Qcsd Cicd Swarm

QCSD CI/CD Swarm v1.0

Shift-left quality engineering swarm for CI/CD pipeline verification and release readiness.

---

Overview

The CI/CD Swarm takes code that passed Development quality checks and validates it is safe to release through the CI/CD pipeline. Where the Development Swarm asks "Is the code quality sufficient to ship?", the CI/CD Swarm asks "Is this change safe to release?"

This swarm operates at the pipeline level, analyzing test results, regression risk, flaky test impact, security pipeline status, and infrastructure changes to render a RELEASE / REMEDIATE / BLOCK decision.

QCSD Phase Positioning

Parameters

• PIPELINE_ARTIFACTS: Path to CI/CD artifacts, test results, and build output (required, e.g., ci/artifacts/)
• BASELINE_REF: Git ref for baseline comparison (optional, default: main)
• OUTPUT_FOLDER: Where to save reports (default: ${PROJECT_ROOT}/Agentic QCSD/cicd/)
• DEPLOY_TARGET: Target deployment environment (optional, e.g., staging, production)

---

ENFORCEMENT RULES - READ FIRST

PROHIBITED BEHAVIORS:

• Summarizing instead of spawning agents
• Skipping agents "for brevity"
• Proceeding before background tasks complete
• Providing your own analysis instead of spawning specialists
• Omitting report sections or using placeholder text

---

Step Execution Protocol

This skill uses a micro-file step architecture. Each step is a self-contained file loaded one at a time to avoid "lost in the middle" context degradation.

Execute steps sequentially by reading each step file with the Read tool.

Steps

1. Flag Detection -- steps/01-flag-detection.md -- Scan pipeline artifacts, detect all 6 flags 2. Core Agents -- steps/02-core-agents.md -- Spawn qe-quality-gate, qe-regression-analyzer, qe-flaky-hunter in parallel 3. Batch 1 Results -- steps/03-batch1-results.md -- Wait for core agents, extract all metrics 4. Conditional Agents -- steps/04-conditional-agents.md -- Spawn flagged conditional agents in parallel 5. Decision Synthesis -- steps/05-decision-synthesis.md -- Apply RELEASE/REMEDIATE/BLOCK logic 6. Report Generation -- steps/06-report-generation.md -- Generate executive summary and full report 7. Learning Persistence -- steps/07-learning-persistence.md -- Store findings to memory, save persistence record 8. Deployment Advisor -- steps/08-deployment-advisor.md -- Run qe-deployment-advisor analysis on all pipeline data 9. Final Output -- steps/09-final-output.md -- Display completion summary with all scores

Execution Instructions

1. Use the Read tool to load the current step file (e.g., Read({ file_path: ".claude/skills/qcsd-cicd-swarm/steps/01-flag-detection.md" })) 2. Execute the step's instructions completely 3. Verify all success criteria are met before proceeding 4. Pass the step's output as context to the next step 5. If a step fails, halt and report the failure point -- do not skip ahead

Resume Support

To resume from a specific step: specify --from-step N and the orchestrator will skip to step N. Ensure you have the required prerequisite data from prior steps.

---

Agent Inventory

Total: 10 agents (3 core + 6 conditional + 1 analysis)

---

Quality Gate Thresholds

---

Report Filename Mapping

---

Execution Model Options

---

Key Principle

Release safety is verified by evidence, not assumptions. This swarm provides pipeline-level quality assessment to ensure every release meets quality gates.

Step 1: Analyze Pipeline Context (Flag Detection)

Prerequisites

• CI/CD swarm skill invoked
• PIPELINE_ARTIFACTS path provided
• OUTPUT_FOLDER determined

Instructions

MANDATORY: Complete this analysis before Step 2.

Step 0: Retrieve Development Phase Signals

Retrieve the most recent Development phase signals from memory.

MCP Method:

aqe memory search --pattern "qcsd-development-*" --namespace "qcsd-development" --limit 1 --json

Flag Detection (Check ALL SIX)

HAS_SECURITY_PIPELINE = FALSE
  Set TRUE if pipeline artifacts include security scan results, SAST/DAST output,
  dependency vulnerability reports, container security scans, secret detection results

HAS_PERFORMANCE_PIPELINE = FALSE
  Set TRUE if pipeline includes performance test results, load test data,
  benchmark comparisons, response time measurements, throughput tests

HAS_INFRA_CHANGE = FALSE
  Set TRUE if pipeline includes infrastructure changes: Terraform plans,
  K8s manifests, Docker image changes, cloud resource modifications,
  deployment topology changes

HAS_MIDDLEWARE = FALSE
  Set TRUE if pipeline includes middleware components: message broker configs,
  ESB routes, API gateway rules, event bus schemas

HAS_SAP_INTEGRATION = FALSE
  Set TRUE if pipeline includes SAP artifacts: OData service definitions,
  SOAP WSDLs, IDoc schemas, RFC function modules

HAS_AUTHORIZATION = FALSE
  Set TRUE if pipeline includes authorization changes: role definitions,
  permission matrices, SoD policies, RBAC configurations

Output flag detection results before proceeding.

