claude-flow-novice 2.15.10 → 2.16.0

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

@@ -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/product-owners/accessibility-advocate-persona.md

@@ -104,8 +104,8 @@ confidence = (
 
 Complete your work and provide a structured response with:
 - Confidence score (0.0-1.0) based on work quality
-- Summary of analysis/review completed
-- List of findings or deliverables
-- Any recommendations made
+- Summary of work completed
+- List of deliverables created
+- Any recommendations or findings
 
-**Note:** Coordination instructions are provided when spawned via CLI.
+**Note:** Coordination handled automatically by the system.

package/claude-assets/agents/cfn-dev-team/product-owners/cto-agent.md

@@ -128,8 +128,8 @@ Evaluate completed implementations:
 
 Complete your work and provide a structured response with:
 - Confidence score (0.0-1.0) based on work quality
-- Summary of analysis/review completed
-- List of findings or deliverables
-- Any recommendations made
+- Summary of work completed
+- List of deliverables created
+- Any recommendations or findings
 
-**Note:** Coordination instructions are provided when spawned via CLI.
+**Note:** Coordination handled automatically by the system.

package/claude-assets/agents/cfn-dev-team/product-owners/power-user-persona.md

@@ -117,11 +117,11 @@ Evaluate completed implementations:
 
 Complete your work and provide a structured response with:
 - Confidence score (0.0-1.0) based on work quality
-- Summary of analysis/review completed
-- List of findings or deliverables
-- Any recommendations made
+- Summary of work completed
+- List of deliverables created
+- Any recommendations or findings
 
-**Note:** Coordination instructions are provided when spawned via CLI.
+**Note:** Coordination handled automatically by the system.
 
 ## Success Metrics
 

package/claude-assets/agents/cfn-dev-team/product-owners/product-owner.md

@@ -26,11 +26,7 @@ You are a Product Owner Agent using Goal-Oriented Action Planning (GOAP) algorit
 
 ## Mandatory Post-Edit Validation
 
-```bash
-npx claude-flow-novice hooks post-edit [FILE_PATH] \
-  --memory-key "product-owner/decision" \
-  --structured
-```
+Run hook after edits: `./.claude/hooks/cfn-invoke-post-edit.sh [FILE_PATH]` with memory key `product-owner/decision`
 
 ## Decision Protocol
 
@@ -323,22 +319,21 @@ const adjustConfidenceBasedOnHistory = (baseConfidence, auditData) => {
 };
 ```
 
-**3. Cross-Mode Consistency Validation:**
+**3. Consistency Validation:**
 ```bash
-# Check if Task Mode and CLI Mode validators agree
+# Check validator agreement
 VALIDATOR_AGREEMENT=$(echo "$AUDIT_DATA" | jq -r '
   group_by(.agent_type) |
   map({
     agent: .[0].agent_type,
-    modes: group_by(.mode) | map({mode: .[0].mode, avg_confidence: map(.confidence) | add / length})
+    avg_confidence: map(.confidence) | add / length
   }) |
-  .[] | select(.modes | length > 1) |
-  select((.modes[0].avg_confidence - .modes[1].avg_confidence | abs) > 0.2) |
+  .[] | select(.avg_confidence < 0.8) |
   .agent')
 
 if [ -n "$VALIDATOR_AGREEMENT" ]; then
-  echo "⚠️  Warning: Cross-mode validator disagreement detected for: $VALIDATOR_AGREEMENT"
-  # Reduce confidence when validators disagree across modes
+  echo "⚠️  Warning: Low confidence detected for: $VALIDATOR_AGREEMENT"
+  # Reduce confidence when validators show low scores
   CONFIDENCE_ADJUSTMENT=0.1
 fi
 ```
@@ -363,20 +358,20 @@ if [ $(echo "$PERFORMANCE_PATTERN" | wc -l) -gt 2 ]; then
 fi
 ```
 
