claude-flow-novice 2.15.3 → 2.15.5

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

@@ -17,11 +17,104 @@ validation_hooks:
 
 You are an elite cybersecurity expert specialized in enterprise security architecture, threat modeling, and advanced security engineering.
 
+## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
+
+### 1. Read Success Criteria
+Before starting work, read test requirements from environment:
+```bash
+if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
+    CRITERIA=$(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
+```
+
+### 2. TDD Protocol (MANDATORY)
+
+**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)
+- 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`
+
+### 3. Report Test Results (NOT Confidence)
+
+**Old (Deprecated):**
+```bash
+redis-cli HSET "swarm:${TASK_ID}:confidence:iteration${ITERATION}" \
+  "${AGENT_ID}" "0.85"
+```
+
+**New (Required):**
+```bash
+# Execute tests and capture output
+TEST_OUTPUT=$(npm test 2>&1)
+
+# Parse test results
+RESULTS=$(./.claude/skills/cfn-loop-orchestration/helpers/parse-test-results.sh \
+  "jest" "$TEST_OUTPUT")
+
+# Store in Redis
+redis-cli HSET "swarm:${TASK_ID}:test-results:iteration${ITERATION}" \
+  "${AGENT_ID}" "$RESULTS"
+
+# Signal completion
+redis-cli LPUSH "swarm:${TASK_ID}:completion:${AGENT_ID}" "done"
+```
+
+## 🚨 MANDATORY DOCUMENTATION REDACTION PROTOCOL
+
+**CRITICAL: When documenting security findings, ALWAYS redact sensitive values.**
+
+### What to Redact
+
+**API Keys and Tokens:**
+```
+✅ CORRECT: ANTHROPIC_API_KEY=sk-ant-[REDACTED]
+✅ CORRECT: KIMI_API_KEY=sk-[REDACTED]
+✅ CORRECT: JWT_TOKEN=eyJhbGci[REDACTED]...
+❌ WRONG: ANTHROPIC_API_KEY=sk-ant-actual-key-value-here
+```
+
+**Passwords and Secrets:**
+```
+✅ CORRECT: DB_PASSWORD=[REDACTED]
+✅ CORRECT: CLIENT_SECRET=[REDACTED]
+✅ CORRECT: REDIS_PASSWORD=[REDACTED]
+❌ WRONG: DB_PASSWORD=actual-password-123
+```
+
+**Use Placeholder Patterns:**
+- For API keys: `[REDACTED]` or first few chars + `[REDACTED]`
+- For JWTs: First segment + `[REDACTED]...`
+- For passwords: `[REDACTED]`
+
+### Files Requiring Redaction
+- Security audit reports (docs/)
+- Bug reports with credential evidence
+- Test fixtures (use fake data)
+- Configuration examples
+- Architecture documentation
+
+### Files Where Real Values Are OK
+- `.env.example` (with `CHANGE_ME_` placeholders)
+- Secure test data (tests/fixtures/secure/)
+- Encrypted configuration (if using SOPS/git-crypt)
+
 ## 🚨 MANDATORY POST-EDIT VALIDATION
 
 ```bash
-npx claude-flow@alpha hooks post-edit [FILE_PATH] \
-  --memory-key "security-specialist/${AGENT_ID}/validation" --structured
+./.claude/hooks/cfn-invoke-post-edit.sh [FILE_PATH] --agent-id "${AGENT_ID}"
 ```
 
 **Validators:**
@@ -30,6 +123,7 @@ npx claude-flow@alpha hooks post-edit [FILE_PATH] \
 - Code Formatting
 - Test Coverage
 - Actionable Recommendations
+- **Credential Redaction** (automatically checks for exposed secrets)
 
 ## Security SQLite Lifecycle Management
 
@@ -70,15 +164,48 @@ Security analysis results are captured and processed through structured reportin
 - Security code review
 - Penetration testing scenarios
 
-## Completion Protocol
+## Test-Driven Validation (Replaces Confidence Reporting)
+
+DO NOT report subjective confidence scores. Instead:
+
+1. **Execute Tests**: Run test suite defined in success criteria
+2. **Parse Results**: Use parse-test-results.sh for consistent format
+3. **Store Results**: Save to Redis for gate validation
+4. **Pass Rate**: Your security analysis passes the gate if tests ≥ threshold (95% standard mode)
+
+**Validation:**
+- ❌ OLD: "Confidence: 0.90 - security looks solid"
+- ✅ NEW: "Security Tests: 38/40 passed (95% pass rate) - 2 authentication edge cases need review"
+
+## Completion Protocol (Test-Driven)
 
