claude-flow-novice 2.14.27 → 2.14.29

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

@@ -129,74 +129,15 @@ await redis.publish('swarm:security:critical', {
 - Security code review
 - Penetration testing scenarios
 
-## ⚠️ CRITICAL: Mode-Specific Completion Protocol (ANTI-023 MEMORY LEAK FIX)
+## Completion Protocol
 
-**First, determine how you were spawned:**
+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
 
-**Task Mode (95%):** You were called via `Task("security-specialist", "...")` in Main Chat
-- Simply complete your security audit and return structured JSON output
-- **❌ DO NOT:** Use Redis commands, execute bash scripts, signal completion via CLI tools
-- Main Chat receives your output automatically
-
-**CLI Mode (5%):** You were spawned via `npx claude-flow-novice agent-spawn ...` command
-- Use Redis signals and completion scripts as outlined below
-
-### Task Mode (Spawned via Task() tool in Main Chat)
-
-**Simply complete your work and return structured output.**
-
-```json
-{
-  "confidence": 0.85,
-  "status": "COMPLETE|NEEDS_WORK",
-  "summary": "Security audit completed with X findings",
-  "deliverables": ["security-report.md", "vulnerability-scan.json"],
-  "findings": {
-    "critical": 0,
-    "high": 2,
-    "medium": 5,
-    "low": 3
-  }
-}
-```
-
-**❌ FORBIDDEN in Task Mode:**
-- **DO NOT** run `redis-cli` commands
-- **DO NOT** execute `invoke-waiting-mode.sh` scripts
-- **DO NOT** use bash completion scripts
-- **DO NOT** signal completion via CLI tools
-- **Main Chat receives your output automatically - no coordination needed**
-
-### CLI Mode (Spawned via `npx claude-flow-novice agent-spawn`)
-
-**Step 1: Complete Work**
-Execute assigned security audit (vulnerability assessment, threat modeling, etc.)
-
-**Step 2: Signal Completion**
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-**Step 3: Report Confidence Score and Exit**
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-**Why This Matters:**
-- **ANTI-023 MEMORY LEAK:** Task Mode agents attempting CLI commands hang indefinitely
-- Task Mode uses direct JSON output, CLI Mode uses Redis coordination
-- Mixing protocols causes memory leaks and process hanging
-- **Check your spawn method FIRST before using any completion protocol**
-
-### How to Tell Which Mode You're In
-
-- **Task Mode**: You see a direct task assignment in Main Chat context
-- **CLI Mode**: You have TASK_ID and AGENT_ID environment variables
-- **When in doubt, assume Task Mode and return structured JSON output**
+**Note:** Coordination instructions are provided when spawned via CLI.
 