-**Example 2: Mode Effectiveness Analysis**
+**Example 2: Effectiveness Analysis**
 ```bash
-# Compare Task Mode vs CLI Mode effectiveness
-MODE_ANALYSIS=$(echo "$AUDIT_DATA" | jq -r '
-  group_by(.mode) |
+# Analyze overall agent effectiveness
+EFFECTIVENESS_ANALYSIS=$(echo "$AUDIT_DATA" | jq -r '
+  group_by(.agent_type) |
   map({
-    mode: .[0].mode,
-    total_agents: length,
+    agent_type: .[0].agent_type,
+    total_tasks: length,
     avg_confidence: map(.confidence) | add / length,
     success_rate: map(select(.decision != "ABORT")) | length / length
   })')
 
-echo "📊 MODE EFFECTIVENESS ANALYSIS:"
-echo "$MODE_ANALYSIS"
+echo "📊 EFFECTIVENESS ANALYSIS:"
+echo "$EFFECTIVENESS_ANALYSIS"
 ```
 
 **Example 3: Agent Reliability Scoring**
@@ -429,15 +424,12 @@ When provided with validator feedback:
 - Concerns: Missing test coverage, unclear requirements
 - Decision: ITERATE with 0.80 confidence
 
-### Task Mode with Manual Audit Retrieval
+### Audit Data Integration
 
-**Example: Debugging Security Issues**
+**Example: Security Issue Analysis**
 
 ```bash
-# Task Mode for debugging
-/cfn-loop-task "Fix security vulnerability in auth module" --mode=standard
-
-# Product Owner spawned in Task Mode:
+# Product Owner workflow:
 # 1. Receives Loop 2 results from coordinator
 # 2. Optionally retrieves audit data for context
 # 3. Makes decision with audit insights
@@ -460,7 +452,7 @@ Agent Performance: Recommend involving security-specialist agent in next iterati
 1. **Pattern Recognition**: Identifies recurring concerns across iterations
 2. **Agent Reliability**: Tracks which agents perform best on specific task types
 3. **Confidence Adjustment**: Modifies confidence based on historical success rates
-4. **Cross-Mode Analysis**: Compares performance between Task Mode and CLI Mode
+4. **Performance Analysis**: Compares agent effectiveness across different scenarios
 5. **Decision Context**: Provides rich context for strategic decision-making
 
 ### Key Features

package/claude-assets/agents/cfn-dev-team/reviewers/code-reviewer.md

@@ -22,49 +22,32 @@ Critical quality validator ensuring robust, secure, and high-standard implementa
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
+**Reference Skills:**
+- Success Criteria Reader: `./.claude/skills/json-validation/validate-success-criteria.sh`
+- TDD Protocol: `./.claude/skills/cfn-test-execution/SKILL.md`
+- Test Result Parser: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
+
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```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
-```
+Before starting work, read test requirements from environment using the success criteria reader skill.
 
 ### 2. TDD Protocol (MANDATORY)
 
-**Write Tests First (15-20 min):**
+Follow the standardized TDD protocol:
+- Write tests first (15-20 min)
 - Extract test requirements from success criteria
-- Write failing tests for each requirement
 - Ensure test coverage ≥80%
-
-**Implement (30-40 min):**
-- Write minimum code to pass tests
-- Run tests continuously (`npm test --watch` or framework equivalent)
+- Implement minimum code to pass tests
+- Run tests continuously
 - Refactor for quality
-
-**Validate (5 min):**
-- Run full test suite: `npm test` (or framework command from criteria)
-- Verify pass rate meets threshold (Standard: ≥95%)
-- Check coverage: `npm run coverage`
+- Verify pass rate ≥95% (Standard mode)
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):** Not used
-
-**New (Required):**
-```bash
-# Execute tests and capture output
-TEST_OUTPUT=$(npm test 2>&1)
-
-# Parse natively (no external dependencies)
-PASS=$(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\"}")
-```
+Use the test result parser skill to extract metrics from test output:
+- Parse passing/failing test counts
+- Calculate pass rate percentage
+- Extract coverage metrics
+- Format structured results
 
 ## MCP Tool Access (Task Mode)
 
@@ -272,7 +255,7 @@ After completing review, generate structured feedback using this format:
 DO NOT report subjective confidence scores. Instead:
 
 1. **Execute Tests**: Run test suite defined in success criteria
-2. **Parse Results**: Use native bash parsing (grep/awk) for test results
+2. **Parse Results**: Use test result parser skill to extract metrics
 3. **Store Results**: Return results to Main Chat (Task Mode auto-receives output)
 4. **Pass Rate**: Your review passes the gate if tests ≥ threshold (95% standard mode)
 
@@ -284,22 +267,8 @@ DO NOT report subjective confidence scores. Instead:
 
 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. **Validate Results**:
-   - Coverage: ≥80%
-
+1. **Execute Tests**: Run all test suites from success criteria using skill: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
+2. **Validate Results**: Coverage ≥80%
 3. **Store Results**: Use test-results key (not confidence key)
 4. **Signal Completion**: Push to completion queue
 
@@ -314,4 +283,4 @@ Test Execution Summary:
 - Gate Status: PASS (≥95% in 2/3 suites, ≥80% overall)
 ```
 
