Fix skill bugs: session state init, agent field cleanup, /start path, /sprint-plan phases

- Remove invalid `agent: Explore` frontmatter from read-only skills (asset-audit, design-review, project-stage-detect, reverse-document)
- Fix design-system and map-systems to create session-state/active.md if it does not exist before updating
- Fix gate-check to remove reference to non-existent bmad-bmm-check skill
- Expand /start recommended paths into phased roadmap (Concept → Architecture → Production)
- Restructure /sprint-plan into numbered phases with clearer next-steps section

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.claude/skills/asset-audit/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[category|all]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
 context: fork
-agent: Explore
+# Read-only diagnostic skill — no specialist agent delegation needed
 ---
 
 ## Phase 1: Read Standards

.claude/skills/design-review/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[path-to-design-doc]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
 context: fork
-agent: Explore
+# Read-only diagnostic skill — no specialist agent delegation needed
 ---
 
 ## Phase 1: Load Documents

.claude/skills/design-system/SKILL.md

@@ -268,7 +268,7 @@ Use the template structure from `.claude/docs/templates/game-design-document.md`
 
 Ask: "May I create the skeleton file at `design/gdd/[system-name].md`?"
 
-After writing, update `production/session-state/active.md` with:
+After writing, create `production/session-state/active.md` if it does not exist, then update it with:
 - Task: Designing [system-name] GDD
 - Current section: Starting (skeleton created)
 - File: design/gdd/[system-name].md
@@ -602,7 +602,7 @@ Use `AskUserQuestion`:
 
 If yes, invoke the design-review skill on the completed file.
 
-### 5c: Update Systems Index
+### 5d: Update Systems Index
 
 After the GDD is complete (and optionally reviewed):
 

.claude/skills/gate-check/SKILL.md

@@ -144,8 +144,8 @@ The project progresses through these stages:
 - [ ] Architecture document has no unresolved open questions in Foundation or Core layers
 - [ ] All ADRs have Engine Compatibility sections stamped with the engine version
 - [ ] All ADRs have ADR Dependencies sections (even if all fields are "None")
-- [ ] `/bmad-bmm-check-implementation-readiness` has been run or equivalent manual
+- [ ] Manual validation confirms GDDs + architecture + epics are coherent
-      validation confirms GDDs + architecture + epics are coherent
+      (run `/review-all-gdds` and `/architecture-review` if not done recently)
 - [ ] **Core fantasy is delivered** — at least one playtester independently described an experience that matches the Player Fantasy section of the core system GDDs (without being prompted).
 
 **Vertical Slice Validation** (FAIL if any item is NO):

.claude/skills/map-systems/SKILL.md

@@ -202,7 +202,7 @@ Wait for approval. Write the file only after "yes."
 
 ### Step 5c: Update Session State
 
-After writing, update `production/session-state/active.md` with:
+After writing, create `production/session-state/active.md` if it does not exist, then update it with:
 - Task: Systems decomposition
 - Status: Systems index created
 - File: design/gdd/systems-index.md

.claude/skills/project-stage-detect/SKILL.md

@@ -6,7 +6,7 @@ user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash, Write
 context: fork
 model: haiku
-agent: Explore
+# Read-only diagnostic skill — no specialist agent delegation needed
 ---
 
 # Project Stage Detection

.claude/skills/reverse-document/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "<type> <path> (e.g., 'design src/gameplay/combat' or 'architectu
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Edit, Bash
 context: fork
-agent: Explore
+# Read-only diagnostic skill — no specialist agent delegation needed
 ---
 
 # Reverse Documentation

.claude/skills/sprint-plan/SKILL.md

@@ -8,7 +8,7 @@ context: |
   !ls production/sprints/ 2>/dev/null
 ---
 
-When this skill is invoked:
+## Phase 1: Gather Context
 
 1. **Read the current milestone** from `production/milestones/`.
 
@@ -20,9 +20,13 @@ When this skill is invoked:
 
 4. **Check the risk register** at `production/risk-register/`.
 
+---
+
+## Phase 2: Generate Output
+
 For `new`:
 
-5. **Generate a sprint plan** following this format and present it to the user. Ask: "May I write this sprint plan to `production/sprints/sprint-[N].md`?" If yes, write the file, creating the directory if needed. Verdict: **COMPLETE** — sprint plan created. If no: Verdict: **BLOCKED** — user declined write.
+**Generate a sprint plan** following this format and present it to the user. Ask: "May I write this sprint plan to `production/sprints/sprint-[N].md`?" If yes, write the file, creating the directory if needed. Verdict: **COMPLETE** — sprint plan created. If no: Verdict: **BLOCKED** — user declined write.
 
 ```markdown
 # Sprint [N] -- [Start Date] to [End Date]
@@ -70,7 +74,7 @@ For `new`:
 
 For `status`:
 
-5. **Generate a status report**:
+**Generate a status report**:
 