 ## Success Metrics
 

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

@@ -197,84 +197,13 @@ After completing review, generate structured feedback using this format:
 - Include a summary of total issues
 ```
 
-## CFN Loop Completion Protocol (Mode-Specific)
+## Completion Protocol
 
-### ⚠️ CRITICAL: Validator Scope Boundaries
+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
 
-**YOU ARE A VALIDATOR, NOT A COORDINATOR**
-
-✅ **Your responsibilities:**
-- Review code and deliverables
-- Assess quality, security, performance
-- Provide structured feedback
-- Report confidence score
-
-❌ **DO NOT:**
-- Spawn nested CFN Loops (`/cfn-loop-cli`, `/cfn-loop-task`)
-- Use SlashCommand tool (Main Chat only)
-- Coordinate other agents
-- Attempt complex orchestration
-
-**If you need deep analysis beyond validation, note it in feedback for Main Chat.**
-
-### ⚠️ CRITICAL: How to Complete Your Validation
-
-**First, determine how you were spawned:**
-
-- **Task Mode**: You were called via `Task("reviewer", "...")` in Main Chat
-- **CLI Mode**: You were spawned via `npx claude-flow-novice agent-spawn ...` command
-
----
-
-### If You Are in Task Mode (95% of cases)
-
-**🎯 YOUR INSTRUCTIONS: Simply return structured JSON output**
-
-```json
-{
-  "confidence": 0.85,
-  "status": "APPROVED|NEEDS_WORK",
-  "feedback": [
-    {"severity": "CRITICAL", "issue": "...", "suggestion": "..."}
-  ],
-  "summary": {
-    "critical_count": 0,
-    "warning_count": 2,
-    "suggestion_count": 3,
-    "files_reviewed": ["src/auth.ts", "tests/auth.test.ts"]
-  }
-}
-```
-
-**❌ DO NOT:**
-- Use any Redis commands (redis-cli)
-- Execute bash scripts for completion
-- Run invoke-waiting-mode.sh
-- Use slash commands (/cfn-loop-cli)
-- **Main Chat receives your JSON output automatically - that's all you need!**
-
----
-
-### If You Are in CLI Mode (Rare cases)
-
-**Only use these instructions if spawned via CLI command:**
-
-**Step 1: Complete Work**
-Execute assigned validation task
-
-**Step 2: Signal Completion**
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-**Step 3: Report Confidence Score**
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-**🚨 MEMORY LEAK WARNING**: If you try CLI commands in Task Mode, you will hang and cause memory leaks!
+**Note:** Coordination instructions are provided when spawned via CLI.
 

package/claude-assets/agents/cfn-dev-team/testers/e2e/playwright-tester.md

@@ -118,24 +118,13 @@ await sqlite.memoryAdapter.set(
 
 **Coordination**: Integrated with Claude Flow swarm ecosystem, following hook protocols and memory sharing for optimal test execution.
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on test coverage and quality
+- Summary of E2E testing completed
+- List of test cases executed and results
+- Performance metrics and any issues identified
 
-### Step 1: Complete Work
-Execute assigned task (implementation, review, testing, etc.)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
+**Note:** Coordination instructions are provided when spawned via CLI.
 

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

@@ -153,24 +153,13 @@ await sqlite.memoryAdapter.set(
 
 Remember: Testing validates system behavior, catches regressions, and ensures quality across user interactions.
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on test coverage and quality
+- Summary of interaction testing completed
+- List of test cases executed and results
+- Accessibility compliance and user flow validation results
 
-### Step 1: Complete Work
-Execute assigned task (implementation, review, testing, etc.)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
+**Note:** Coordination instructions are provided when spawned via CLI.
 

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

@@ -154,83 +154,13 @@ lifecycle:
 - Use containerization for test isolation
 - Implement automated test setup and teardown
 
-## CFN Loop Completion Protocol (Mode-Specific)
+## Completion Protocol
 
-### ⚠️ CRITICAL: Validator Scope Boundaries
+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
 
-**YOU ARE A TESTER/VALIDATOR, NOT A COORDINATOR**
-
-✅ **Your responsibilities:**
-- Execute test cases and validation
-- Report test results with confidence scores
-- Identify bugs and quality issues
-- Provide structured feedback
-
-❌ **DO NOT:**
-- Spawn nested CFN Loops (`/cfn-loop-cli`, `/cfn-loop-task`)
-- Use SlashCommand tool (Main Chat only)
-- Coordinate other agents
-- Attempt complex orchestration
-
-**If you need deep testing beyond validation, note it in feedback for Main Chat.**
-
-### ⚠️ CRITICAL: How to Complete Your Testing
-
-**First, determine how you were spawned:**
-
-- **Task Mode**: You were called via `Task("tester", "...")` in Main Chat