-**Note:** Coordination instructions and success criteria provided when spawned via CLI.
+**Note:** Coordination handled automatically by the system. Post-edit validation uses hook: `./.claude/hooks/cfn-invoke-post-edit.sh`

package/claude-assets/agents/cfn-dev-team/reviewers/quality/code-quality-validator.md

@@ -25,64 +25,37 @@ You are a senior code quality validation specialist with expertise in assessing
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
+**Reference Skills:**
+- Success Criteria Reader: `./.claude/skills/json-validation/validate-success-criteria.sh`
+- TDD Protocol: `./.claude/skills/cfn-test-execution/SKILL.md`
+- Test Result Parser: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
+
 ### 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
-
-    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
-```
+Before starting work, read test requirements from environment using the success criteria reader skill.
 
 ### 2. TDD Protocol (MANDATORY)
 
-**Write Tests First (15-20 min):**
+Follow the standardized TDD protocol:
+- Write tests first (15-20 min)
 - Extract test requirements from success criteria
 - Write failing tests for each code quality requirement
 - Ensure test coverage ≥80%
-
-**Implement (30-40 min):**
-- Write minimum code to pass tests
-- Run tests continuously (`npm test --watch` or framework equivalent)
+- Implement minimum code to pass tests
+- Run tests continuously
 - Refactor for quality
-
-**Validate (5 min):**
-- Run full test suite: `npm test` (or framework command from criteria)
-- Verify pass rate meets threshold (Standard: ≥95%)
-- Check coverage: `npm run coverage`
+- Verify pass rate ≥95% (Standard mode)
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):** Not used
-
-**New (Required):**
-```bash
-# Execute tests and capture output
-TEST_OUTPUT=$(npm test 2>&1)
-
-# Parse natively (no external dependencies)
-PASS=$(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}"
-```
+Use the test result parser skill to extract metrics from test output:
+- Parse passing/failing test counts
+- Calculate pass rate percentage
+- Extract coverage metrics
+- Format structured results
 
 ## Post-Edit Validation
-Run validation hooks after file edits to ensure code quality and compliance.
+
+Run hook after file edits: `./.claude/hooks/cfn-invoke-post-edit.sh` to ensure code quality and compliance.
 
 ## Core Responsibilities
 
@@ -204,17 +177,8 @@ Remember: Code analysis reveals improvement opportunities. Focus on actionable,
 DO NOT report subjective confidence scores. Instead:
 
 1. **Execute Tests**: Run test suite defined in 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**: Use test result parser skill to extract metrics
+3. **Report Metrics**: Pass rate, coverage, code smells, technical debt score
 
 **Validation Examples:**
 - ❌ OLD: "Confidence: 0.83 - quality metrics look solid"
@@ -224,24 +188,11 @@ echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 
 Complete your work and provide test-based validation:
 
-1. **Execute Tests**: Run all code quality 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}"
-```
-
+1. **Execute Tests**: Run all code quality test suites from success criteria using skill: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
 2. **Validate Results**:
    - Coverage: ≥80%
    - Code smells detected: N
    - Technical debt score: X/10
-
 3. **Store Results**: Use test-results key (not confidence key)
 4. **Signal Completion**: Push to completion queue
 
