agentleFS
VincentChuWaiChowVincentChuWaiChow/vanguard-frontier-agentic/agents/AGENTS.md

vanguard-frontier-agentic / agents

AGENTS.md23 starsChanged 4 months agoApache-2.0View on GitHub

Live-guard agents refuse to proceed without: target confirmation (cluster/account/region), current-state evidence (kubectl get … -o yaml / equivalent), and explicit platform-team or operator sign-off. Missing any one is a hard stop. Entry point: load agents/aws/aws-maestro-agent/AGENT.md for any AWS task; it routes to the right specialist and back.

The file

We split this AGENTS.md into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every agent here is static-review.

    line 320
  2. Very specific:

    Run npm run validate after any agent metadata change.

    line 348
  3. Distinctive:

    Never auto-dispatch a live-guard agent from a router or orchestration flow — the human must confirm target + current state first.

    line 349
  4. Very specific:

    Never flatten harness variants into the provider root.

    line 350
  5. Distinctive:

    Start with the domain's maestro (AWS / Azure / OCI / Kubernetes / Terraform).

    line 356
  6. Distinctive:

    Never load a live-guard agent without explicit operator intent.

    line 359

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md — Navigation Compass

<!-- count:global:agents -->735<!-- /count --> agents across <!-- count:global:providers -->45<!-- /count --> providers. This file is the index; load provider files on demand.

File structure

agents/<provider>/<agent-id>/AGENT.md          ← harness-neutral role contract (load this)
agents/<provider>/<agent-id>/harnesses/        ← 7 adapters: codex, copilot, claude-code,
                                                  cursor, gemini, kiro-ide, kiro-cli
agents/<provider>/<agent-id>/metadata.json     ← catalog mirror
catalog/agents.json                            ← machine-readable index of every agent

Agent tiers

Tiersandbox_modeWhen to load
reviewread-onlyAudit, analysis, recommendations — never writes to live systems
router / maestroread-onlyClassifies task → dispatches narrowest specialist(s); never auto-dispatches live-guards
live-guardworkspace-writeApproval-gated mutations; requires current-state capture + explicit sign-off before every write

Live-guard agents refuse to proceed without: target confirmation (cluster/account/region), current-state evidence (kubectl get … -o yaml / equivalent), and explicit platform-team or operator sign-off. Missing any one is a hard stop.


🟧 AWS — <!-- count:dir:aws:agents -->47<!-- /count --> agents → agents/aws/AGENTS.md

Entry point: load agents/aws/aws-maestro-agent/AGENT.md for any AWS task; it routes to the right specialist and back.

