory, NEVER guess the path):
+   - If slice has its own file: update `.memory/pipeline/progress/slices/phase-NN-slice-NN.md`
+   - If inline: update `.memory/pipeline/progress/phases/phase-NN.md`
 
 2. **Release any claimed tasks** — if the completed task had `[!]`:
    - Change status from `[/]` to `[x]`
@@ -42,7 +42,7 @@
    **Progress**: 4/7 slices
    ```
 
-5. **Update `.factory/progress/index.md`** — recalculate overall progress:
+5. **Update `.memory/pipeline/progress/index.md`** — recalculate overall progress:
    ```markdown
    **Overall**: 12/20 slices (60%)
    ```

package/template/.factory/skills/session-continuity/protocols/07-spec-pipeline-generation.md

@@ -13,7 +13,7 @@ have IA specs, BE specs, and FE specs completed.
 
 1. **Read the IA index** — `.memory/wiki/specs/ia/index.md` — to get the list of shards.
 
-2. **Create `.factory/progress/spec-pipeline.md`**:
+2. **Create `.memory/pipeline/progress/spec-pipeline.md`**:
    ```markdown
    # Spec Pipeline Progress
 

package/template/.factory/skills/session-continuity/protocols/08-spec-pipeline-update.md

@@ -14,7 +14,7 @@
 1. **Identify the shard and layer** — which shard just got its spec completed,
    and which layer (IA, BE, or FE)?
 
-2. **Update `.factory/progress/spec-pipeline.md`** — before updating any cell, perform these validation checks:
+2. **Update `.memory/pipeline/progress/spec-pipeline.md`** — before updating any cell, perform these validation checks:
 
    (a) Read the `File` column for the shard from the tracker to get the expected file path.
    (b) Confirm the file exists at that path. If not → **skip the update** and report: `"Cannot mark [shard] [layer] as complete — file not found at [path]"`
@@ -44,7 +44,7 @@
 
 6. **Read-back verification** — immediately after updating the tracker:
 
-   (a) Read `.factory/progress/spec-pipeline.md` back.
+   (a) Read `.memory/pipeline/progress/spec-pipeline.md` back.
    (b) Locate the row for the shard that was just updated.
    (c) Verify the column that was just marked shows `complete` (not `not-started`, not unchanged, not any other value).
    (d) If the cell does NOT show `complete`:

package/template/.factory/skills/session-continuity/protocols/11-parallel-synthesis.md

@@ -4,7 +4,7 @@ Run after all parallel agents have completed and QA-GREEN has passed.
 
 ## Pre-Synthesis Plan
 
-Before beginning any synthesis work, write a `## Synthesis Plan` section to the slice file (`.factory/progress/slices/phase-NN-slice-NN.md`) listing:
+Before beginning any synthesis work, write a `## Synthesis Plan` section to the slice file (`.memory/pipeline/progress/slices/phase-NN-slice-NN.md`) listing:
 - All `// BOUNDARY:` stubs found across agent outputs (file path + stub description)
 - All cross-surface integrations to wire (e.g., "BE auth middleware → FE token refresh handler")
 

package/template/.factory/skills/setup-cfsa/SKILL.md

@@ -121,7 +121,7 @@ Call skill: `setup/setup-verify`
 
 After successful verification, initialize progress tracking:
 
-1. Create master progress file at `.factory/progress/spec-pipeline.md`
+1. Create master progress file at `.memory/pipeline/progress/spec-pipeline.md`
 2. Set initial state: "Ready to start ideation"
 3. Create session log for today
 4. Recommend next step: `/ideate`

package/template/.factory/skills/write-architecture-spec/SKILL.md

@@ -16,14 +16,14 @@ Runs IA specification authoring in two shards: design → deepen.
 ## Prerequisites
 
 1. Decomposition outputs exist (`.memory/wiki/specs/ia/` skeletons + indexes)
-2. `.factory/progress/spec-pipeline.md` exists and includes IA column states
+2. `.memory/pipeline/progress/spec-pipeline.md` exists and includes IA column states
 3. Stack map is resolved for required categories (Databases, Security, Surfaces)
 
 ## Step-by-Step
 
 ### Step 0 — Pipeline-state shard selection
 
-1. Read `.factory/progress/spec-pipeline.md`.
+1. Read `.memory/pipeline/progress/spec-pipeline.md`.
 2. Select lowest-numbered IA shard with `not-started` status unless override is explicitly requested.
 3. If no IA shard remains: stop and direct next step to `/write-be-spec`.
 

package/template/.factory/skills/write-architecture-spec-deepen/SKILL.md

@@ -45,7 +45,7 @@ Ensure event-consumer cross-references are valid and bidirectional.
 ### Step 4 — Update indexes and tracker
 
 1. Mark shard complete in `.memory/wiki/specs/ia/index.md`.
-2. Update `.factory/progress/spec-pipeline.md` IA column via protocol.
+2. Update `.memory/pipeline/progress/spec-pipeline.md` IA column via protocol.
 3. Run conditional bootstrap if shard is the architecture-design stack-lock shard.
 
