refactor(commands/agents): replace bash/jq with ccw session commands

Replace legacy bash/jq operations with ccw session commands for better
consistency and maintainability across workflow commands and agents.

Changes:
- commands/memory/docs.md: Use ccw session update/read for session ops
- commands/workflow/review.md: Replace cat/jq with ccw session read
- commands/workflow/tdd-verify.md: Replace find/jq with ccw session read
- agents/conceptual-planning-agent.md: Use ccw session read for metadata
- agents/test-fix-agent.md: Use ccw session read for context package
- skills/command-guide/reference/*: Mirror changes to skill docs
- ccw/src/commands/session.js: Fix EPIPE error when piping to jq/head

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

.claude/skills/command-guide/reference/commands/memory/docs.md

@@ -74,7 +74,7 @@ SlashCommand(command="/workflow:session:start --type docs --new \"{project_name}
 
 ```bash
 # Update workflow-session.json with docs-specific fields
-bash(jq '. + {"target_path":"{target_path}","project_root":"{project_root}","project_name":"{project_name}","mode":"full","tool":"gemini","cli_execute":false}' .workflow/active/{sessionId}/workflow-session.json > tmp.json && mv tmp.json .workflow/active/{sessionId}/workflow-session.json)
+ccw session update {sessionId} --type session --content '{"target_path":"{target_path}","project_root":"{project_root}","project_name":"{project_name}","mode":"full","tool":"gemini","cli_execute":false}'
 ```
 
 ### Phase 2: Analyze Structure
@@ -136,7 +136,8 @@ bash(if [ -d .workflow/docs/\${project_name} ]; then find .workflow/docs/\${proj
 
 ```bash
 # Count existing docs from doc-planning-data.json
-bash(cat .workflow/active/WFS-docs-{timestamp}/.process/doc-planning-data.json | jq '.existing_docs.file_list | length')
+ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq '.existing_docs.file_list | length'
+# Or read entire process file and parse
 ```
 
 **Data Processing**: Use count result, then use **Edit tool** to update `workflow-session.json`:

.claude/skills/command-guide/reference/commands/workflow/execute.md

@@ -115,7 +115,7 @@ List sessions with metadata and prompt user selection:
 ```bash
 bash(for dir in .workflow/active/WFS-*/; do
   session=$(basename "$dir")
-  project=$(jq -r '.project // "Unknown"' "$dir/workflow-session.json" 2>/dev/null)
+  project=$(ccw session read "$session" --type session --raw 2>/dev/null | jq -r '.project // "Unknown"')
   total=$(grep -c "^- \[" "$dir/TODO_LIST.md" 2>/dev/null || echo "0")
   completed=$(grep -c "^- \[x\]" "$dir/TODO_LIST.md" 2>/dev/null || echo "0")
   [ "$total" -gt 0 ] && progress=$((completed * 100 / total)) || progress=0
@@ -152,7 +152,7 @@ Parse user input (supports: number "1", full ID "WFS-auth-system", or partial "a
 
 #### Step 1.3: Load Session Metadata
 ```bash
-bash(cat .workflow/active/${sessionId}/workflow-session.json)
+ccw session read ${sessionId} --type session
 ```
 
 **Output**: Store session metadata in memory

.claude/skills/command-guide/reference/commands/workflow/review.md

@@ -113,13 +113,14 @@ After bash validation, the model takes control to:
 1. **Load Context**: Read completed task summaries and changed files
    ```bash
    # Load implementation summaries
-   cat .workflow/active/${sessionId}/.summaries/IMPL-*.md
+   ccw session read ${sessionId} --type summary --raw
 
    # Load test results (if available)
-   cat .workflow/active/${sessionId}/.summaries/TEST-FIX-*.md 2>/dev/null
+   ccw session read ${sessionId} --type summary --filename "TEST-FIX-*.md" --raw 2>/dev/null
 
-   # Get changed files
-   git log --since="$(cat .workflow/active/${sessionId}/workflow-session.json | jq -r .created_at)" --name-only --pretty=format: | sort -u
+   # Get session created_at for git log filter
+   created_at=$(ccw session read ${sessionId} --type session --raw | jq -r .created_at)
+   git log --since="$created_at" --name-only --pretty=format: | sort -u
    ```
 
 2. **Perform Specialized Review**: Based on `review_type`
@@ -169,11 +170,11 @@ After bash validation, the model takes control to:
    - Verify all requirements and acceptance criteria met:
      ```bash
      # Load task requirements and acceptance criteria
-     find .workflow/active/${sessionId}/.task -name "IMPL-*.json" -exec jq -r '
+     ccw session read ${sessionId} --type task --raw | jq -r '
        "Task: " + .id + "\n" +
        "Requirements: " + (.context.requirements | join(", ")) + "\n" +
        "Acceptance: " + (.context.acceptance | join(", "))
-     ' {} \;
+     '
 
      # Check implementation summaries against requirements
      cd .workflow/active/${sessionId} && gemini -p "

.claude/skills/command-guide/reference/commands/workflow/tdd-verify.md

@@ -77,18 +77,18 @@ find .workflow/active/ -name "WFS-*" -type d | head -1 | sed 's/.*\///'
 
 ```bash
 # Load all task JSONs
-find .workflow/active/{sessionId}/.task/ -name '*.json'
+ccw session read {sessionId} --type task
 
 # Extract task IDs
-find .workflow/active/{sessionId}/.task/ -name '*.json' -exec jq -r '.id' {} \;
+ccw session read {sessionId} --type task --raw | jq -r '.id'
 
-# Check dependencies
-find .workflow/active/{sessionId}/.task/ -name 'IMPL-*.json' -exec jq -r '.context.depends_on[]?' {} \;
-find .workflow/active/{sessionId}/.task/ -name 'REFACTOR-*.json' -exec jq -r '.context.depends_on[]?' {} \;
+# Check dependencies - read tasks and filter for IMPL/REFACTOR
+ccw session read {sessionId} --type task --task-id "IMPL-*" --raw | jq -r '.context.depends_on[]?'
+ccw session read {sessionId} --type task --task-id "REFACTOR-*" --raw | jq -r '.context.depends_on[]?'
 
 # Check meta fields
-find .workflow/active/{sessionId}/.task/ -name '*.json' -exec jq -r '.meta.tdd_phase' {} \;
-find .workflow/active/{sessionId}/.task/ -name '*.json' -exec jq -r '.meta.agent' {} \;
+ccw session read {sessionId} --type task --raw | jq -r '.meta.tdd_phase'
+ccw session read {sessionId} --type task --raw | jq -r '.meta.agent'
 ```
 
 **Validation**: