refactor: restructure specs and plans directories

- Specs (brainstorming output) now go to docs/superpowers/specs/
- Plans (writing-plans output) now go to docs/superpowers/plans/
- User preferences for locations override these defaults
- Update all skill references and test files

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

skills/requesting-code-review/SKILL.md

@@ -58,7 +58,7 @@ HEAD_SHA=$(git rev-parse HEAD)
 
 [Dispatch superpowers:code-reviewer subagent]
   WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
-  PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
+  PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
   BASE_SHA: a7981ec
   HEAD_SHA: 3df7661
   DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types

skills/subagent-driven-development/SKILL.md

@@ -93,7 +93,7 @@ digraph process {
 ```
 You: I'm using Subagent-Driven Development to execute this plan.
 
-[Read plan file once: docs/plans/feature-plan.md]
+[Read plan file once: docs/superpowers/plans/feature-plan.md]
 [Extract all 5 tasks with full text and context]
 [Create TodoWrite with all tasks]
 

skills/writing-plans/SKILL.md

@@ -15,7 +15,8 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 
 **Context:** This should be run in a dedicated worktree (created by brainstorming skill).
 
-**Save plans to:** `docs/plans/YYYY-MM-DD-<feature-name>.md`
+**Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
+- (User preferences for plan location override this default)
 
 ## Bite-Sized Task Granularity
 
@@ -98,7 +99,7 @@ git commit -m "feat: add specific feature"
 
 After saving the plan, offer execution choice:
 
-**"Plan complete and saved to `docs/plans/<filename>.md`. Two execution options:**
+**"Plan complete and saved to `docs/superpowers/plans/<filename>.md`. Two execution options:**
 
 **1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration
 

tests/claude-code/test-helpers.sh

@@ -143,7 +143,7 @@ cleanup_test_project() {
 create_test_plan() {
     local project_dir="$1"
     local plan_name="${2:-test-plan}"
-    local plan_file="$project_dir/docs/plans/$plan_name.md"
+    local plan_file="$project_dir/docs/superpowers/plans/$plan_name.md"
 
     mkdir -p "$(dirname "$plan_file")"
 

tests/claude-code/test-subagent-driven-development-integration.sh

@@ -42,10 +42,10 @@ cat > package.json <<'EOF'
 }
 EOF
 
-mkdir -p src test docs/plans
+mkdir -p src test docs/superpowers/plans
 
 # Create a simple implementation plan
-cat > docs/plans/implementation-plan.md <<'EOF'
+cat > docs/superpowers/plans/implementation-plan.md <<'EOF'
 # Test Implementation Plan
 
 This is a minimal plan to test the subagent-driven-development workflow.
@@ -121,7 +121,7 @@ OUTPUT_FILE="$TEST_PROJECT/claude-output.txt"
 
 # Create prompt file
 cat > "$TEST_PROJECT/prompt.txt" <<'EOF'
-I want you to execute the implementation plan at docs/plans/implementation-plan.md using the subagent-driven-development skill.
+I want you to execute the implementation plan at docs/superpowers/plans/implementation-plan.md using the subagent-driven-development skill.
 
 IMPORTANT: Follow the skill exactly. I will be verifying that you:
 1. Read the plan once at the beginning
@@ -136,7 +136,7 @@ EOF
 # Note: We use a longer timeout since this is integration testing
 # Use --allowed-tools to enable tool usage in headless mode
 # IMPORTANT: Run from superpowers directory so local dev skills are available
-PROMPT="Change to directory $TEST_PROJECT and then execute the implementation plan at docs/plans/implementation-plan.md using the subagent-driven-development skill.
+PROMPT="Change to directory $TEST_PROJECT and then execute the implementation plan at docs/superpowers/plans/implementation-plan.md using the subagent-driven-development skill.
 
 IMPORTANT: Follow the skill exactly. I will be verifying that you:
 1. Read the plan once at the beginning

tests/explicit-skill-requests/prompts/action-oriented.txt

@@ -1,3 +1,3 @@
-The plan is done. docs/plans/auth-system.md has everything.
+The plan is done. docs/superpowers/plans/auth-system.md has everything.
 
 Do subagent-driven development on this - start with Task 1, dispatch a subagent, then we'll review.

tests/explicit-skill-requests/prompts/after-planning-flow.txt

@@ -1,4 +1,4 @@
-Great, the plan is complete. I've saved it to docs/plans/auth-system.md.
+Great, the plan is complete. I've saved it to docs/superpowers/plans/auth-system.md.
 
 Here's a summary of what we designed:
 - Task 1: Add User Model with email/password fields

tests/explicit-skill-requests/prompts/claude-suggested-it.txt

@@ -1,5 +1,5 @@
 [Previous assistant message]:
-Plan complete and saved to docs/plans/auth-system.md.
+Plan complete and saved to docs/superpowers/plans/auth-system.md.
 
 Two execution options:
 1. Subagent-Driven (this session) - I dispatch a fresh subagent per task, review between tasks, fast iteration within this conversation

tests/explicit-skill-requests/prompts/i-know-what-sdd-means.txt

@@ -1,4 +1,4 @@