 ### Step 5 — Ambiguity gates and last-shard branch

package/template/.factory/skills/write-architecture-spec-design/SKILL.md

@@ -20,7 +20,7 @@ parameters:
 
 ### Step 0 — Pipeline and map guards
 
-1. Read `.factory/progress/spec-pipeline.md` and select target shard.
+1. Read `.memory/pipeline/progress/spec-pipeline.md` and select target shard.
 2. Verify required stack map values exist in `.factory/instructions/tech-stack.md`:
    - Databases
    - Security

package/template/.factory/skills/write-be-spec/SKILL.md

@@ -16,14 +16,14 @@ Runs BE specification authoring in two shards: classify → write.
 ## Prerequisites
 
 1. IA shard(s) are complete and marked ✅ in `.memory/wiki/specs/ia/index.md`
-2. `.factory/progress/spec-pipeline.md` exists
+2. `.memory/pipeline/progress/spec-pipeline.md` exists
 3. BE conventions/index files exist under `.memory/wiki/specs/be/`
 
 ## Step-by-Step
 
 ### Step 0 — Pipeline-state shard selection
 
-1. Read `.factory/progress/spec-pipeline.md`.
+1. Read `.memory/pipeline/progress/spec-pipeline.md`.
 2. Find shards where IA is `complete` and BE is `not-started`.
 3. Select lowest-numbered eligible shard unless user explicitly overrides.
 4. If none remain, stop and recommend `/write-fe-spec`.
@@ -45,7 +45,7 @@ Call skill: `write-be-spec-write`
 Expected outputs:
 - Full BE spec file(s) in `.memory/wiki/specs/be/`
 - Updated `.memory/wiki/specs/be/index.md`
-- Updated `.factory/progress/spec-pipeline.md` BE status
+- Updated `.memory/pipeline/progress/spec-pipeline.md` BE status
 - Ambiguity gate results + next allowed command
 
 ## Quality Gate

package/template/.factory/skills/write-be-spec-classify/SKILL.md

@@ -14,7 +14,7 @@ parameters:
 ## Prerequisites
 
 1. Target IA shard is complete
-2. `.memory/wiki/specs/ia/index.md` and `.factory/progress/spec-pipeline.md` are present
+2. `.memory/wiki/specs/ia/index.md` and `.memory/pipeline/progress/spec-pipeline.md` are present
 
 ## Step-by-Step
 

package/template/.factory/skills/write-be-spec-write/SKILL.md

@@ -46,7 +46,7 @@ Apply line-count thresholds:
 ### Step 4 — Index and tracker updates
 
 1. Update `.memory/wiki/specs/be/index.md`.
-2. Update BE completion state in `.factory/progress/spec-pipeline.md`.
+2. Update BE completion state in `.memory/pipeline/progress/spec-pipeline.md`.
 3. Handle structural-reference no-spec rows when classification indicates 0 specs.
 
 ### Step 5 — Iterative deepening passes

package/template/.factory/skills/write-fe-spec/SKILL.md

@@ -16,7 +16,7 @@ Runs FE specification authoring in two shards: classify → write.
 ## Prerequisites
 
 1. BE spec for target shard is complete
-2. `.factory/progress/spec-pipeline.md` exists
+2. `.memory/pipeline/progress/spec-pipeline.md` exists
 3. FE conventions/index files exist under `.memory/wiki/specs/fe/`
 4. Design system and brand guidance are available for visual surfaces
 
@@ -24,7 +24,7 @@ Runs FE specification authoring in two shards: classify → write.
 
 ### Step 0 — Pipeline-state shard selection
 
-1. Read `.factory/progress/spec-pipeline.md`.
+1. Read `.memory/pipeline/progress/spec-pipeline.md`.
 2. Find shards where BE is `complete` and FE is `not-started`.
 3. Select lowest-numbered eligible shard unless user explicitly overrides.
 4. If none remain, stop and recommend `/plan-phase`.
@@ -47,7 +47,7 @@ Call skill: `write-fe-spec-write`
 Expected outputs:
 - Full FE spec file(s) in `.memory/wiki/specs/fe/`
 - Updated `.memory/wiki/specs/fe/index.md`
-- Updated `.factory/progress/spec-pipeline.md` FE status
+- Updated `.memory/pipeline/progress/spec-pipeline.md` FE status
 - Ambiguity + navigation completeness gate outcomes
 
 ## Quality Gate

package/template/.factory/skills/write-fe-spec-write/SKILL.md

@@ -34,7 +34,7 @@ Apply line-count thresholds:
 ### Step 3 — Index and tracker updates
 
 1. Update `.memory/wiki/specs/fe/index.md` status.
-2. Update FE completion state in `.factory/progress/spec-pipeline.md` via protocol.
+2. Update FE completion state in `.memory/pipeline/progress/spec-pipeline.md` via protocol.
 
 ### Step 4 — Iterative deepening passes