diff --git a/.claude/agents/conceptual-planning-agent.md b/.claude/agents/conceptual-planning-agent.md
index a49debd9..c5fd1511 100644
--- a/.claude/agents/conceptual-planning-agent.md
+++ b/.claude/agents/conceptual-planning-agent.md
@@ -109,7 +109,7 @@ This agent processes **simplified inline [FLOW_CONTROL]** format from brainstorm
 
 3. **load_session_metadata**
    - Action: Load session metadata
-   - Command: bash(cat .workflow/WFS-{session}/workflow-session.json)
+   - Command: ccw session read WFS-{session} --type session
    - Output: session_metadata
 ```
 
@@ -155,7 +155,7 @@ When called, you receive:
 - **User Context**: Specific requirements, constraints, and expectations from user discussion
 - **Output Location**: Directory path for generated analysis files
 - **Role Hint** (optional): Suggested role or role selection guidance
-- **context-package.json** (CCW Workflow): Artifact paths catalog - extract using `jq -r '.brainstorm_artifacts.role_analyses[].files[].path'`
+- **context-package.json** (CCW Workflow): Artifact paths catalog - use `ccw session read {session} --type context` to get context package
 - **ASSIGNED_ROLE** (optional): Specific role assignment
 - **ANALYSIS_DIMENSIONS** (optional): Role-specific analysis dimensions
 
diff --git a/.claude/agents/test-fix-agent.md b/.claude/agents/test-fix-agent.md
index 2d6e3683..1bb83486 100644
--- a/.claude/agents/test-fix-agent.md
+++ b/.claude/agents/test-fix-agent.md
@@ -83,17 +83,18 @@ When task JSON contains implementation_approach array:
   - L1 (Unit): `*.test.*`, `*.spec.*` in `__tests__/`, `tests/unit/`
   - L2 (Integration): `tests/integration/`, `*.integration.test.*`
   - L3 (E2E): `tests/e2e/`, `*.e2e.test.*`, `cypress/`, `playwright/`
-- **context-package.json** (CCW Workflow): Extract artifact paths using `jq -r '.brainstorm_artifacts.role_analyses[].files[].path'`
+- **context-package.json** (CCW Workflow): Use `ccw session read {session} --type context` to get context package with artifact paths
 - Identify test commands from project configuration
 