CategoryAgentsLoad when
Routeraws-maestro-agentAny AWS task without a known specialist
IAM / identityaws-iam-least-privilege-review-agent, aws-kms-secrets-lifecycle-steward-agent, aws-s3-data-perimeter-governor-agent, aws-compliance-evidence-mapper-agentIAM policy, KMS key policy, S3 perimeter, compliance mapping
Security postureaws-security-posture-hardening-agent, aws-bedrock-agent-security-governor-agentSecurity Hub, GuardDuty, Bedrock agent trust
Compute / EKS / ECSaws-eks-platform-operator-agent, aws-ecs-fargate-platform-operator-agent, aws-ec2-compute-operations-steward-agent, aws-ecs-service-remediation-operator-agentEKS cluster ops, ECS/Fargate service review, EC2 operations
Databasesaws-rds-aurora-performance-investigator-agent, aws-dynamodb-data-modeling-performance-review-agentRDS/Aurora query tuning, DynamoDB data model
Serverlessaws-serverless-production-readiness-agent, aws-serverless-rollout-corrector-agentLambda readiness, canary/alias rollout
Networking / edgeaws-network-architect-agent, aws-api-edge-delivery-review-agentVPC/TGW/DirectConnect, API Gateway + CloudFront + WAF
IaCaws-iac-change-safety-review-agent, aws-iac-patch-executor-agentCDK/CFN/SAM/Terraform review, IaC file patching
Cost / FinOpsaws-cost-optimization-governor-agent, aws-cost-anomaly-watch-coordinator-agentCost Explorer, budget drift
CI/CD / DevOpsaws-ci-cd-release-engineer-agent, aws-devops-agent-skill-designer-agent, aws-pipeline-fix-operator-agent, aws-deployment-hotfix-operator-agentCodePipeline, release gates, hotfix patching
Architectureaws-solution-architect-agent, aws-migration-cutover-architect-agent, aws-resilience-bcdr-review-agent, aws-event-driven-architecture-review-agent, aws-landing-zone-governor-agent, aws-network-architect-agentSolution design, migrations, BCDR, event-driven, Control Tower
AI / Bedrockaws-generative-ai-developer-agent, aws-agentcore-agentBedrock app dev, AgentCore deployment
Ops / observabilityaws-observability-incident-responder-agent, aws-daily-operations-briefing-coordinator-agent, aws-ticket-triage-escalation-coordinator-agent, aws-change-impact-advisor-agent, aws-data-protection-backup-steward-agent, aws-limits-capacity-planner-agent*CloudWatch, incident triage, ops briefing
Live-guard (5)aws-live-deployment-guarded-operator-agent, aws-live-ecs-rollout-guard-agent, aws-live-iac-change-guard-agent, aws-live-pipeline-approval-operator-agent, aws-live-serverless-release-guard-agentApproval-gated live mutations; never auto-dispatched

For operational rules, credential chain guidance, and MCP tool usage → agents/aws/AGENTS.md


🟦 Azure — <!-- count:dir:azure:agents -->36<!-- /count --> agents → agents/azure/AGENTS.md

Entry point: load agents/azure/azure-maestro-agent/AGENT.md for any Azure task.

CategoryAgentsLoad when
Routerazure-maestro-agentAny Azure task without a known specialist
Identity / RBACazure-rbac-review-agent, azure-role-selector-agent, azure-entra-id-specialist-agent, azure-identity-governance-review-agentRole assignments, custom roles, Entra ID posture, identity governance
AKS / containersazure-aks-platform-operator-agentAKS cluster ops, node pool, networking
App Serviceazure-app-service-production-readiness-agentWeb Apps, Function Apps, deployment slots
Databasesazure-cosmosdb-platform-operator-agent, azure-cosmosdb-performance-investigator-agent, azure-cosmosdb-application-developer-agentCosmosDB ops, query perf, app dev patterns
Key Vault / secretsazure-key-vault-secret-lifecycle-auditor-agentSecret rotation, access policy, purge-protection
Cost / FinOpsazure-cost-optimization-governor-agent, azure-cost-estimation-review-agentSpend governance, estimate review
Networkingazure-network-topology-review-agent, azure-private-endpoint-adoption-planner-agentHub-spoke, Private Link, DNS
IaC / governanceazure-governance-policy-guardrails-agent, azure-subscription-resource-organization-agent, azure-landing-zone-architect-agentPolicy, management groups, landing zones
CI/CD / DevOpsazure-platform-automation-devops-agentPipelines, automation, platform DevOps
AI / Foundryazure-ai-foundry-ops-governor-agentAI Foundry, model deployments, governance
Architectureazure-solution-architect-agent*, azure-migrate-landing-zone-cutover-agent, azure-resilience-bcdr-review-agentSolution design, migrations, BCDR
Observability / opsazure-observability-investigator-agent, azure-resource-health-incident-triage-agent, azure-security-posture-hardening-agentMonitor, Log Analytics, incident triage
Live-guard (7)azure-live-aks-rollout-guard-agent, azure-live-app-service-slot-swap-guard-agent, azure-live-arm-deployment-stack-guard-agent, azure-live-cost-budget-action-guard-agent, azure-live-entra-role-assignment-guard-agent, azure-live-keyvault-rotation-purge-guard-agent, azure-live-pim-jit-activation-guard-agentApproval-gated live mutations; never auto-dispatched

For permission models, PIM gate details, and MCP guidance → agents/azure/AGENTS.md


🟥 OCI — <!-- count:dir:oci:agents -->39<!-- /count --> agents → agents/oci/AGENTS.md

Entry point: load agents/oci/oci-maestro-agent/AGENT.md for any OCI task.