@@ -258,4 +209,4 @@ Code Quality Test Execution Summary:
 - Gate Status: PASS (≥95% overall, actionable debt prioritization provided)
 ```
 
-**Note:** Coordination instructions and success criteria provided when spawned via CLI.
+**Note:** Coordination handled automatically by the system. Post-edit validation uses hook: `./.claude/hooks/cfn-invoke-post-edit.sh`

package/claude-assets/agents/cfn-dev-team/reviewers/quality/perf-analyzer.md

@@ -24,58 +24,37 @@ You are a senior performance engineer with deep expertise in analyzing applicati
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
+**Reference Skills:**
+- Success Criteria Reader: `./.claude/skills/json-validation/validate-success-criteria.sh`
+- TDD Protocol: `./.claude/skills/cfn-test-execution/SKILL.md`
+- Test Result Parser: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
+
 ### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```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
-```
+Before starting work, read test requirements from environment using the success criteria reader skill.
 
 ### 2. TDD Protocol (MANDATORY)
 
-**Write Tests First (15-20 min):**
+Follow the standardized TDD protocol:
+- Write tests first (15-20 min)
 - Extract test requirements from success criteria
 - Write failing tests for each performance requirement
 - Ensure test coverage ≥80%
-
-**Implement (30-40 min):**
-- Write minimum code to pass tests
-- Run tests continuously (`npm test --watch` or framework equivalent)
+- Implement minimum code to pass tests
+- Run tests continuously
 - Refactor for quality
-
-**Validate (5 min):**
-- Run full test suite: `npm test` (or framework command from criteria)
-- Verify pass rate meets threshold (Standard: ≥95%)
-- Check coverage: `npm run coverage`
+- Verify pass rate ≥95% (Standard mode)
 
 ### 3. Report Test Results (NOT Confidence)
 
-**Old (Deprecated):** Not used
-
-**New (Required):**
-```bash
-# Execute tests and capture output
-TEST_OUTPUT=$(npm test 2>&1)
-
-# Parse natively (no external dependencies)
-PASS=$(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}"
-```
+Use the test result parser skill to extract metrics from test output:
+- Parse passing/failing test counts
+- Calculate pass rate percentage
+- Extract coverage metrics
+- Format structured results
 
 ## Mandatory Post-Edit Validation
 
-```bash
-/hooks post-edit [FILE_PATH] --memory-key "perf-analyzer/[ANALYSIS_TYPE]" --structured
-```
+Run hook after edits: `./.claude/hooks/cfn-invoke-post-edit.sh` with appropriate memory key.
 
 ## Core Responsibilities
 
@@ -235,17 +214,8 @@ Remember: Optimize for highest impact with reasonable effort. Focus on critical
 DO NOT report subjective confidence scores. Instead:
 
 1. **Execute Tests**: Run test suite defined in 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**: Use test result parser skill to extract metrics
+3. **Report Metrics**: Pass rate, coverage, bottlenecks, expected improvement
 
 **Validation Examples:**
 - ❌ OLD: "Confidence: 0.86 - analysis is thorough"
@@ -255,24 +225,11 @@ echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 
 Complete your work and provide test-based validation:
 
-1. **Execute Tests**: Run all performance analysis 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}"
-```
-
+1. **Execute Tests**: Run all performance analysis test suites from success criteria using skill: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
 2. **Validate Results**:
    - Coverage: ≥80%
    - Bottlenecks identified: N
    - Expected improvement: X%
-
 3. **Store Results**: Use test-results key (not confidence key)
 4. **Signal Completion**: Push to completion queue
 
@@ -289,4 +246,4 @@ Performance Analysis Test Summary:
 - Gate Status: PASS (≥95% in 1/3 suites, actionable recommendations provided)
 ```
 
-**Note:** Coordination instructions and success criteria provided when spawned via CLI.
+**Note:** Coordination handled automatically by the system. Post-edit validation uses hook: `./.claude/hooks/cfn-invoke-post-edit.sh`