 ```bash
 # Detect test framework and multi-layered commands
 if [ -f "package.json" ]; then
-    # Extract layer-specific test commands
-    LINT_CMD=$(cat package.json | jq -r '.scripts.lint // "eslint ."')
-    UNIT_CMD=$(cat package.json | jq -r '.scripts["test:unit"] // .scripts.test')
-    INTEGRATION_CMD=$(cat package.json | jq -r '.scripts["test:integration"] // ""')
-    E2E_CMD=$(cat package.json | jq -r '.scripts["test:e2e"] // ""')
+    # Extract layer-specific test commands using Read tool or jq
+    PKG_JSON=$(cat package.json)
+    LINT_CMD=$(echo "$PKG_JSON" | jq -r '.scripts.lint // "eslint ."')
+    UNIT_CMD=$(echo "$PKG_JSON" | jq -r '.scripts["test:unit"] // .scripts.test')
+    INTEGRATION_CMD=$(echo "$PKG_JSON" | jq -r '.scripts["test:integration"] // ""')
+    E2E_CMD=$(echo "$PKG_JSON" | jq -r '.scripts["test:e2e"] // ""')
 elif [ -f "pytest.ini" ] || [ -f "setup.py" ]; then
     LINT_CMD="ruff check . || flake8 ."
     UNIT_CMD="pytest tests/unit/"
diff --git a/.claude/commands/memory/docs.md b/.claude/commands/memory/docs.md
index a01edb83..81e8d170 100644
--- a/.claude/commands/memory/docs.md
+++ b/.claude/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`:
@@ -190,10 +191,10 @@ Large Projects (single dir >10 docs):
 
 ```bash
 # 1. Get top-level directories from doc-planning-data.json
-bash(cat .workflow/active/WFS-docs-{timestamp}/.process/doc-planning-data.json | jq -r '.top_level_dirs[]')
+ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq -r '.top_level_dirs[]'
 
 # 2. Get mode from workflow-session.json
-bash(cat .workflow/active/WFS-docs-{timestamp}/workflow-session.json | jq -r '.mode // "full"')
+ccw session read WFS-docs-{timestamp} --type session --raw | jq -r '.mode // "full"'
 
 # 3. Check for HTTP API
 bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo "NO_API")
@@ -222,7 +223,7 @@ bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo
 
 **Task ID Calculation**:
 ```bash
-group_count=$(jq '.groups.count' .workflow/active/WFS-docs-{timestamp}/.process/doc-planning-data.json)
+group_count=$(ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq '.groups.count')
 readme_id=$((group_count + 1))   # Next ID after groups
 arch_id=$((group_count + 2))
 api_id=$((group_count + 3))
@@ -285,8 +286,8 @@ api_id=$((group_count + 3))
         "step": "load_precomputed_data",
         "action": "Load Phase 2 analysis and extract group directories",
         "commands": [
-          "bash(cat ${session_dir}/.process/doc-planning-data.json)",
-          "bash(jq '.groups.assignments[] | select(.group_id == \"${group_number}\") | .directories' ${session_dir}/.process/doc-planning-data.json)"
+          "ccw session read ${session_id} --type process --filename doc-planning-data.json",
+          "ccw session read ${session_id} --type process --filename doc-planning-data.json --raw | jq '.groups.assignments[] | select(.group_id == \"${group_number}\") | .directories'"
         ],
         "output_to": "phase2_context",
         "note": "Single JSON file contains all Phase 2 analysis results"
diff --git a/.claude/commands/workflow/review.md b/.claude/commands/workflow/review.md
index 869a2875..e40795a9 100644
--- a/.claude/commands/workflow/review.md
+++ b/.claude/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 "
diff --git a/.claude/commands/workflow/tdd-verify.md b/.claude/commands/workflow/tdd-verify.md
index 61f529ef..587ee3f9 100644
--- a/.claude/commands/workflow/tdd-verify.md
+++ b/.claude/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**:
diff --git a/.claude/skills/command-guide/reference/agents/conceptual-planning-agent.md b/.claude/skills/command-guide/reference/agents/conceptual-planning-agent.md
index a49debd9..c5fd1511 100644
--- a/.claude/skills/command-guide/reference/agents/conceptual-planning-agent.md
+++ b/.claude/skills/command-guide/reference/agents/conceptual-planning-agent.md
@@ -109,7 +109,7 @@ This agent processes **simplified inline [FLOW_CONTROL]** format from brainstorm
 
 3. **load_session_metadata**
    - Action: Load session metadata
-   - Command: bash(cat .workflow/WFS-{session}/workflow-session.json)
+   - Command: ccw session read WFS-{session} --type session
    - Output: session_metadata
 ```
 
@@ -155,7 +155,7 @@ When called, you receive:
 - **User Context**: Specific requirements, constraints, and expectations from user discussion
 - **Output Location**: Directory path for generated analysis files
 - **Role Hint** (optional): Suggested role or role selection guidance
-- **context-package.json** (CCW Workflow): Artifact paths catalog - extract using `jq -r '.brainstorm_artifacts.role_analyses[].files[].path'`
+- **context-package.json** (CCW Workflow): Artifact paths catalog - use `ccw session read {session} --type context` to get context package
 - **ASSIGNED_ROLE** (optional): Specific role assignment
 - **ANALYSIS_DIMENSIONS** (optional): Role-specific analysis dimensions
 
diff --git a/.claude/skills/command-guide/reference/agents/test-fix-agent.md b/.claude/skills/command-guide/reference/agents/test-fix-agent.md
index 2d6e3683..1bb83486 100644
--- a/.claude/skills/command-guide/reference/agents/test-fix-agent.md
+++ b/.claude/skills/command-guide/reference/agents/test-fix-agent.md
@@ -83,17 +83,18 @@ When task JSON contains implementation_approach array:
   - L1 (Unit): `*.test.*`, `*.spec.*` in `__tests__/`, `tests/unit/`
   - L2 (Integration): `tests/integration/`, `*.integration.test.*`
   - L3 (E2E): `tests/e2e/`, `*.e2e.test.*`, `cypress/`, `playwright/`
-- **context-package.json** (CCW Workflow): Extract artifact paths using `jq -r '.brainstorm_artifacts.role_analyses[].files[].path'`
+- **context-package.json** (CCW Workflow): Use `ccw session read {session} --type context` to get context package with artifact paths
 - Identify test commands from project configuration
 
