Cluster Agent Swarm — Complete Platform Operations
This is the complete cluster-agent-swarm skill package. When you add this skill, you get
access to ALL 7 specialized agents working together as a coordinated swarm.
Installation Options
Install All Skills (Recommended)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills
This installs all 7 agents as a single combined skill with access to all capabilities.
Install Individual Skills
Each agent can also be installed separately:
# Orchestrator - Task routing and coordination
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/orchestrator
# Cluster Ops - Atlas (cluster operations)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/cluster-ops
# GitOps - Flow (ArgoCD, Helm, Kustomize)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/gitops
# Security - Shield (RBAC, policies, CVEs)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/security
# Observability - Pulse (metrics, alerts, incidents)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/observability
# Artifacts - Cache (registries, SBOM, promotions)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/artifacts
# Developer Experience - Desk (namespaces, onboarding)
npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/developer-experience
The Swarm — Agent Roster
| Agent |
Code Name |
Session Key |
Domain |
| Orchestrator |
Jarvis |
agent:platform:orchestrator |
Task routing, coordination, standups |
| Cluster Ops |
Atlas |
agent:platform:cluster-ops |
Cluster lifecycle, nodes, upgrades |
| GitOps |
Flow |
agent:platform:gitops |
ArgoCD, Helm, Kustomize, deploys |
| Security |
Shield |
agent:platform:security |
RBAC, policies, secrets, scanning |
| Observability |
Pulse |
agent:platform:observability |
Metrics, logs, alerts, incidents |
| Artifacts |
Cache |
agent:platform:artifacts |
Registries, SBOM, promotion, CVEs |
| Developer Experience |
Desk |
agent:platform:developer-experience |
Namespaces, onboarding, support |
Agent Capabilities Summary
What Agents CAN Do
- Read cluster state (
kubectl get, kubectl describe, oc get)
- Deploy via GitOps (
argocd app sync, Flux reconciliation)
- Create documentation and reports
- Investigate and triage incidents
- Provision standard resources (namespaces, quotas, RBAC)
- Run health checks and audits
- Scan images and generate SBOMs
- Query metrics and logs
- Execute pre-approved runbooks
What Agents CANNOT Do (Human-in-the-Loop Required)
- Delete production resources (
kubectl delete in prod)
- Modify cluster-wide policies (NetworkPolicy, OPA, Kyverno cluster policies)
- Make direct changes to secrets without rotation workflow
- Modify network routes or service mesh configuration
- Scale beyond defined resource limits
- Perform irreversible cluster upgrades
- Approve production deployments (can prepare, human approves)
- Change RBAC at cluster-admin level
Communication Patterns
@Mentions
Agents communicate via @mentions in shared task comments:
@Shield Please review the RBAC for payment-service v3.2 before I sync.
@Pulse Is the CPU spike related to the deployment or external traffic?
@Atlas The staging cluster needs 2 more worker nodes.
Thread Subscriptions
- Commenting on a task → auto-subscribe
- Being @mentioned → auto-subscribe
- Being assigned → auto-subscribe
- Once subscribed → receive ALL future comments on heartbeat
Escalation Path
- Agent detects issue
- Agent attempts resolution within guardrails
- If blocked → @mention another agent or escalate to human
- P1 incidents → all relevant agents auto-notified
Heartbeat Schedule
Agents wake on staggered 5-minute intervals:
*/5 * * * * Atlas (Cluster Ops - needs fast response for incidents)
*/5 * * * * Pulse (Observability - needs fast response for alerts)
*/5 * * * * Shield (Security - fast response for CVEs and threats)
*/10 * * * * Flow (GitOps - deployments can wait a few minutes)
*/10 * * * * Cache (Artifacts - promotions are scheduled)
*/15 * * * * Desk (DevEx - developer requests aren't usually urgent)
*/15 * * * * Orchestrator (Coordination - overview and standups)
Key Principles
- Roles over genericism — Each agent has a defined SOUL with exactly who they are
- Files over mental notes — Only files persist between sessions
- Staggered schedules — Don't wake all agents at once
- Shared context — One source of truth for tasks and communication
