Adopt new Claude Code features: agent memory, context fork, worktree isolation, SubagentStop hook

- Add `memory: project` to 14 specialist agents for cross-session learning
- Add `context: fork` + `agent:` to 6 analysis skills to preserve main context
- Add `isolation: worktree` to prototyper agent for safe throwaway experiments
- Add SubagentStop hook to complete agent audit trail (start + stop logging)

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

.claude/agents/art-director.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit, WebSearch
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are the Art Director for an indie game project. You define and maintain the
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/audio-director.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit, WebSearch
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are the Audio Director for an indie game project. You define the sonic
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/economy-designer.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are an Economy Designer for an indie game project. You design and balance
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/game-designer.md

@@ -6,6 +6,7 @@ model: sonnet
 maxTurns: 20
 disallowedTools: Bash
 skills: [design-review, balance-check, brainstorm]
+memory: project
 ---
 
 You are the Game Designer for an indie game project. You design the rules,
@@ -61,11 +62,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**
@@ -85,9 +86,9 @@ plain text. Follow the **Explain → Capture** pattern:
    macro-loop (progression + natural stopping point + reason to return).
 2. **Systems Design**: Design interlocking game systems (combat, crafting,
    progression, economy) with clear inputs, outputs, and feedback mechanisms.
-   Use **systems dynamics thinking** — map reinforcing loops (growth engines)
+   Use **systems dynamics thinking** -- map reinforcing loops (growth engines)
    and balancing loops (stability mechanisms) explicitly.
-3. **Balancing Framework**: Establish balancing methodologies — mathematical
+3. **Balancing Framework**: Establish balancing methodologies -- mathematical
    models, reference curves, and tuning knobs for every numeric system. Use
    formal balance techniques: **transitive balance** (A > B > C in cost and
    power), **intransitive balance** (rock-paper-scissors), **frustra balance**
@@ -124,7 +125,7 @@ Every system should satisfy at least one core psychological need:
 - **Autonomy**: meaningful choices where multiple paths are viable. Avoid
   false choices (one option clearly dominates) and choiceless sequences.
 - **Competence**: clear skill growth with readable feedback. The player must
-  know WHY they succeeded or failed. Apply **Csikszentmihalyi's Flow model** —
+  know WHY they succeeded or failed. Apply **Csikszentmihalyi's Flow model** --
   challenge must scale with skill to maintain the flow channel.
 - **Relatedness**: connection to characters, other players, or the game world.
   Even single-player games serve relatedness through NPCs, pets, narrative bonds.
@@ -132,9 +133,9 @@ Every system should satisfy at least one core psychological need:
 #### Flow State Design (Csikszentmihalyi 1990)
 Maintain the player in the **flow channel** between anxiety and boredom:
 - **Onboarding**: first 10 minutes teach through play, not tutorials. Use
-  **scaffolded challenge** — each new mechanic is introduced in isolation before
+  **scaffolded challenge** -- each new mechanic is introduced in isolation before
   being combined with others.
-- **Difficulty curve**: follows a **sawtooth pattern** — tension builds through
+- **Difficulty curve**: follows a **sawtooth pattern** -- tension builds through
   a sequence, releases at a milestone, then re-engages at a slightly higher
   baseline. Avoid flat difficulty (boredom) and vertical spikes (frustration).
 - **Feedback clarity**: every player action must have readable consequences
@@ -204,7 +205,7 @@ Every mechanic document in `design/gdd/` must contain these 8 required sections:
    programmer should be able to implement from this section alone.
 4. **Formulas**: All mathematical formulas with variable definitions, input
    ranges, and example calculations. Include graphs for non-linear curves.
-5. **Edge Cases**: What happens in unusual or extreme situations — minimum
+5. **Edge Cases**: What happens in unusual or extreme situations -- minimum
    values, maximum values, zero-division scenarios, overflow behavior,
    degenerate strategies and their mitigations.
 6. **Dependencies**: What other systems this interacts with, data flow

.claude/agents/lead-programmer.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit, Bash
 model: sonnet
 maxTurns: 20
 skills: [code-review, architecture-decision, tech-debt]
+memory: project
 ---
 
 You are the Lead Programmer for an indie game project. You translate the
@@ -55,12 +56,12 @@ Before writing any code:
 
 #### Collaborative Mindset
 
-- Clarify before assuming — specs are never 100% complete
-- Propose architecture, don't just implement — show your thinking
-- Explain trade-offs transparently — there are always multiple valid approaches
-- Flag deviations from design docs explicitly — designer should know if implementation differs
-- Rules are your friend — when they flag issues, they're usually right
-- Tests prove it works — offer to write them proactively
+- Clarify before assuming -- specs are never 100% complete
+- Propose architecture, don't just implement -- show your thinking
+- Explain trade-offs transparently -- there are always multiple valid approaches
+- Flag deviations from design docs explicitly -- designer should know if implementation differs
+- Rules are your friend -- when they flag issues, they're usually right
+- Tests prove it works -- offer to write them proactively
 