Success Criteria

• [ ] Development phase signals retrieved
• [ ] All SIX flags evaluated with evidence
• [ ] Expected agent count calculated

Output

All flag values with evidence, expected agent count.

Navigation

• On success: proceed to Step 2 by reading steps/02-core-agents.md
• On failure: halt and report

Step 2: Spawn Core Agents (Parallel Batch 1)

Prerequisites

• Step 1 completed with flags

Instructions

Spawn ALL THREE core agents in ONE message

Agent 1: Quality Gate

Evaluate all quality gates (coverage thresholds, lint rules, build status, test pass rates). Save to: ${OUTPUT_FOLDER}/02-quality-gates.md

Agent 2: Regression Analyzer

Analyze test results for regressions between baseline and current. Save to: ${OUTPUT_FOLDER}/03-regression-analysis.md

Agent 3: Flaky Hunter

Identify flaky tests, quarantine recommendations, and stability metrics. Save to: ${OUTPUT_FOLDER}/04-flaky-analysis.md

Success Criteria

• [ ] All THREE agents spawned in ONE message
• [ ] Post-spawn confirmation sent

Output

Confirmation of 3 agents running.

Navigation

• On success: proceed to Step 3 by reading steps/03-batch1-results.md

Step 3: Wait for Batch 1 & Extract Results

Prerequisites

• Step 2: All 3 core agents spawned

Instructions

WAIT for all three agents. Extract:

• Quality gate pass/fail status and scores
• Regression count and severity
• Flaky test count and quarantine recommendations
• Overall pipeline health metrics

Output Batch 1 Results Summary with all values.

Success Criteria

• [ ] All three agents returned
• [ ] All metrics extracted

Navigation

• On success: proceed to Step 4 by reading steps/04-conditional-agents.md

Step 4: Spawn Conditional Agents (Parallel Batch 2)

Prerequisites

• Step 3 completed, flags from Step 1

Instructions

If ALL flags FALSE, skip to Step 5.

Success Criteria

• [ ] All flagged agents spawned and completed

Navigation

• On success: proceed to Step 5 by reading steps/05-decision-synthesis.md

Step 5: Synthesize Results & Determine Recommendation

Prerequisites

• Core and conditional results available

Instructions

Apply RELEASE/REMEDIATE/BLOCK decision logic EXACTLY

BLOCK conditions (ANY triggers BLOCK):

• Quality gate FAILED on critical thresholds
• P0/P1 regressions detected
• Security vulnerabilities with CVSS >= 9.0
• Flaky test rate > 20% on critical paths

RELEASE conditions (ALL required):

• All quality gates PASSED
• No P0/P1 regressions
• Flaky test rate < 5%
• All conditional checks passed

Default: REMEDIATE

Record decision with metrics and rationale.

Success Criteria

• [ ] FINAL RECOMMENDATION: RELEASE / REMEDIATE / BLOCK

Navigation

• On success: proceed to Step 6 by reading steps/06-report-generation.md

Step 6: Generate Verification Report

Prerequisites

• Step 5 completed with recommendation

Instructions

Generate the CI/CD Verification Report to ${OUTPUT_FOLDER}/01-executive-summary.md.

Must include: Executive Summary, Quality Gates, Regression Analysis, Flaky Test Analysis, Conditional sections, Deployment Readiness Assessment, Recommended Actions.

Success Criteria

• [ ] Complete report saved

Navigation

• On success: proceed to Step 7 by reading steps/07-learning-persistence.md

Step 7: Store Learnings & Persist State

Prerequisites

• Step 6 completed

Instructions

ALWAYS RUN. NOT OPTIONAL.

Store verification findings to memory:

aqe memory store \
  --key "qcsd-cicd-${buildId}-${Date.now()}" \
  --namespace "qcsd-cicd" \
  --value '{...}' \
  --json

Save persistence record to ${OUTPUT_FOLDER}/11-learning-persistence.json.

Success Criteria

• [ ] Memory stored
• [ ] Persistence JSON saved

Navigation

• On success: proceed to Step 8 by reading steps/08-deployment-advisor.md

Step 8: Apply Deployment Advisor (Analysis)

Prerequisites

• Step 7 completed

Instructions

ALWAYS RUN qe-deployment-advisor

Spawn qe-deployment-advisor to provide deployment readiness assessment:

1. Analyze all pipeline data and agent outputs 2. Assess deployment risk score 3. Provide deployment strategy recommendation (blue-green, canary, rolling, direct) 4. Identify monitoring priorities for post-deploy 5. Generate rollback criteria

Save to: ${OUTPUT_FOLDER}/12-deployment-advisory.md

Success Criteria

• [ ] Deployment advisor completed
• [ ] Advisory report saved

Navigation

• On success: proceed to Step 9 by reading steps/09-final-output.md

Step 9: Final Output & Completion Summary

Prerequisites

• All steps completed

Instructions

Display the completion summary with all scores and recommendation: RELEASE / REMEDIATE / BLOCK with rationale, quality gate status, regression count, flaky rate, deployment risk score, and all deliverables.

Success Criteria

• [ ] Summary displayed

Navigation

• Terminal step.