CategoryAgentsLoad when
Routeroci-maestro-agentAny OCI task without a known specialist
IAM / identityoci-identity-access-governor-agent, oci-cloud-guard-responder-agentOCI IAM policies, dynamic groups, Cloud Guard
Computeoci-compute-platform-operator-agent, oci-compute-instance-agent-operator-agentInstances, autoscaling, instance agents
Databasesoci-autonomous-database-architect-agent, oci-exadata-platform-architect-agent, oci-database-platform-dba-agent, oci-mysql-heatwave-ai-specialist-agent, oci-goldengate-replication-operator-agent, oci-recovery-service-operator-agent, oci-dbtools-sql-analyst-agentADB, Exadata, DBA ops, HeatWave, GoldenGate, recovery
OKE / containersoci-devops-container-platform-engineer-agentOKE, DevOps pipelines, container registry
Networkingoci-network-architect-agent, oci-load-balancer-traffic-engineer-agentVCN, FastConnect, LBaaS, DRG
Storage / backupoci-storage-backup-steward-agent, oci-registry-artifact-governor-agentObject Storage, backups, OCIR
Cost / FinOpsoci-cost-finops-analyst-agent, oci-limits-capacity-planner-agentCost analysis, limits, quotas
Architectureoci-solution-architect-agent, oci-migration-cutover-architect-agent, oci-multi-cloud-architect-agent, oci-resilience-bcdr-architect-agent*Solution design, migrations, multi-cloud
Observability / supportoci-observability-incident-responder-agent, oci-support-incident-coordinator-agent, oci-resource-search-inventory-analyst-agentMonitoring, support SRs, resource inventory
Specialistoci-security-compliance-reviewer-agent, oci-iot-digital-twin-engineer-agent, oci-fusion-apps-environment-operator-agentSecurity posture, IoT/OIC, Fusion SaaS
Live-guard (7)oci-live-autonomous-db-lifecycle-guard-agent, oci-live-cost-budget-runaway-guard-agent, oci-live-iam-policy-compartment-guard-agent, oci-live-network-security-rule-guard-agent, oci-live-oke-rollout-guard-agent, oci-live-resource-manager-stack-guard-agent, oci-live-vault-key-destruction-guard-agentApproval-gated live mutations; never auto-dispatched

For compartment scoping, Resource Manager rules, and OCI MCP guidance → agents/oci/AGENTS.md


☁️ OVHcloud — <!-- count:dir:ovhcloud:agents -->6<!-- /count --> agents → agents/ovhcloud/README.md

Entry point: load agents/ovhcloud/ovhcloud-maestro-agent/AGENT.md for any OVHcloud task.

CategoryAgentsLoad when
Routerovhcloud-maestro-agentAny OVHcloud task without a known specialist
IAMovhcloud-iam-policy-review-agentIAM policy conditions, identity groups, OAuth2 access
Cost / FinOpsovhcloud-cost-finops-analyst-agentPublic Cloud cost, commitments, idle waste
Kubernetesovhcloud-kubernetes-platform-operator-agentMCK lifecycle, node pools, workload placement
Networkingovhcloud-network-architect-agentvRack design, network isolation, connectivity
Live-guard (1)ovhcloud-live-kms-key-destruction-guard-agentKMS key destruction; approval-gated, never auto-dispatched

Conditional IAM policies (IP, tag, expiration) are unique — always audit policy scope before approval.


🌐 IONOS Cloud — <!-- count:dir:ionos:agents -->6<!-- /count --> agents → agents/ionos/README.md

Entry point: load agents/ionos/ionos-maestro-agent/AGENT.md for any IONOS Cloud task.