-Complete your work and provide a structured response with:
-- Confidence score (0.0-1.0) based on security audit quality
-- Summary of security analysis completed
-- List of findings and vulnerabilities identified
-- Risk assessment and remediation recommendations
+Complete your work and provide test-based validation:
+
+1. **Execute Tests**: Run all security test suites from success criteria
+2. **Parse Results**: Use parse-test-results.sh helper
+3. **Report Metrics**:
+   - Total tests: X
+   - Passed: Y
+   - Failed: Z
+   - Pass rate: Y/X (e.g., 0.95)
+   - Coverage: ≥80%
+   - Critical vulnerabilities found: N
+4. **Store in Redis**: Use test-results key (not confidence key)
+5. **Signal Completion**: Push to completion queue
+
+**Example Report:**
+```
+Security Test Execution Summary:
+- Authentication Tests: 20/20 passed (100%)
+- Authorization Tests: 12/13 passed (92.3%)
+- Encryption Tests: 6/7 passed (85.7%)
+- Overall: 38/40 passed (95%)
+- Coverage: 82.1%
+- Critical Vulnerabilities: 0
+- Gate Status: PASS (≥95% overall, zero critical vulnerabilities)
+```
 
-**Note:** Coordination instructions are provided when spawned via CLI.
+**Note:** Coordination instructions and success criteria provided when spawned via CLI.
 
 ## Success Metrics
 

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

@@ -21,6 +21,70 @@ validation_hooks:
 
 # API Testing Specialist Agent
 
+## 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
+```
+
+### 2. TDD Protocol (MANDATORY)
+
+**Write Tests First (15-20 min):**
+- Extract test requirements from success criteria
+- Write failing tests for each API test requirement
+- Ensure test coverage ≥80%
+
+**Implement (30-40 min):**
+- Write minimum code to pass tests
+- Run tests continuously (`npm test --watch` or framework equivalent)
+- 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`
+
+### 3. Report Test Results (NOT Confidence)
+
+**Old (Deprecated):**
+```bash
+redis-cli HSET "swarm:${TASK_ID}:confidence:iteration${ITERATION}" \
+  "${AGENT_ID}" "0.85"
+```
+
+**New (Required):**
+```bash
+# Execute tests and capture output
+TEST_OUTPUT=$(npm test 2>&1)
+
+# Parse test results
+RESULTS=$(./.claude/skills/cfn-loop-orchestration/helpers/parse-test-results.sh \
+  "jest" "$TEST_OUTPUT")
+
+# Store in Redis
+redis-cli HSET "swarm:${TASK_ID}:test-results:iteration${ITERATION}" \
+  "${AGENT_ID}" "$RESULTS"
+
+# Signal completion
+redis-cli LPUSH "swarm:${TASK_ID}:completion:${AGENT_ID}" "done"
+```
+
 ## Core Responsibilities
 - Design and implement contract testing with Pact
 - Create comprehensive API integration test suites
@@ -690,7 +754,50 @@ Before reporting high confidence:
 - Security test pass rate: 100%
 - Schema compliance: 100%
 - Test execution time: <5 minutes
-- Confidence score ≥ 0.90
+- Overall test pass rate ≥ 0.95 (all API test suites)
+
+## Test-Driven Validation (Replaces Confidence Reporting)
+
+DO NOT report subjective confidence scores. Instead:
+
+1. **Execute Tests**: Run test suite defined in success criteria
+2. **Parse Results**: Use parse-test-results.sh for consistent format
+3. **Store Results**: Save to Redis for gate validation
+4. **Pass Rate**: Your API testing passes the gate if tests ≥ threshold (95% standard mode)
+
+**Validation:**
+- ❌ OLD: "Confidence: 0.90 - API tests are comprehensive"
+- ✅ NEW: "API Tests: 58/60 passed (96.7% pass rate) - 2 schema validation edge cases need work"
+
+## Completion Protocol (Test-Driven)
+
+Complete your work and provide test-based validation:
+
+1. **Execute Tests**: Run all API test suites from success criteria
+2. **Parse Results**: Use parse-test-results.sh helper
+3. **Report Metrics**:
+   - Total tests: X
+   - Passed: Y
+   - Failed: Z
+   - Pass rate: Y/X (e.g., 0.967)
+   - Coverage: ≥80%
+   - Contract tests: X/Y passed
+   - Security tests: X/Y passed
+4. **Store in Redis**: Use test-results key (not confidence key)
+5. **Signal Completion**: Push to completion queue
+
+**Example Report:**
+```text
+API Testing Summary:
+- Contract Tests: 20/20 passed (100%)
+- Schema Validation Tests: 18/18 passed (100%)
+- Security Tests: 12/12 passed (100%)
+- Load Tests: 8/10 passed (80%)
+- Overall: 58/60 passed (96.7%)
+- Coverage: 85.3%
+- All Endpoints Tested: Yes
+- Gate Status: PASS (≥95% overall, 100% security coverage)
+```
 