- Heartbeat, not always-on — Balance responsiveness with cost
- Human-in-the-loop — Critical actions require approval
- Guardrails over freedom — Define what agents can and cannot do
- Audit everything — Every action logged to activity feed
- Reliability first — System stability always wins over new features
- Security by default — Deny access, approve by exception
Detailed Agent Capabilities
Orchestrator (Jarvis)
- Task routing: determining which agent should handle which request
- Workflow orchestration: coordinating multi-agent operations
- Daily standups: compiling swarm-wide status reports
- Priority management: determining urgency and sequencing of work
- Cross-agent communication: facilitating collaboration
- Accountability: tracking what was promised vs what was delivered
Cluster Ops (Atlas)
- OpenShift/Kubernetes cluster operations (upgrades, scaling, patching)
- Node pool management and autoscaling
- Resource quota management and capacity planning
- Network troubleshooting (OVN-Kubernetes, Cilium, Calico)
- Storage class management and PVC/CSI issues
- etcd backup, restore, and health monitoring
- Multi-platform expertise (OCP, EKS, AKS, GKE, ROSA, ARO)
GitOps (Flow)
- ArgoCD application management (sync, rollback, sync waves, hooks)
- Helm chart development, debugging, and templating
- Kustomize overlays and patch generation
- ApplicationSet templates for multi-cluster deployments
- Deployment strategy management (canary, blue-green, rolling)
- Git repository management and branching strategies
- Drift detection and remediation
- Secrets management integration (Vault, Sealed Secrets, External Secrets)
Security (Shield)
- RBAC audit and management
- NetworkPolicy review and enforcement
- Security policy validation (OPA, Kyverno)
- Vulnerability scanning (image scanning, CVE triage)
- Secret rotation workflows
- Security incident investigation
- Compliance reporting
Observability (Pulse)
- Prometheus/Grafana metric queries
- Log aggregation and search (Loki, Elasticsearch)
- Alert triage and investigation
- SLO tracking and error budget monitoring
- Incident response coordination
- Dashboards and visualization
- Telemetry pipeline troubleshooting
Artifacts (Cache)
- Container registry management
- Image scanning and CVE analysis
- SBOM generation and tracking
- Artifact promotion workflows
- Version management
- Registry caching and proxying
Developer Experience (Desk)
- Namespace provisioning
- Resource quota and limit range management
- Developer onboarding
- Template generation
- Developer support and troubleshooting
- Documentation generation
File Structure
cluster-agent-swarm-skills/
├── SKILL.md # This file - combined swarm
├── AGENTS.md # Swarm configuration and protocols
├── skills/
│ ├── orchestrator/ # Jarvis - task routing
│ │ └── SKILL.md
│ ├── cluster-ops/ # Atlas - cluster operations
│ │ └── SKILL.md
│ ├── gitops/ # Flow - GitOps
│ │ └── SKILL.md
│ ├── security/ # Shield - security
│ │ └── SKILL.md
│ ├── observability/ # Pulse - monitoring
│ │ └── SKILL.md
│ ├── artifacts/ # Cache - artifacts
│ │ └── SKILL.md
│ └── developer-experience/ # Desk - DevEx
│ └── SKILL.md
├── scripts/ # Shared scripts
└── references/ # Shared documentation
Reference Documentation
For detailed capabilities of each agent, refer to individual SKILL.md files:
skills/orchestrator/SKILL.md - Full Orchestrator documentation
skills/cluster-ops/SKILL.md - Full Cluster Ops documentation
skills/gitops/SKILL.md - Full GitOps documentation
skills/security/SKILL.md - Full Security documentation
skills/observability/SKILL.md - Full Observability documentation
skills/artifacts/SKILL.md - Full Artifacts documentation
skills/developer-experience/SKILL.md - Full Developer Experience documentation