CategoryAgentsLoad when
Routerionos-maestro-agentAny IONOS Cloud task without a known specialist
DCD topologyionos-datacenter-designer-reviewer-agentData Center Designer review, multi-AZ placement, blast radius
Complianceionos-security-compliance-reviewer-agentGDPR posture, data residency, encryption audit
Kubernetesionos-kubernetes-platform-operator-agentManaged K8s, node pools, workload placement
Cost / FinOpsionos-cost-optimization-analyst-agentCost analysis, resource utilization
Live-guard (1)ionos-live-database-lifecycle-guard-agentDBaaS failover/scaling/backup; approval-gated

DCD changes have multi-AZ topology blast radius; live-guards must snapshot current state before any mutation.


🇫🇷 Scaleway — <!-- count:dir:scaleway:agents -->6<!-- /count --> agents → agents/scaleway/README.md

Entry point: load agents/scaleway/scaleway-maestro-agent/AGENT.md for any Scaleway task.

CategoryAgentsLoad when
Routerscaleway-maestro-agentAny Scaleway task without a known specialist
IAMscaleway-iam-policy-review-agentIAM bindings, service accounts, API key governance
Kapsule (K8s)scaleway-kapsule-platform-operator-agentManaged K8s readiness, node pools, CNI choice, placement
Cost / FinOpsscaleway-cost-optimizer-agentInstance type review, reserved utilization, rightsizing
Networkingscaleway-network-architect-agentVPC, security groups, placement groups for HA
Live-guard (1)scaleway-live-kapsule-rollout-guard-agentKapsule cluster + node pool mutations; approval-gated

Placement groups orchestrate HA; Kapsule control-plane and CNI choice are immutable post-creation.


🇩🇪 Hetzner Cloud — <!-- count:dir:hetzner:agents -->6<!-- /count --> agents → agents/hetzner/README.md

Entry point: load agents/hetzner/hetzner-maestro-agent/AGENT.md for any Hetzner Cloud task.

CategoryAgentsLoad when
Routerhetzner-maestro-agentAny Hetzner Cloud task without a known specialist
Cost / FinOpshetzner-cost-optimization-analyst-agentInstance type review, resource utilization, cost savings
Infra reviewhetzner-infrastructure-reviewer-agentFirewall rules, LB config, network design, public-IP exposure
Capacityhetzner-capacity-planner-agentResource limits, quota, growth planning, region distribution
Live-guard (2)hetzner-live-firewall-rule-guard-agent, hetzner-live-server-lifecycle-guard-agentFirewall rule + server lifecycle mutations; approval-gated

No official Terraform provider — agents recommend REST API / hcloud-python over community Terraform.


💰 Contabo — <!-- count:dir:contabo:agents -->6<!-- /count --> agents → agents/contabo/README.md

Entry point: load agents/contabo/contabo-maestro-agent/AGENT.md for any Contabo task.

CategoryAgentsLoad when
Routercontabo-maestro-agentAny Contabo task without a known specialist
Cost / FinOpscontabo-cost-optimization-analyst-agentContract period analysis, VPS sizing, addon utilization
Capacitycontabo-capacity-planner-agentResource planning, region coverage, instance sizing
Securitycontabo-security-hardening-agentSSH key management, default user policy, firewall posture
Live-guard (2)contabo-live-instance-lifecycle-guard-agent, contabo-live-storage-operations-guard-agentVPS/VDS + Object Storage mutations; approval-gated

Contractual periods (1/3/6/12 months) drive billing; live-guards demand explicit period acknowledgment before any lifecycle change. No official Terraform/SDK — automation via cntb CLI or REST API.


☸️ Kubernetes — <!-- count:dir:kubernetes:agents -->15<!-- /count --> agents → agents/kubernetes/README.md

Entry point: load agents/kubernetes/kubernetes-maestro-agent/AGENT.md — routes to all K8s specialists (including CNCF domain agents below) and enforces the live-guard gate.