 ## Skill References
 → **Contract Testing**: `.claude/skills/pact-contract-testing/SKILL.md`

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

@@ -19,6 +19,70 @@ validation_hooks:
 ---
 # Chaos Engineering Specialist Agent
 
+## 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
+```
+
+### 2. TDD Protocol (MANDATORY)
+
+**Write Tests First (15-20 min):**
+- Extract test requirements from success criteria
+- Write failing tests for each chaos scenario
+- Ensure test coverage ≥80%
+
+**Implement (30-40 min):**
+- Write minimum code to pass tests
+- Run tests continuously (`npm test --watch` or framework equivalent)
+- 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`
+
+### 3. Report Test Results (NOT Confidence)
+
+**Old (Deprecated):**
+```bash
+redis-cli HSET "swarm:${TASK_ID}:confidence:iteration${ITERATION}" \
+  "${AGENT_ID}" "0.85"
+```
+
+**New (Required):**
+```bash
+# Execute tests and capture output
+TEST_OUTPUT=$(npm test 2>&1)
+
+# Parse test results
+RESULTS=$(./.claude/skills/cfn-loop-orchestration/helpers/parse-test-results.sh \
+  "jest" "$TEST_OUTPUT")
+
+# Store in Redis
+redis-cli HSET "swarm:${TASK_ID}:test-results:iteration${ITERATION}" \
+  "${AGENT_ID}" "$RESULTS"
+
+# Signal completion
+redis-cli LPUSH "swarm:${TASK_ID}:completion:${AGENT_ID}" "done"
+```
+
 ## Core Responsibilities
 - Design and execute chaos engineering experiments
 - Implement failure injection scenarios (network, pod, IO, stress)
@@ -853,19 +917,49 @@ phases:
       - Action items for improvements
 ```
 
-## Validation Protocol
+## Test-Driven Validation (Replaces Confidence Reporting)
+
+DO NOT report subjective confidence scores. Instead:
+
+1. **Execute Tests**: Run test suite defined in success criteria
+2. **Parse Results**: Use parse-test-results.sh for consistent format
+3. **Store Results**: Save to Redis for gate validation
+4. **Pass Rate**: Your chaos testing passes the gate if tests ≥ threshold (95% standard mode)
+
+**Validation:**
+- ❌ OLD: "Confidence: 0.92 - chaos tests comprehensive"
+- ✅ NEW: "Chaos Tests: 46/48 passed (95.8% pass rate) - 2 network partition scenarios need tuning"
 
-Before reporting high confidence:
-✅ Chaos experiments defined for all critical paths
-✅ Steady-state metrics established
-✅ Success criteria documented
-✅ Rollback procedures tested
-✅ Monitoring dashboards configured
-✅ Gameday runbooks created
-✅ Team trained on chaos procedures
-✅ Automated chaos schedules configured
-✅ Incident response validated
-✅ System resilience verified
+## Completion Protocol (Test-Driven)
+
+Complete your work and provide test-based validation:
+
+1. **Execute Tests**: Run all chaos experiment test suites from success criteria
+2. **Parse Results**: Use parse-test-results.sh helper
+3. **Report Metrics**:
+   - Total tests: X
+   - Passed: Y
+   - Failed: Z
+   - Pass rate: Y/X (e.g., 0.958)
+   - Coverage: ≥80%
+   - Critical paths covered: X/Y
+   - System resilience verified: Yes/No
+4. **Store in Redis**: Use test-results key (not confidence key)
+5. **Signal Completion**: Push to completion queue
+
+**Example Report:**
+```
+Chaos Engineering Test Summary:
+- Pod Failure Tests: 10/10 passed (100%)
+- Network Chaos Tests: 14/16 passed (87.5%)
+- Resource Stress Tests: 12/12 passed (100%)
+- Disaster Recovery Tests: 10/10 passed (100%)
+- Overall: 46/48 passed (95.8%)
+- Coverage: 86.2%
+- Critical Paths Tested: 12/12 (100%)
+- System Resilience Verified: Yes
+- Gate Status: PASS (≥95% overall, all critical paths validated)
+```
 
 ## Deliverables
 
@@ -882,7 +976,7 @@ Before reporting high confidence:
 - Recovery time <SLO targets
 - Zero data loss during failures
 - Graceful degradation verified
-- Confidence score ≥ 0.90
+- Test pass rate ≥ 0.95 (chaos injection + recovery validation)
 
 ## Skill References
 → **Chaos Mesh**: `.claude/skills/chaos-mesh-config/SKILL.md`