 ```markdown
 # Sprint [N] Status -- [Date]
@@ -101,7 +105,9 @@ For `status`:
 - [Any new risks identified this sprint]
 ```
 
-### Sprint Status File
+---
+
+## Phase 3: Write Sprint Status File
 
 After generating a new sprint plan, also write `production/sprint-status.yaml`.
 This is the machine-readable source of truth for story status — read by
@@ -142,16 +148,27 @@ Initialize each story from the sprint plan's task tables:
 For `update`: read the existing `sprint-status.yaml`, carry over statuses for
 stories that haven't changed, add new stories, remove dropped ones.
 
-### Scope Reminder
+---
+
+## Phase 4: Scope and Risk Check
 
 After presenting the sprint plan, add:
 
 > **Scope check:** If this sprint includes stories added beyond the original epic scope, run `/scope-check [epic]` to detect scope creep before implementation begins.
 
-When reviewing stories during selection (step 3 above), note any stories that appear outside the original epic goals. If any are uncertain, flag them inline: "Are these stories within the original epic scope? If unsure, `/scope-check` can verify."
+When reviewing stories during selection, note any stories that appear outside the original epic goals. If any are uncertain, flag them inline: "Are these stories within the original epic scope? If unsure, `/scope-check` can verify."
-
-### Agent Consultation
 
 For comprehensive sprint planning, consider consulting:
 - `producer` agent for capacity planning, risk assessment, and cross-department coordination
 - `game-designer` agent for feature prioritization and design readiness assessment
+
+---
+
+## Phase 5: Next Steps
+
+After the sprint plan is written, recommend:
+
+- `/sprint-status` — check progress mid-sprint
+- `/scope-check [epic]` — verify no scope creep before implementation begins
+- `/dev-story [story-file]` — begin implementing the first story
+- `/story-readiness [story-file]` — validate a story is ready before starting it

.claude/skills/start/SKILL.md

@@ -61,10 +61,20 @@ The user needs creative exploration before anything else.
 2. Briefly explain what `/brainstorm` does (guided ideation using professional frameworks — MDA, player psychology, verb-first design)
 3. Recommend running `/brainstorm open` as the next step
 4. Show the recommended path:
+   **Concept phase:**
    - `/brainstorm` — discover your game concept
    - `/setup-engine` — configure the engine (brainstorm will recommend one)
-   - `/map-systems` — decompose the concept into systems and plan GDD writing order
+   - `/map-systems` — decompose the concept into systems
-   - `/prototype` — test the core mechanic
+   - `/design-system` — author a GDD for each MVP system
+   - `/review-all-gdds` — cross-system consistency check
+   - `/gate-check` — validate readiness before architecture work
+   **Architecture phase:**
+   - `/architecture-decision` — record key technical decisions (one per system)
+   - `/create-control-manifest` — compile decisions into an actionable rules sheet
+   - `/architecture-review` — validate architecture coverage
+   **Production phase:**
+   - `/create-epics` — map systems to epics
+   - `/create-stories` — break epics into implementable stories
    - `/sprint-plan` — plan the first sprint
 
 #### If B: Vague idea
@@ -73,10 +83,20 @@ The user needs creative exploration before anything else.
 2. Validate the idea as a starting point (don't judge or redirect)
 3. Recommend running `/brainstorm [their hint]` to develop it
 4. Show the recommended path:
+   **Concept phase:**
    - `/brainstorm [hint]` — develop the idea into a full concept
    - `/setup-engine` — configure the engine
    - `/map-systems` — decompose the concept into systems
-   - `/prototype` — test the core mechanic
+   - `/design-system` — author a GDD for each MVP system
+   - `/review-all-gdds` — cross-system consistency check
+   - `/gate-check` — validate readiness before architecture work
+   **Architecture phase:**
+   - `/architecture-decision` — record key technical decisions (one per system)
+   - `/create-control-manifest` — compile decisions into an actionable rules sheet
+   - `/architecture-review` — validate architecture coverage
+   **Production phase:**
+   - `/create-epics` — map systems to epics
+   - `/create-stories` — break epics into implementable stories
    - `/sprint-plan` — plan the first sprint
 
 #### If C: Clear concept
@@ -89,11 +109,20 @@ The user needs creative exploration before anything else.
    - **Formalize first**: Run `/brainstorm` to structure the concept into a proper game concept document
    - **Jump to engine setup**: Go straight to `/setup-engine` and write the GDD manually afterward
 3. Show the recommended path:
+   **Concept phase:**
    - `/brainstorm` or `/setup-engine` (their pick)
    - `/design-review` — validate the concept doc
    - `/map-systems` — decompose the concept into individual systems
-   - `/design-system` — author per-system GDDs
+   - `/design-system` — author a GDD for each MVP system
-   - `/architecture-decision` — make first technical decisions
+   - `/review-all-gdds` — cross-system consistency check
+   - `/gate-check` — validate readiness before architecture work
+   **Architecture phase:**
+   - `/architecture-decision` — record key technical decisions (one per system)
+   - `/create-control-manifest` — compile decisions into an actionable rules sheet
+   - `/architecture-review` — validate architecture coverage
+   **Production phase:**
+   - `/create-epics` — map systems to epics
+   - `/create-stories` — break epics into implementable stories
    - `/sprint-plan` — plan the first sprint
 
 #### If D: Existing work