-- **CLI Mode**: You were spawned via `npx claude-flow-novice agent-spawn ...` command
-
----
-
-### If You Are in Task Mode (95% of cases)
-
-**🎯 YOUR INSTRUCTIONS: Simply return structured test report**
-
-```markdown
-## Test Execution Report
-- **Total Test Cases**: N
-- **Passed**: X
-- **Failed**: Y
-- **Confidence Score**: 0.85
-- **Status**: PASS|FAIL
-- **Critical Issues**: [List]
-- **Warnings**: [List]
-- **Files Tested**: [file1.ts, file2.test.ts]
-```
-
-**❌ DO NOT:**
-- Use any Redis commands (redis-cli)
-- Execute bash scripts for completion
-- Run invoke-waiting-mode.sh
-- Use slash commands (/cfn-loop-cli)
-- **Main Chat receives your test report automatically - that's all you need!**
-
----
-
-### If You Are in CLI Mode (Rare cases)
-
-**Only use these instructions if spawned via CLI command:**
-
-**Step 1: Complete Testing**
-Execute all test cases and validation
-
-**Step 2: Signal Completion**
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-**Step 3: Report Confidence Score**
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-**🚨 MEMORY LEAK WARNING**: If you try CLI commands in Task Mode, you will hang and cause memory leaks!
-
-**Step 4: Exit Cleanly**
-Agent exits after reporting (no waiting mode)
+**Note:** Coordination instructions are provided when spawned via CLI.
 

package/claude-assets/agents/cfn-dev-team/testers/unit/tdd-london-unit-swarm.md

@@ -23,23 +23,12 @@ lifecycle:
 ---
 **Key Insight**: The London School emphasizes object collaboration over internal state. Focus on interactions, define clear contracts, and verify behavior through precise mock expectations.
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on unit test quality and coverage
+- Summary of TDD London School implementation completed
+- List of unit tests created with interaction focus
+- Mock verification and behavior contracts validated
 
-### Step 1: Complete Work
-Execute assigned task (unit test implementation, test suite development, interaction verification)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
+**Note:** Coordination instructions are provided when spawned via CLI.

package/claude-assets/agents/cfn-dev-team/testers/validation/validation-production-validator.md

@@ -8,24 +8,12 @@ model: claude-sonnet-4
 
 Remember: Production validation ensures system reliability, user safety, and organizational compliance.
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
-
-### Step 1: Complete Work
-Execute assigned task (validation, readiness assessment, deployment checks)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
+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
 
+**Note:** Coordination instructions are provided when spawned via CLI.

package/claude-assets/agents/cfn-dev-team/testing/test-validation-agent.md

@@ -40,52 +40,15 @@ Specialized reviewer agent focused on validating test results, analyzing coverag
 - Validate mock/stub correctness
 - Check for race conditions in async tests
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+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
 
-### Step 1: Complete Work
-Execute test validation analysis:
-- Read test output files
-- Parse coverage reports
-- Analyze test quality metrics
-- Document findings in structured format
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score and Exit
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
-
-**Why This Matters:**
-- Orchestrator collects confidence/consensus scores from Redis
-- Enables adaptive agent specialization for next iteration
-- Prevents orchestrator blocking on wait $PID
-- Coordinator spawns appropriate specialist based on feedback type
-
-**Context Variables:**
-- `TASK_ID`: Provided by orchestrator/coordinator
-- `AGENT_ID`: Your unique agent identifier (e.g., "test-validation-agent-1")
-- Confidence: Self-assessment score (0.0-1.0) based on validation completeness
-
-**Confidence Scoring Criteria:**
-- 0.95-1.0: All tests pass, coverage meets criteria, no quality issues
-- 0.85-0.94: Minor issues detected, coverage adequate, tests reliable
-- 0.75-0.84: Moderate issues, coverage gaps exist, some test improvements needed
-- 0.60-0.74: Significant issues, coverage below threshold, quality concerns
-- Below 0.60: Critical failures, inadequate coverage, major quality problems
-
-See: `.claude/skills/cfn-redis-coordination/SKILL.md` for full protocol details
+**Note:** Coordination instructions are provided when spawned via CLI.
 
 ## Validation Workflow
 

package/claude-assets/agents/cfn-dev-team/utility/agent-builder.md

@@ -95,46 +95,20 @@ description: MUST BE USED when specific use case. Keywords - relevant, terms
 description: MUST BE USED when [primary use case]. Use PROACTIVELY for [secondary scenarios]. Keywords - [searchable, terms, for, discovery]
 ```
 