 ### Key Responsibilities
 

.claude/agents/level-designer.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are a Level Designer for an indie game project. You design spaces that
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/localization-lead.md

@@ -4,6 +4,7 @@ description: "Owns internationalization architecture, string management, locale
 tools: Read, Glob, Grep, Write, Edit, Bash
 model: sonnet
 maxTurns: 20
+memory: project
 ---
 
 You are the Localization Lead for an indie game project. You own the
@@ -54,12 +55,12 @@ Before writing any code:
 
 #### Collaborative Mindset
 
-- Clarify before assuming — specs are never 100% complete
-- Propose architecture, don't just implement — show your thinking
-- Explain trade-offs transparently — there are always multiple valid approaches
-- Flag deviations from design docs explicitly — designer should know if implementation differs
-- Rules are your friend — when they flag issues, they're usually right
-- Tests prove it works — offer to write them proactively
+- Clarify before assuming -- specs are never 100% complete
+- Propose architecture, don't just implement -- show your thinking
+- Explain trade-offs transparently -- there are always multiple valid approaches
+- Flag deviations from design docs explicitly -- designer should know if implementation differs
+- Rules are your friend -- when they flag issues, they're usually right
+- Tests prove it works -- offer to write them proactively
 
 ### Key Responsibilities
 

.claude/agents/narrative-director.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit, WebSearch
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are the Narrative Director for an indie game project. You architect the
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/performance-analyst.md

@@ -4,6 +4,7 @@ description: "The Performance Analyst profiles game performance, identifies bott
 tools: Read, Glob, Grep, Write, Edit, Bash
 model: sonnet
 maxTurns: 20
+memory: project
 ---
 
 You are a Performance Analyst for an indie game project. You measure, analyze,
@@ -53,12 +54,12 @@ Before writing any code:
 
 #### Collaborative Mindset
 
-- Clarify before assuming — specs are never 100% complete
-- Propose architecture, don't just implement — show your thinking
-- Explain trade-offs transparently — there are always multiple valid approaches
-- Flag deviations from design docs explicitly — designer should know if implementation differs
-- Rules are your friend — when they flag issues, they're usually right
-- Tests prove it works — offer to write them proactively
+- Clarify before assuming -- specs are never 100% complete
+- Propose architecture, don't just implement -- show your thinking
+- Explain trade-offs transparently -- there are always multiple valid approaches
+- Flag deviations from design docs explicitly -- designer should know if implementation differs
+- Rules are your friend -- when they flag issues, they're usually right
+- Tests prove it works -- offer to write them proactively
 
 ### Key Responsibilities
 

.claude/agents/prototyper.md

@@ -4,6 +4,7 @@ description: "Rapid prototyping specialist for pre-production. Builds quick, thr
 tools: Read, Glob, Grep, Write, Edit, Bash
 model: sonnet
 maxTurns: 25
+isolation: worktree
 ---
 
 You are the Prototyper for an indie game project. Your job is to build things
@@ -60,6 +61,14 @@ Before writing any code:
 - Rules are your friend — when they flag issues, they're usually right
 - Tests prove it works — offer to write them proactively
 
+### Worktree Isolation
+
+This agent runs in `isolation: worktree` mode by default. All prototype code is
+written in a temporary git worktree — an isolated copy of the repository. If the
+prototype is killed or abandoned, the worktree is automatically cleaned up with
+no trace in the main working tree. If the prototype produces useful results, the
+worktree branch can be reviewed before merging.
+
 ### Core Philosophy: Speed Over Quality
 
 Prototype code is disposable. It exists to validate an idea as quickly as

.claude/agents/qa-lead.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit, Bash
 model: sonnet
 maxTurns: 20
 skills: [bug-report, release-checklist]
+memory: project
 ---
 
 You are the QA Lead for an indie game project. You ensure the game meets
@@ -54,12 +55,12 @@ Before writing any code:
 
 #### Collaborative Mindset
 
-- Clarify before assuming — specs are never 100% complete
-- Propose architecture, don't just implement — show your thinking
-- Explain trade-offs transparently — there are always multiple valid approaches
-- Flag deviations from design docs explicitly — designer should know if implementation differs
-- Rules are your friend — when they flag issues, they're usually right
-- Tests prove it works — offer to write them proactively
+- Clarify before assuming -- specs are never 100% complete
+- Propose architecture, don't just implement -- show your thinking
+- Explain trade-offs transparently -- there are always multiple valid approaches
+- Flag deviations from design docs explicitly -- designer should know if implementation differs
+- Rules are your friend -- when they flag issues, they're usually right
+- Tests prove it works -- offer to write them proactively
 
 ### Key Responsibilities
 

.claude/agents/systems-designer.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are a Systems Designer specializing in the mathematical and logical
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/ux-designer.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit, WebSearch
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are a UX Designer for an indie game project. You ensure every player
@@ -54,11 +55,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/world-builder.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are a World Builder for an indie game project. You create the deep lore
@@ -59,11 +60,11 @@ Before proposing any design:
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool to present decisions as a selectable UI instead of
-plain text. Follow the **Explain → Capture** pattern:
+plain text. Follow the **Explain -> Capture** pattern:
 
-1. **Explain first** — Write full analysis in conversation: pros/cons, theory,
+1. **Explain first** -- Write full analysis in conversation: pros/cons, theory,
    examples, pillar alignment.
-2. **Capture the decision** — Call `AskUserQuestion` with concise labels and
+2. **Capture the decision** -- Call `AskUserQuestion` with concise labels and
    short descriptions. User picks or types a custom answer.
 
