claude-flow-novice 2.15.11 → 2.16.1

package/claude-assets/agents/cfn-dev-team/developers/backend-developer.md

@@ -20,23 +20,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, read test requirements from environment using the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides centralized error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -58,10 +53,17 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**IMPORTANT:** Use the centralized completion script which handles Redis gracefully:
+Use the centralized test runner skill for parsing and reporting:
 
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
+- Executes test suite with native bash parsing (no external dependencies)
+- Calculates pass rates and coverage metrics
+- Handles Redis gracefully (automatic failure in Task mode)
+- Stores results in Redis (when available)
+
+Usage:
 ```bash
-# Execute tests and capture output
+# Execute tests and capture results
 TEST_OUTPUT=$(npm test 2>&1)
 
 # Parse natively (no external dependencies)
@@ -70,10 +72,11 @@ FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
 TOTAL=$((PASS + FAIL))
 RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
 
-# Report completion (automatically fails gracefully in Task mode)
+# Return results (Main Chat receives automatically in Task Mode)
+echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 ```
 
-**Note:** Redis commands automatically fail gracefully when unavailable (Task mode). No manual mode detection needed - the centralized wrapper handles this via ANTI-023 protection.
+**Note:** Redis commands fail gracefully when unavailable (Task mode). The skill handles this via ANTI-023 protection.
 
 ## Core Responsibilities
 - Design and implement scalable backend services
@@ -161,49 +164,28 @@ DO NOT report subjective confidence scores. Instead:
 
 ## Completion Protocol (Test-Driven)
 
-Complete your work and provide test-based validation:
-
-1. **Execute Tests**: Run all test suites from success criteria
-   ```bash
-   # Parse natively (no external dependencies)
-   PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
-   FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
-   TOTAL=$((PASS + FAIL))
-   RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
-
-   # Return results (Main Chat receives automatically in Task Mode)
-   echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
-   ```
-
-2. **Parse Results**: Extract test counts and calculate pass rate
-
-3. **Coverage Check**: Ensure coverage meets minimum thresholds
-   - Unit tests: ≥95%
-   - Integration tests: ≥90%
-   - Coverage: ≥80%
+Complete your work and provide test-based validation using the test runner skill:
 
-4. **Store in Redis**: Use test-results key (not confidence key)
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-5. **Signal Completion**: Push to completion queue
+1. **Execute Tests**: Run all test suites from success criteria
+2. **Parse Results**: Extract test counts and calculate pass rate using native bash parsing
+3. **Coverage Check**: Ensure coverage meets minimum thresholds (≥80%)
+4. **Store Results**: Use test-results key for reporting (skill handles Redis gracefully)
+5. **Signal Completion**: Push to completion queue (automatic via skill)
 
-**Example Report:**
-```text
-Test Execution Summary:
-- Unit Tests: 45/47 passed (95.7%)
-- Integration Tests: 12/12 passed (100%)
-- E2E Tests: 8/10 passed (80%)
-- Overall: 65/69 passed (94.2%)
-- Coverage: 84.3%
-- Gate Status: PASS
+**Example Implementation:**
+```bash
+source .claude/skills/cfn-test-runner/run-all-tests.sh
 
-Gate Logic (Hybrid Threshold):
-  Pass criteria: At least 2 of 3 test suites meet ≥95% threshold AND overall ≥80%
-  This example: 2 suites (Integration 100%, Unit 95.7%) meet ≥95% ✓
-                Overall 94.2% meets ≥80% ✓
-                Result: PASS
+# Run tests and get results
+TEST_OUTPUT=$(npm test 2>&1)
+PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
+FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
+RATE=$(awk "BEGIN {if ($((PASS + FAIL)) > 0) printf \"%.2f\", $PASS/($PASS+$FAIL); else print \"0.00\"}")
 
-Note: The hybrid 2-of-3 rule applies when multiple test suites are defined in success criteria.
-      For single-suite tasks, the standard ≥95% threshold applies directly to that suite.
+# Return results
+echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 ```
 
 **Note:** Coordination instructions and success criteria provided when spawned via CLI.

package/claude-assets/agents/cfn-dev-team/developers/data/data-engineer.md

@@ -1,6 +1,6 @@
 ---
 name: data-engineer
-description: MUST BE USED for data pipeline design, ETL processes, data warehousing, and data quality. Use PROACTIVELY for data ingestion, transformation, orchestration, data lakes, streaming. ALWAYS delegate for "ETL pipeline", "data warehouse", "data lake", "Apache Airflow", "data quality". Keywords - ETL, data pipeline, Airflow, data warehouse, data lake, streaming, Kafka, Spark, dbt, data quality
+description: MUST BE USED for data pipelines, ETL processes, data warehousing. Use PROACTIVELY for data transformation, batch processing, streaming. Keywords - data, ETL, pipeline, warehouse, processing
 tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: sonnet
 type: specialist
@@ -19,23 +19,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, use the JSON validation skill to safely parse test requirements:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides centralized error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -57,10 +52,14 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
+Use the test runner skill for parsing and reporting results:
 
-**New (Required):**
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
+- Executes test suite with native bash parsing
+- Calculates pass rates and coverage metrics
+- Handles Redis gracefully (automatic failure in Task mode)
+
+Implementation:
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(npm test 2>&1)
@@ -73,7 +72,6 @@ RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0
 
 # Return results (Main Chat receives automatically in Task Mode)
 echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
-
 ```
 