 ```bash
 # Detect test framework and multi-layered commands
 if [ -f "package.json" ]; then
-    # Extract layer-specific test commands
-    LINT_CMD=$(cat package.json | jq -r '.scripts.lint // "eslint ."')
-    UNIT_CMD=$(cat package.json | jq -r '.scripts["test:unit"] // .scripts.test')
-    INTEGRATION_CMD=$(cat package.json | jq -r '.scripts["test:integration"] // ""')
-    E2E_CMD=$(cat package.json | jq -r '.scripts["test:e2e"] // ""')
+    # Extract layer-specific test commands using Read tool or jq
+    PKG_JSON=$(cat package.json)
+    LINT_CMD=$(echo "$PKG_JSON" | jq -r '.scripts.lint // "eslint ."')
+    UNIT_CMD=$(echo "$PKG_JSON" | jq -r '.scripts["test:unit"] // .scripts.test')
+    INTEGRATION_CMD=$(echo "$PKG_JSON" | jq -r '.scripts["test:integration"] // ""')
+    E2E_CMD=$(echo "$PKG_JSON" | jq -r '.scripts["test:e2e"] // ""')
 elif [ -f "pytest.ini" ] || [ -f "setup.py" ]; then
     LINT_CMD="ruff check . || flake8 ."
     UNIT_CMD="pytest tests/unit/"
diff --git a/.claude/skills/command-guide/reference/commands/memory/docs.md b/.claude/skills/command-guide/reference/commands/memory/docs.md
index a01edb83..510065d3 100644
--- a/.claude/skills/command-guide/reference/commands/memory/docs.md
+++ b/.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`:
diff --git a/.claude/skills/command-guide/reference/commands/workflow/execute.md b/.claude/skills/command-guide/reference/commands/workflow/execute.md
index 6844876a..669622a9 100644
--- a/.claude/skills/command-guide/reference/commands/workflow/execute.md
+++ b/.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
diff --git a/.claude/skills/command-guide/reference/commands/workflow/review.md b/.claude/skills/command-guide/reference/commands/workflow/review.md
index 869a2875..e40795a9 100644
--- a/.claude/skills/command-guide/reference/commands/workflow/review.md
+++ b/.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 "
diff --git a/.claude/skills/command-guide/reference/commands/workflow/tdd-verify.md b/.claude/skills/command-guide/reference/commands/workflow/tdd-verify.md
index 61f529ef..587ee3f9 100644
--- a/.claude/skills/command-guide/reference/commands/workflow/tdd-verify.md
+++ b/.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**:
diff --git a/ccw/src/commands/session.js b/ccw/src/commands/session.js
index fca52a95..501652e5 100644
--- a/ccw/src/commands/session.js
+++ b/ccw/src/commands/session.js
@@ -7,6 +7,14 @@ import chalk from 'chalk';
 import http from 'http';
 import { executeTool } from '../tools/index.js';
 
+// Handle EPIPE errors gracefully (occurs when piping to head/jq that closes early)
+process.stdout.on('error', (err) => {
+  if (err.code === 'EPIPE') {
+    process.exit(0);
+  }
+  throw err;
+});
+
 /**
  * Notify dashboard of granular events (fire and forget)
  * @param {Object} data - Event data