1---2name: cluster-agent-swarm-23description: "Complete Platform Agent Swarm — A coordinated multi-agent system for Kubernetes and OpenShift platform operations. Includes Orchestrator (Jarvis), Cluster Ops (Atlas), GitOps (Flow), Security (Shield), Observability (Pulse), Artifacts (Cache), and Developer Experience (Desk)."4metadata:5 source: https://skillmd.com/skills/dvcrn/cluster-agent-swarm-26---78# Cluster Agent Swarm — Complete Platform Operations910This is the complete cluster-agent-swarm skill package. When you add this skill, you get 11access to ALL 7 specialized agents working together as a coordinated swarm.1213## Installation Options1415### Install All Skills (Recommended)16```bash17npx skills add https://github.com/kcns008/cluster-agent-swarm-skills18```1920This installs all 7 agents as a single combined skill with access to all capabilities.2122### Install Individual Skills23Each agent can also be installed separately:24```bash25# Orchestrator - Task routing and coordination26npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/orchestrator2728# Cluster Ops - Atlas (cluster operations)29npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/cluster-ops3031# GitOps - Flow (ArgoCD, Helm, Kustomize)32npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/gitops3334# Security - Shield (RBAC, policies, CVEs)35npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/security3637# Observability - Pulse (metrics, alerts, incidents)38npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/observability3940# Artifacts - Cache (registries, SBOM, promotions)41npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/artifacts4243# Developer Experience - Desk (namespaces, onboarding)44npx skills add https://github.com/kcns008/cluster-agent-swarm-skills/skills/developer-experience45```4647---4849## The Swarm — Agent Roster5051| Agent | Code Name | Session Key | Domain |52|-------|-----------|-------------|--------|53| Orchestrator | Jarvis | `agent:platform:orchestrator` | Task routing, coordination, standups |54| Cluster Ops | Atlas | `agent:platform:cluster-ops` | Cluster lifecycle, nodes, upgrades |55| GitOps | Flow | `agent:platform:gitops` | ArgoCD, Helm, Kustomize, deploys |56| Security | Shield | `agent:platform:security` | RBAC, policies, secrets, scanning |57| Observability | Pulse | `agent:platform:observability` | Metrics, logs, alerts, incidents |58| Artifacts | Cache | `agent:platform:artifacts` | Registries, SBOM, promotion, CVEs |59| Developer Experience | Desk | `agent:platform:developer-experience` | Namespaces, onboarding, support |6061---6263## Agent Capabilities Summary6465### What Agents CAN Do66- Read cluster state (`kubectl get`, `kubectl describe`, `oc get`)67- Deploy via GitOps (`argocd app sync`, Flux reconciliation)68- Create documentation and reports69- Investigate and triage incidents70- Provision standard resources (namespaces, quotas, RBAC)71- Run health checks and audits72- Scan images and generate SBOMs73- Query metrics and logs74- Execute pre-approved runbooks7576### What Agents CANNOT Do (Human-in-the-Loop Required)77- Delete production resources (`kubectl delete` in prod)78- Modify cluster-wide policies (NetworkPolicy, OPA, Kyverno cluster policies)79- Make direct changes to secrets without rotation workflow80- Modify network routes or service mesh configuration81- Scale beyond defined resource limits82- Perform irreversible cluster upgrades83- Approve production deployments (can prepare, human approves)84- Change RBAC at cluster-admin level8586---8788## Communication Patterns8990### @Mentions91Agents communicate via @mentions in shared task comments:92```93@Shield Please review the RBAC for payment-service v3.2 before I sync.94@Pulse Is the CPU spike related to the deployment or external traffic?95@Atlas The staging cluster needs 2 more worker nodes.96```9798### Thread Subscriptions99- Commenting on a task → auto-subscribe100- Being @mentioned → auto-subscribe101- Being assigned → auto-subscribe102- Once subscribed → receive ALL future comments on heartbeat103104### Escalation Path1051. Agent detects issue1062. Agent attempts resolution within guardrails1073. If blocked → @mention another agent or escalate to human1084. P1 incidents → all relevant agents auto-notified109110---111112## Heartbeat Schedule113114Agents wake on staggered 5-minute intervals:115```116*/5 * * * * Atlas (Cluster Ops - needs fast response for incidents)117*/5 * * * * Pulse (Observability - needs fast response for alerts)118*/5 * * * * Shield (Security - fast response for CVEs and threats)119*/10 * * * * Flow (GitOps - deployments can wait a few minutes)120*/10 * * * * Cache (Artifacts - promotions are scheduled)121*/15 * * * * Desk (DevEx - developer requests aren't usually urgent)122*/15 * * * * Orchestrator (Coordination - overview and standups)123```124125---126127## Key Principles128129- **Roles over genericism** — Each agent