-## CFN Loop Redis Completion Protocol
+## Agent Completion Protocol
 
-When creating agent templates, MUST include this exact protocol section:
+When creating agent templates, include this standardized completion section:
 
 ```markdown
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+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
 
-### Step 1: Complete Work
-Execute assigned task (describe agent's specific task type here)
-
-### Step 2: Signal Completion
-\```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-\```
-
-### Step 3: Report Confidence Score and Exit
-\```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-\```
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
-
-**Why This Matters:**
-- Orchestrator collects confidence/consensus scores from Redis
-- Enables adaptive agent specialization for next iteration
-- Prevents orchestrator blocking on wait $PID
-- Coordinator spawns appropriate specialist based on feedback type
-
-**Context Variables:**
-- \`TASK_ID\`: Provided by orchestrator/coordinator
-- \`AGENT_ID\`: Your unique agent identifier (e.g., "agent-name-1")
-- Confidence: Self-assessment score (0.0-1.0) - explain agent-specific criteria
-
-See: \`.claude/skills/cfn-redis-coordination/SKILL.md\` for full protocol details
+**Note:** Coordination instructions are provided when spawned via CLI.
 ```
 
 ---
@@ -231,28 +205,15 @@ You implement REST API endpoints following best practices and OpenAPI specificat
    - Update OpenAPI spec
    - Generate API docs
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+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
 
-### Step 1: Complete Work
-Implement API endpoints with tests and documentation
-
-### Step 2: Signal Completion
-\```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-\```
-
-### Step 3: Report Confidence Score and Exit
-\```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-\```
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
+**Note:** Coordination instructions are provided when spawned via CLI.
 
 ## Success Metrics
 - All endpoints tested
@@ -325,28 +286,15 @@ You review code for security vulnerabilities and compliance issues.
 - [Suggestion]
 - Benefit: [security improvement]
 
-## CFN Loop Redis Completion Protocol
-
-When participating in CFN Loop workflows, agents MUST follow this protocol:
-
-### Step 1: Complete Work
-Perform security review and generate findings
+## Completion Protocol
 
-### Step 2: Signal Completion
-\```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-\```
+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
 
-### Step 3: Report Confidence Score and Exit
-\```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-\```
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
+**Note:** Coordination instructions are provided when spawned via CLI.
 
 ## Success Metrics
 - Zero critical vulnerabilities
@@ -402,49 +350,25 @@ You coordinate multiple agents to implement complex features.
 
 ## Agent Spawning Pattern
 
-\```bash
+Use CLI spawning commands and let the coordination system handle the workflow:
+
+```bash
 # Spawn implementers
 npx claude-flow-novice agent-spawn backend-dev --task-id "$TASK_ID"
 npx claude-flow-novice agent-spawn frontend-dev --task-id "$TASK_ID"
+```
 
-# Wait for completion via Redis
-redis-cli blpop "swarm:$TASK_ID:backend-dev-1:done" 0
-redis-cli blpop "swarm:$TASK_ID:frontend-dev-1:done" 0
-
-# Collect confidence scores
-CONSENSUS=$(./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh collect \
-  --task-id "$TASK_ID" \
-  --agent-ids "backend-dev-1,frontend-dev-1")
-
-# Check gate threshold
-if (( $(echo "$CONSENSUS >= 0.75" | bc -l) )); then
-  echo "✅ Gate passed, proceeding to validation"
-  # Spawn validators...
-fi
-\```
-
-## CFN Loop Redis Completion Protocol
-
-When participating in CFN Loop workflows, agents MUST follow this protocol:
-
-### Step 1: Complete Work
-Orchestrate all agents through CFN Loop workflow
+**Note:** The coordination system handles agent completion, confidence collection, and workflow progression automatically.
 
-### Step 2: Signal Completion
-\```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-\```
+## Completion Protocol
 
-### Step 3: Report Confidence Score and Exit
-\```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-\```
+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
 
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
+**Note:** Coordination instructions are provided when spawned via CLI.
 
 ## Success Metrics
 - Feature fully implemented