AgentTierLoad when
kubernetes-maestro-agentrouterAny Kubernetes task; dispatches to the right specialist(s) in parallel
kubernetes-rbac-review-agentreviewRoles, ClusterRoles, RoleBindings, ClusterRoleBindings, escalation paths
kubernetes-workload-identity-review-agentreviewIRSA, Azure Workload Identity, GKE WI Federation, projected tokens, OIDC trust policy
kubernetes-psa-review-agentreviewPod Security Admission labels, enforce/audit/warn modes, PSP migration
kubernetes-pod-spec-review-agentreviewPod securityContext, capabilities, privileged containers, host network/PID/IPC, readOnly filesystem
external-secrets-operator-review-agentreviewESO SecretStore, ClusterSecretStore, ExternalSecret, PushSecret scope and auth
kubecost-chargeback-allocation-review-agentreviewKubecost label taxonomy, shared cost model, idle allocation, namespace budget alerts
kubernetes-live-rbac-mutation-guard-agentlive-guardkubectl apply/delete on Roles/ClusterRoles/Bindings
kubernetes-live-admission-policy-guard-agentlive-guardkubectl apply/delete on Kyverno ClusterPolicy/Policy/PolicyException, VAP
kubernetes-live-argocd-sync-guard-agentlive-guardargocd sync, AppProject mutations, sync-window changes
kubernetes-live-mesh-policy-guard-agentlive-guardkubectl apply/delete on Istio AuthorizationPolicy, PeerAuthentication
kubernetes-live-network-policy-guard-agentlive-guardkubectl apply/delete on CiliumNetworkPolicy, NetworkPolicy
kubernetes-live-velero-restore-guard-agentlive-guardvelero restore create, backup schedule deletion, backup lifecycle operations

📊 Prometheus — <!-- count:dir:prometheus:agents -->1<!-- /count --> agents → agents/prometheus/README.md

AgentTierLoad when
prometheus-alerting-cardinality-review-agentreviewPromQL alerting rules, recording rules, label cardinality, AlertmanagerConfig routing, inhibition rules

🦅 Falco — <!-- count:dir:falco:agents -->1<!-- /count --> agents → agents/falco/README.md

AgentTierLoad when
falco-runtime-threat-rules-review-agentreviewFalco rules, macros, exception blast radius, K8s audit webhook gaps, SIEM alert routing

🔏 Sigstore — <!-- count:dir:sigstore:agents -->1<!-- /count --> agents → agents/sigstore/README.md

AgentTierLoad when
sigstore-cosign-supply-chain-review-agentreviewCosign signing policy, SBOM attestation, Rekor inclusion, keyless trust root, admission enforcement

🔐 cert-manager — <!-- count:dir:cert-manager:agents -->1<!-- /count --> agents → agents/cert-manager/README.md

AgentTierLoad when
cert-manager-issuer-trust-review-agentreviewClusterIssuer scope, CertificateRequestPolicy auto-approval gap, SAN wildcards, trust-manager bundle blast radius
aws-private-ca-issuer-review-agentreviewAWS Private CA issuer: IRSA trust chain, PCA hierarchy, certificate template scope
azure-keyvault-certificate-issuer-review-agentreviewAzure Key Vault cert issuer: Managed Identity auth, soft-delete, rotation trigger
oci-certificates-issuer-review-agentreviewOCI Certificates Service issuer: instance principal auth, validity duration, revocation policy

🔄 FluxCD — <!-- count:dir:fluxcd:agents -->1<!-- /count --> agents → agents/fluxcd/README.md

AgentTierLoad when
fluxcd-kustomization-helmrelease-review-agentreviewKustomization SA scoping and prune safety, HelmRelease version pinning, SOPS encryption, multi-tenant isolation

🎭 Backstage — <!-- count:dir:backstage:agents -->1<!-- /count --> agents → agents/backstage/README.md

AgentTierLoad when
backstage-scaffolder-template-review-agentreviewScaffolder template action blast-radius, input injection, RBAC gate, secret scope, catalog entity poisoning