 # Data Engineer Agent

package/claude-assets/agents/cfn-dev-team/developers/database/database-architect.md

@@ -1,6 +1,6 @@
 ---
 name: database-architect
-description: MUST BE USED for database schema design, migration strategies, query optimization, and data modeling. Use PROACTIVELY for relational/NoSQL design, indexing strategies, normalization, data integrity. ALWAYS delegate for "design schema", "database migration", "optimize queries", "data modeling". Keywords - database, schema, SQL, PostgreSQL, MongoDB, migrations, indexing, normalization, query optimization
+description: MUST BE USED for database design, schema optimization, query performance. Use PROACTIVELY for data modeling, indexing, migrations. Keywords - database, schema, SQL, optimization, modeling
 tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: sonnet
 type: specialist
@@ -22,33 +22,18 @@ Frontmatter parser ignores HTML comments, agent runtime reads via grep
 -->
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, read test requirements from environment using the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely (prevents CVSS 8.2 injection)
+- Provides centralized error handling with descriptive messages
+- Extracts test suites with proper fallbacks
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing (prevents CVSS 8.2 injection)
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        echo "   Expected: {\"test_suites\": [{\"name\": \"...\", \"command\": \"...\"}]}" >&2
-        echo "   Received: ${AGENT_SUCCESS_CRITERIA:0:100}..." >&2
-        exit 1
-    fi
-
-    # Parse validated JSON with error handling
-    if ! CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.' 2>&1); then
-        echo "❌ Failed to parse AGENT_SUCCESS_CRITERIA: $CRITERIA" >&2
-        exit 1
-    fi
-
-    # Extract test suites with fallback for missing fields
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[]? // empty' 2>/dev/null || echo "")
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    else
-        echo "⚠️  No test suites found in success criteria (agent may proceed without tests)"
-    fi
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -74,8 +59,14 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-Execute tests and report objective pass/fail metrics:
+Use the centralized test runner skill for executing and reporting results:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
+- Executes test suite with native bash parsing (no external dependencies)
+- Calculates pass rates and coverage metrics
+- Handles Redis gracefully (automatic failure in Task mode)
 
+Usage:
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(npm test 2>&1)
@@ -88,7 +79,6 @@ RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0
 
 # Return results (Main Chat receives automatically in Task Mode)
 echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
-
 ```
 
 # Database Architect Agent
@@ -344,6 +334,7 @@ Validate work with tests instead of confidence scores:
    - Index effectiveness tests
    - Rollback procedure tests
 
+```bash
 # Parse natively (no external dependencies)
 PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")

package/claude-assets/agents/cfn-dev-team/developers/frontend/mobile-dev.md

@@ -33,23 +33,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, use the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -71,10 +66,10 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
+Use the test runner skill:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-**New (Required):**
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(npm test 2>&1)
@@ -213,6 +208,7 @@ Remember: Mobile development requires constant testing on actual devices and con
 Complete your work and provide test-based validation:
 
 1. **Execute Tests**: Run all test suites from success criteria
+```bash
 # Parse natively (no external dependencies)
 PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")

package/claude-assets/agents/cfn-dev-team/developers/frontend/react-frontend-engineer.md

@@ -18,14 +18,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, use the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[]')
-    echo "📋 Success Criteria Loaded:"
-    echo "$TEST_SUITES" | jq -r '.name'
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -47,10 +51,10 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
+Use the test runner skill:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-**New (Required):**
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(npm test 2>&1)
@@ -220,6 +224,7 @@ echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 Complete your work and provide test-based validation:
 
 1. **Execute Tests**: Run all test suites from success criteria
+```bash
 # Parse natively (no external dependencies)
 PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")

package/claude-assets/agents/cfn-dev-team/developers/frontend/typescript-specialist.md

@@ -1,6 +1,6 @@
 ---
 name: typescript-specialist
-description: MUST BE USED for TypeScript development, type system design, and type safety implementation. Use PROACTIVELY for type definitions, generics, utility types, advanced TypeScript patterns, and compile-time validation. Keywords - TypeScript types, generics, interfaces, type safety, utility types, advanced patterns, type guards, conditional types
+description: MUST BE USED for TypeScript development, type safety, advanced typing. Use PROACTIVELY for type definitions, generics. Keywords - typescript, types, type safety, generics
 tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: haiku
 type: specialist
@@ -16,14 +16,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, use the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[]')
-    echo "📋 Success Criteria Loaded:"
-    echo "$TEST_SUITES" | jq -r '.name'
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -45,10 +49,10 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
+Use the test runner skill:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-**New (Required):**
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(npm test 2>&1)
@@ -353,6 +357,7 @@ If post-edit validation fails:
 Complete your work and provide test-based validation:
 
 1. **Execute Tests**: Run all test suites from success criteria
+```bash
 # Parse natively (no external dependencies)
 PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")

package/claude-assets/agents/cfn-dev-team/developers/frontend/ui-designer.md

@@ -1,6 +1,6 @@
 ---
 name: ui-designer
-description: MUST BE USED when designing user interfaces and user experience for web applications. Use PROACTIVELY for responsive design, component libraries, and modern UI/UX patterns. ALWAYS delegate when user asks to "UI design", "user interface", "UX design", "component design". Keywords - UI design, user experience, responsive design, component libraries, interface design
+description: MUST BE USED for UI/UX design, component libraries, design systems. Use PROACTIVELY for interface design, accessibility, responsive layouts. Keywords - UI, UX, design, components, accessibility
 tools: [Read, Write, Edit, Bash, TodoWrite]
 model: haiku
 color: mediumpurple
@@ -20,23 +20,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
+Before starting work, use the JSON validation skill:
 
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides error handling
 
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
+Usage:
+```bash
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -60,19 +55,14 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
+Use the test runner skill:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-**New (Required):**
 ```bash
-# Validate required environment variables
-if [ -z "$TASK_ID" ] || [ -z "$ITERATION" ] || [ -z "$AGENT_ID" ]; then
-    echo "❌ ERROR: Required environment variables not set" >&2
-    echo "   Missing: TASK_ID=${TASK_ID:-<unset>} ITERATION=${ITERATION:-<unset>} AGENT_ID=${AGENT_ID:-<unset>}" >&2
-    exit 1
-fi
+# Execute tests and capture output
+TEST_OUTPUT=$(npm test 2>&1)
 