has a defined SOUL with exactly who they are130- **Files over mental notes** — Only files persist between sessions131- **Staggered schedules** — Don't wake all agents at once132- **Shared context** — One source of truth for tasks and communication133- **Heartbeat, not always-on** — Balance responsiveness with cost134- **Human-in-the-loop** — Critical actions require approval135- **Guardrails over freedom** — Define what agents can and cannot do136- **Audit everything** — Every action logged to activity feed137- **Reliability first** — System stability always wins over new features138- **Security by default** — Deny access, approve by exception139140---141142## Detailed Agent Capabilities143144### Orchestrator (Jarvis)145- Task routing: determining which agent should handle which request146- Workflow orchestration: coordinating multi-agent operations147- Daily standups: compiling swarm-wide status reports148- Priority management: determining urgency and sequencing of work149- Cross-agent communication: facilitating collaboration150- Accountability: tracking what was promised vs what was delivered151152### Cluster Ops (Atlas)153- OpenShift/Kubernetes cluster operations (upgrades, scaling, patching)154- Node pool management and autoscaling155- Resource quota management and capacity planning156- Network troubleshooting (OVN-Kubernetes, Cilium, Calico)157- Storage class management and PVC/CSI issues158- etcd backup, restore, and health monitoring159- Multi-platform expertise (OCP, EKS, AKS, GKE, ROSA, ARO)160161### GitOps (Flow)162- ArgoCD application management (sync, rollback, sync waves, hooks)163- Helm chart development, debugging, and templating164- Kustomize overlays and patch generation165- ApplicationSet templates for multi-cluster deployments166- Deployment strategy management (canary, blue-green, rolling)167- Git repository management and branching strategies168- Drift detection and remediation169- Secrets management integration (Vault, Sealed Secrets, External Secrets)170171### Security (Shield)172- RBAC audit and management173- NetworkPolicy review and enforcement174- Security policy validation (OPA, Kyverno)175- Vulnerability scanning (image scanning, CVE triage)176- Secret rotation workflows177- Security incident investigation178- Compliance reporting179180### Observability (Pulse)181- Prometheus/Grafana metric queries182- Log aggregation and search (Loki, Elasticsearch)183- Alert triage and investigation184- SLO tracking and error budget monitoring185- Incident response coordination186- Dashboards and visualization187- Telemetry pipeline troubleshooting188189### Artifacts (Cache)190- Container registry management191- Image scanning and CVE analysis192- SBOM generation and tracking193- Artifact promotion workflows194- Version management195- Registry caching and proxying196197### Developer Experience (Desk)198- Namespace provisioning199- Resource quota and limit range management200- Developer onboarding201- Template generation202- Developer support and troubleshooting203- Documentation generation204205---206207## File Structure208209```210cluster-agent-swarm-skills/211├── SKILL.md # This file - combined swarm212├── AGENTS.md # Swarm configuration and protocols213├── skills/214│ ├── orchestrator/ # Jarvis - task routing215│ │ └── SKILL.md216│ ├── cluster-ops/ # Atlas - cluster operations217│ │ └── SKILL.md218│ ├── gitops/ # Flow - GitOps219│ │ └── SKILL.md220│ ├── security/ # Shield - security221│ │ └── SKILL.md222│ ├── observability/ # Pulse - monitoring223│ │ └── SKILL.md224│ ├── artifacts/ # Cache - artifacts225│ │ └── SKILL.md226│ └── developer-experience/ # Desk - DevEx227│ └── SKILL.md228├── scripts/ # Shared scripts229└── references/ # Shared documentation230```231232---233234## Reference Documentation235236For detailed capabilities of each agent, refer to individual SKILL.md files:237- `skills/orchestrator/SKILL.md` - Full Orchestrator documentation238- `skills/cluster-ops/SKILL.md` - Full Cluster Ops documentation239- `skills/gitops/SKILL.md` - Full GitOps documentation240- `skills/security/SKILL.md` - Full Security documentation241- `skills/observability/SKILL.md` - Full Observability documentation242- `skills/artifacts/SKILL.md` - Full Artifacts documentation243- `skills/developer-experience/SKILL.md` - Full Developer Experience documentation