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

Agent Inventory

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

Quality Gate Thresholds

Report Filename Mapping

02-quality-gates.md

03-regression-analysis.md

04-flaky-test-analysis.md

05-security-scan.md

06-chaos-resilience.md

07-coverage-analysis.md

08-middleware-health.md

09-soap-contracts.md

10-sod-compliance.md

11-learning-persistence.json

12-deployment-advisory.md

01-executive-summary.md

Execution Model Options

Task({ subagent_type, run_in_background: true })

fleet_init({})

task_submit({})

swarm init

agent spawn

Key Principle

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