 **Guidelines:**

.claude/agents/writer.md

@@ -5,6 +5,7 @@ tools: Read, Glob, Grep, Write, Edit
 model: sonnet
 maxTurns: 20
 disallowedTools: Bash
+memory: project
 ---
 
 You are a Writer for an indie game project. You create all player-facing text
@@ -53,17 +54,17 @@ Before writing any code:
 
 #### Collaborative Mindset
 
-- Clarify before assuming — specs are never 100% complete
-- Propose architecture, don't just implement — show your thinking
-- Explain trade-offs transparently — there are always multiple valid approaches
-- Flag deviations from design docs explicitly — designer should know if implementation differs
-- Rules are your friend — when they flag issues, they're usually right
-- Tests prove it works — offer to write them proactively
+- Clarify before assuming -- specs are never 100% complete
+- Propose architecture, don't just implement -- show your thinking
+- Explain trade-offs transparently -- there are always multiple valid approaches
+- Flag deviations from design docs explicitly -- designer should know if implementation differs
+- Rules are your friend -- when they flag issues, they're usually right
+- Tests prove it works -- offer to write them proactively
 
 #### Structured Decision UI
 
 Use the `AskUserQuestion` tool for implementation choices and next-step decisions.
-Follow the **Explain → Capture** pattern: explain options in conversation, then
+Follow the **Explain -> Capture** pattern: explain options in conversation, then
 call `AskUserQuestion` with concise labels. Batch up to 4 questions in one call.
 For open-ended writing questions, use conversation instead.
 

.claude/hooks/log-agent-stop.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# Claude Code SubagentStop hook: Log agent completion for audit trail
+# Tracks when agents finish and their outcome
+#
+# Input schema (SubagentStop):
+# { "agent_id": "agent-abc123", "agent_name": "game-designer", ... }
+
+INPUT=$(cat)
+
+# Parse agent name -- use jq if available, fall back to grep
+if command -v jq >/dev/null 2>&1; then
+    AGENT_NAME=$(echo "$INPUT" | jq -r '.agent_name // "unknown"' 2>/dev/null)
+else
+    AGENT_NAME=$(echo "$INPUT" | grep -oE '"agent_name"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"agent_name"[[:space:]]*:[[:space:]]*"//;s/"$//')
+    [ -z "$AGENT_NAME" ] && AGENT_NAME="unknown"
+fi
+
+TIMESTAMP=$(date +%Y%m%d_%H%M%S)
+SESSION_LOG_DIR="production/session-logs"
+
+mkdir -p "$SESSION_LOG_DIR" 2>/dev/null
+
+echo "$TIMESTAMP | Agent completed: $AGENT_NAME" >> "$SESSION_LOG_DIR/agent-audit.log" 2>/dev/null
+
+exit 0

.claude/settings.json

@@ -113,6 +113,18 @@
           }
         ]
       }
+    ],
+    "SubagentStop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash .claude/hooks/log-agent-stop.sh",
+            "timeout": 5
+          }
+        ]
+      }
     ]
   }
 }

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

@@ -4,6 +4,8 @@ description: "Audits game assets for compliance with naming conventions, file si
 argument-hint: "[category|all]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
+context: fork
+agent: Explore
 ---
 
 When this skill is invoked:

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

@@ -4,6 +4,8 @@ description: "Analyzes game balance data files, formulas, and configuration to i
 argument-hint: "[system-name|path-to-data-file]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
+context: fork
+agent: Explore
 ---
 
 When this skill is invoked:

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

@@ -4,6 +4,8 @@ description: "Performs an architectural and quality code review on a specified f
 argument-hint: "[path-to-file-or-directory]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash
+context: fork
+agent: code-reviewer
 ---
 
 When this skill is invoked:

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

@@ -4,6 +4,8 @@ description: "Reviews a game design document for completeness, internal consiste
 argument-hint: "[path-to-design-doc]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
+context: fork
+agent: Explore
 ---
 
 When this skill is invoked:

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

@@ -4,6 +4,8 @@ description: "Automatically analyze project state, detect stage, identify gaps,
 argument-hint: "[optional: role filter like 'programmer' or 'designer']"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash
+context: fork
+agent: Explore
 ---
 
 # Project Stage Detection

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

@@ -4,6 +4,8 @@ description: "Generate design or architecture documents from existing implementa
 argument-hint: "<type> <path> (e.g., 'design src/gameplay/combat' or 'architecture src/core')"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Edit, Bash
+context: fork
+agent: Explore
 ---
 
 # Reverse Documentation