-I have my implementation plan ready at docs/plans/auth-system.md.
+I have my implementation plan ready at docs/superpowers/plans/auth-system.md.
 
 I want to use subagent-driven-development to execute it. That means:
 - Dispatch a fresh subagent for each task in the plan

tests/explicit-skill-requests/prompts/mid-conversation-execute-plan.txt

@@ -1,3 +1,3 @@
-I have a plan at docs/plans/auth-system.md that's ready to implement.
+I have a plan at docs/superpowers/plans/auth-system.md that's ready to implement.
 
 subagent-driven-development, please

tests/explicit-skill-requests/prompts/skip-formalities.txt

@@ -1,3 +1,3 @@
-Plan is at docs/plans/auth-system.md.
+Plan is at docs/superpowers/plans/auth-system.md.
 
 subagent-driven-development, please. Don't waste time - just read the plan and start dispatching subagents immediately.

tests/explicit-skill-requests/run-claude-describes-sdd.sh

@@ -12,7 +12,7 @@ OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/claude-d
 mkdir -p "$OUTPUT_DIR"
 
 PROJECT_DIR="$OUTPUT_DIR/project"
-mkdir -p "$PROJECT_DIR/docs/plans"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
 
 echo "=== Test: Claude Describes SDD First ==="
 echo "Output dir: $OUTPUT_DIR"
@@ -21,7 +21,7 @@ echo ""
 cd "$PROJECT_DIR"
 
 # Create a plan
-cat > "$PROJECT_DIR/docs/plans/auth-system.md" << 'EOF'
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
 # Auth System Implementation Plan
 
 ## Task 1: Add User Model
@@ -36,7 +36,7 @@ EOF
 
 # Turn 1: Have Claude describe execution options including SDD
 echo ">>> Turn 1: Ask Claude to describe execution options..."
-claude -p "I have a plan at docs/plans/auth-system.md. Tell me about my options for executing it, including what subagent-driven-development means and how it works." \
+claude -p "I have a plan at docs/superpowers/plans/auth-system.md. Tell me about my options for executing it, including what subagent-driven-development means and how it works." \
     --model haiku \
     --plugin-dir "$PLUGIN_DIR" \
     --dangerously-skip-permissions \

tests/explicit-skill-requests/run-extended-multiturn-test.sh

@@ -12,7 +12,7 @@ OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/extended
 mkdir -p "$OUTPUT_DIR"
 
 PROJECT_DIR="$OUTPUT_DIR/project"
-mkdir -p "$PROJECT_DIR/docs/plans"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
 
 echo "=== Extended Multi-Turn Test ==="
 echo "Output dir: $OUTPUT_DIR"

tests/explicit-skill-requests/run-haiku-test.sh

@@ -12,7 +12,7 @@ OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/explicit-skill-requests/haiku"
 mkdir -p "$OUTPUT_DIR"
 
 PROJECT_DIR="$OUTPUT_DIR/project"
-mkdir -p "$PROJECT_DIR/docs/plans"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
 mkdir -p "$PROJECT_DIR/.claude"
 
 echo "=== Haiku Model Test with User CLAUDE.md ==="
@@ -31,7 +31,7 @@ else
 fi
 
 # Create a dummy plan file
-cat > "$PROJECT_DIR/docs/plans/auth-system.md" << 'EOF'
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
 # Auth System Implementation Plan
 
 ## Task 1: Add User Model

tests/explicit-skill-requests/run-multiturn-test.sh

@@ -16,7 +16,7 @@ mkdir -p "$OUTPUT_DIR"
 
 # Create project directory (conversation is cwd-based)
 PROJECT_DIR="$OUTPUT_DIR/project"
-mkdir -p "$PROJECT_DIR/docs/plans"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
 
 echo "=== Multi-Turn Explicit Skill Request Test ==="
 echo "Output dir: $OUTPUT_DIR"
@@ -27,7 +27,7 @@ echo ""
 cd "$PROJECT_DIR"
 
 # Create a dummy plan file
-cat > "$PROJECT_DIR/docs/plans/auth-system.md" << 'EOF'
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
 # Auth System Implementation Plan
 
 ## Task 1: Add User Model
@@ -59,7 +59,7 @@ echo ""
 # Turn 2: Continue with more planning detail
 echo ">>> Turn 2: Continuing planning..."
 TURN2_LOG="$OUTPUT_DIR/turn2.json"
-claude -p "Good analysis. I've already written the plan to docs/plans/auth-system.md. Now I'm ready to implement. What are my options for execution?" \
+claude -p "Good analysis. I've already written the plan to docs/superpowers/plans/auth-system.md. Now I'm ready to implement. What are my options for execution?" \
     --continue \
     --plugin-dir "$PLUGIN_DIR" \
     --dangerously-skip-permissions \

tests/explicit-skill-requests/run-test.sh

@@ -43,10 +43,10 @@ cp "$PROMPT_FILE" "$OUTPUT_DIR/prompt.txt"
 
 # Create a minimal project directory for the test
 PROJECT_DIR="$OUTPUT_DIR/project"
-mkdir -p "$PROJECT_DIR/docs/plans"
+mkdir -p "$PROJECT_DIR/docs/superpowers/plans"
 
 # Create a dummy plan file for mid-conversation tests
-cat > "$PROJECT_DIR/docs/plans/auth-system.md" << 'EOF'
+cat > "$PROJECT_DIR/docs/superpowers/plans/auth-system.md" << 'EOF'
 # Auth System Implementation Plan
 
 ## Task 1: Add User Model

tests/skill-triggering/prompts/executing-plans.txt

@@ -1 +1 @@
-I have a plan document at docs/plans/2024-01-15-auth-system.md that needs to be executed. Please implement it.
+I have a plan document at docs/superpowers/plans/2024-01-15-auth-system.md that needs to be executed. Please implement it.