-# Validate helper exists and is executable
 # Parse natively (no external dependencies)
 PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")

package/claude-assets/agents/cfn-dev-team/developers/graphql-specialist.md

@@ -1,6 +1,6 @@
 ---
 name: graphql-specialist
-description: MUST BE USED for GraphQL schema design, resolver implementation, federation, and performance optimization. Use PROACTIVELY for GraphQL APIs, schema stitching, Apollo Server, federation, subscriptions, DataLoader. ALWAYS delegate for "GraphQL API", "schema design", "resolvers", "federation", "GraphQL subscriptions". Keywords - GraphQL, schema, resolvers, mutations, queries, subscriptions, Apollo, federation, DataLoader, N+1
+description: MUST BE USED for GraphQL API design, schema definition, resolver implementation. Use PROACTIVELY for GraphQL optimization, federation. Keywords - GraphQL, schema, resolvers, API, federation
 tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: sonnet
 type: specialist
@@ -18,23 +18,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, use the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -56,12 +51,10 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
-# Not shown - deprecated pattern
-```
+Use the test runner skill:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-**New (Required):**
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(npm test 2>&1)
@@ -71,6 +64,9 @@ PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
 TOTAL=$((PASS + FAIL))
 RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
+
+# Return results (Main Chat receives automatically in Task Mode)
+echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 ```
 
 # GraphQL Specialist Agent

package/claude-assets/agents/cfn-dev-team/developers/rust-developer.md

@@ -28,23 +28,18 @@ model: glm-4.6
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
+Before starting work, use the JSON validation skill:
+
+**Skill Reference:** `.claude/skills/json-validation/validate-success-criteria.sh`
+- Validates `AGENT_SUCCESS_CRITERIA` JSON safely
+- Prevents injection attacks
+- Provides error handling
+
+Usage:
 ```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
+source .claude/skills/json-validation/validate-success-criteria.sh
+validate_success_criteria || exit 1
+list_test_suites
 ```
 
 ### 2. TDD Protocol (MANDATORY)
@@ -71,12 +66,10 @@ fi
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):**
-```bash
-# Not shown - deprecated pattern
-```
+Use the test runner skill:
+
+**Skill Reference:** `.claude/skills/cfn-test-runner/run-all-tests.sh`
 
-**New (Required):**
 ```bash
 # Execute tests and capture output
 TEST_OUTPUT=$(cargo test 2>&1)
@@ -86,6 +79,9 @@ PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
 FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
 TOTAL=$((PASS + FAIL))
 RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
+
+# Return results (Main Chat receives automatically in Task Mode)
+echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 ```
 
 # Rust Developer Agent

package/claude-assets/agents/cfn-dev-team/documentation/pseudocode.md

@@ -1,6 +1,6 @@
 ---
 name: pseudocode
-description: MUST BE USED when designing algorithms, logic flows, or data structures in SPARC methodology. Use PROACTIVELY for algorithm design, pseudocode creation, complexity analysis, data structure selection, logic flow mapping. Keywords - SPARC, pseudocode, algorithm, logic flow, complexity analysis, Big-O, optimization
+description: MUST BE USED for algorithm design, logic planning, code outline creation. Use PROACTIVELY for problem decomposition, planning. Keywords - pseudocode, algorithm, logic, planning
 tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: haiku
 color: indigo