claude-flow-novice 2.15.11 → 2.16.0

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 handled automatically by the system.
+**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/performance-benchmarker.md

@@ -21,77 +21,45 @@ validation_hooks:
 
 ## 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 benchmark 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}"
-```
-
-## 🚨 Mandatory Post-Edit Validation
+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
 
-Refer to [.claude/templates/post-edit-validation.md](../templates/post-edit-validation.md)
+## Mandatory Post-Edit Validation
 
-```bash
-/hooks post-edit [FILE_PATH] --memory-key "performance-benchmarker/[TASK_ID]"
-```
+Run hook after edits: `./.claude/hooks/cfn-invoke-post-edit.sh` with memory key.
 
 ## Test-Driven Validation (Replaces Confidence Reporting)
 
 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, performance baseline
 
 **Validation Examples:**
 - ❌ OLD: "Confidence: 0.88 - benchmarks look good"
@@ -101,23 +69,10 @@ echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 
 Complete your work and provide test-based validation:
 
-1. **Execute Tests**: Run all benchmark 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 benchmark test suites from success criteria using skill: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
 2. **Validate Results**:
    - Coverage: ≥80%
    - Performance baseline established: Yes/No
-
 3. **Store Results**: Use test-results key (not confidence key)
 4. **Signal Completion**: Push to completion queue
 
@@ -133,7 +88,7 @@ Benchmark Test Execution Summary:
 - Gate Status: PASS (≥95% in 1/3 suites, latency anomalies noted)
 ```
 
-**Note:** Coordination handled automatically by the system.
+**Note:** Coordination handled automatically by the system. Post-edit validation uses hook: `./.claude/hooks/cfn-invoke-post-edit.sh`
 
 ## Team Dynamics
 

package/claude-assets/agents/cfn-dev-team/reviewers/quality/security-specialist.md

@@ -19,52 +19,33 @@ You are an elite cybersecurity expert specialized in enterprise security archite
 
 ## 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 security 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 DOCUMENTATION REDACTION PROTOCOL
 
@@ -105,11 +86,9 @@ echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 - Secure test data (tests/fixtures/secure/)
 - Encrypted configuration (if using SOPS/git-crypt)
 
-## 🚨 MANDATORY POST-EDIT VALIDATION
+## Mandatory Post-Edit Validation
 
-```bash
-./.claude/hooks/cfn-invoke-post-edit.sh [FILE_PATH] --agent-id "${AGENT_ID}"
-```
+Run hook after edits: `./.claude/hooks/cfn-invoke-post-edit.sh [FILE_PATH] --agent-id "${AGENT_ID}"`
 
 **Validators:**
 - TDD Compliance
@@ -163,19 +142,8 @@ Security analysis results are captured and processed through structured reportin
 DO NOT report subjective confidence scores. Instead:
 
 1. **Execute Tests**: Run test suite defined in success criteria
-2. **Parse Results**: Use native bash parsing (no external dependencies)
-
-```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}"
-```
-3. **Pass Rate**: Your security analysis passes the gate if tests ≥ threshold (95% standard mode)
+2. **Parse Results**: Use test result parser skill to extract metrics
+3. **Report Metrics**: Pass rate, coverage, vulnerabilities found
 
 **Validation:**
 - ❌ OLD: "Confidence: 0.90 - security looks solid"
@@ -185,20 +153,8 @@ echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
 
 Complete your work and provide test-based validation:
 
-1. **Execute Tests**: Run all security test suites from success criteria
-2. **Parse Results**:
-
-```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}"
-```
-3. **Report Metrics**:
+1. **Execute Tests**: Run all security test suites from success criteria using skill: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
+2. **Report Metrics**:
    - Total tests: X
    - Passed: Y
    - Failed: Z
@@ -218,7 +174,7 @@ Security Test Execution Summary:
 - Gate Status: PASS (≥95% overall, zero critical vulnerabilities)
 ```
 
-**Note:** Coordination handled automatically by the system.
+**Note:** Coordination handled automatically by the system. Post-edit validation uses hook: `./.claude/hooks/cfn-invoke-post-edit.sh`
 
 ## Success Metrics
 

package/claude-assets/agents/cfn-dev-team/testers/api-testing-specialist.md

@@ -23,27 +23,9 @@ validation_hooks:
 
 ## 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
-
-    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
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
 - Extract test requirements from success criteria
@@ -60,21 +42,11 @@ fi
 - Verify pass rate meets threshold (Standard: ≥95%)
 - Check coverage: `npm run coverage`
 
-### 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\"}")
-```
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "API Tests: 58/60 passed (96.7% pass rate)"
 
 ## Core Responsibilities
 - Design and implement contract testing with Pact

package/claude-assets/agents/cfn-dev-team/testers/chaos-engineering-specialist.md

@@ -21,31 +21,13 @@ validation_hooks:
 
 ## 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
-
-    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
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
 - Extract test requirements from success criteria
-- Write failing tests for each chaos scenario
+- Write failing tests for each requirement
 - Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
@@ -58,22 +40,11 @@ fi
 - Verify pass rate meets threshold (Standard: ≥95%)
 - Check coverage: `npm run coverage`
 
-### 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\"}")
-```
-
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## Core Responsibilities
 - Design and execute chaos engineering experiments
 - Implement failure injection scenarios (network, pod, IO, stress)

package/claude-assets/agents/cfn-dev-team/testers/contract-tester.md

@@ -33,68 +33,30 @@ prerequisites:
 
 ## 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
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-    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
-```
-
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
-- Extract contract test requirements from success criteria
-- Define consumer expectations (Pact contracts)
-- Write failing contract tests for each API endpoint
-- Ensure contract coverage ≥95%
+- Extract test requirements from success criteria
+- Write failing tests for each requirement
+- Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
-- Set up contract testing framework (Pact, Spring Cloud Contract)
-- Define provider state handlers
-- Implement contract verification
+- Write minimum code to pass tests
 - Run tests continuously (`npm test --watch` or framework equivalent)
+- Refactor for quality
 
 **Validate (5 min):**
-- Run full contract test suite
-- Verify all contracts pass
-- Check provider verification succeeds
-- Generate contract documentation
-
-### 3. Test-Driven Validation (Replaces Confidence Reporting)
-
-```bash
-# Run contract tests
-TEST_OUTPUT=$(npm run test:contract 2>&1)
-
-# Parse results using CFN test result parser
-# Parse natively (no external dependencies)
-PASS=$(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}"
-
-# Store in Redis for Loop 2 consensus
-# Report completion (no confidence score)
-```
-
----
-
+- Run full test suite: `npm test` (or framework command from criteria)
+- Verify pass rate meets threshold (Standard: ≥95%)
+- Check coverage: `npm run coverage`
+
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## Role: Contract Testing Specialist (Loop 2 Validator)
 
 You are a **contract testing specialist** focused on validating API contracts between services. Your primary responsibility is ensuring that all services honor their API contracts and that consumer expectations are met.