💾 Velero — 1 live-guard → agents/velero/README.md

AgentTierLoad when
kubernetes-live-velero-restore-guard-agentlive-guardvelero restore create, backup schedule deletion, backup lifecycle operations

Agent lives in agents/kubernetes/ — dispatched via kubernetes-maestro


🛡️ Kyverno — <!-- count:dir:kyverno:agents -->1<!-- /count --> agents → agents/kyverno/README.md

AgentTierLoad when
kyverno-policy-review-agentreviewClusterPolicy/Policy failureAction, PolicyException scope, background scan, Kyverno-vs-VAP decision

Live mutation of Kyverno policies → kubernetes-live-admission-policy-guard-agent (above)


🔄 Argo CD — <!-- count:dir:argocd:agents -->2<!-- /count --> agents → agents/argocd/README.md

AgentTierLoad when
argocd-gitops-review-agentreviewAppProject blast-radius, sync impersonation, RollingSync, sync-window scope
argo-rollouts-progressive-delivery-review-agentreviewCanary analysis templates, traffic provider wiring, PDB/maxUnavailable deadlock, blue-green autoPromotion

Live ArgoCD mutations → kubernetes-live-argocd-sync-guard-agent (above)


🕸️ Istio — <!-- count:dir:istio:agents -->7<!-- /count --> agents → agents/istio/README.md

AgentTierLoad when
istio-ambient-mesh-review-agentreviewAmbient mesh, ztunnel L4 vs waypoint L7 enforcement, silent-bypass trap, PeerAuthentication, mTLS posture

Live Istio policy mutations → kubernetes-live-mesh-policy-guard-agent (above)


🐝 Cilium — <!-- count:dir:cilium:agents -->1<!-- /count --> agents → agents/cilium/README.md

AgentTierLoad when
cilium-network-policy-review-agentreviewCiliumNetworkPolicy, ClusterMesh trust, 169.254.169.254 egress posture, WireGuard encryption

Live Cilium policy mutations → kubernetes-live-network-policy-guard-agent (above)


📡 OpenTelemetry — <!-- count:dir:opentelemetry:agents -->1<!-- /count --> agents → agents/opentelemetry/README.md

AgentTierLoad when
opentelemetry-collector-config-review-agentreviewCollector pipeline, memory_limiter position, receiver exposure, exporter cardinality, no-exporter silent loss

🟩 Terraform / OpenTofu — <!-- count:dir:terraform:agents -->9<!-- /count --> agents → agents/terraform/README.md

Engine-shared board: one provider covers Terraform and OpenTofu, and every specialist names the engine behind any version-sensitive claim. See docs/terraform-opentofu-boundary.md. Every agent here is static-review; execution always leaves for a cloud live-guard agent after a human gate.

AgentTierLoad when
terraform-maestro-agentrouterAny IaC task; classifies and routes, applying documented thresholds before adding a second specialist
terraform-plan-blast-radius-agentreviewA plan replaces or destroys something; lifecycle ordering, address churn, -target, whether the reviewed plan binds the apply
terraform-state-reliability-agentreviewBackend or locking config, recovery posture, a proposed state mv/state rm/force-unlock, secrets in state, OpenTofu state encryption
terraform-estate-reconciliation-agentreviewDrift disposition, brownfield import, and moved/removed refactors — making the record match reality without destroying anything
terraform-supply-chain-integrity-agentreviewProvider/module source addresses, .terraform.lock.hcl platform coverage, mirrors, dev_overrides, registry provenance
terraform-engine-compatibility-agentreviewCore or provider-major upgrades, deprecation exposure, and the Terraform-versus-OpenTofu decision as a divergence register
terraform-policy-evidence-agentreviewControl mapping, enforcement level (advisory / soft-mandatory / hard-mandatory), exception scope and expiry, audit evidence artifacts
terraform-execution-governance-agentreviewRunner identity and credential lifetime, plan-to-apply binding, plan-artifact handling, approval integrity, trigger surface
terraform-reviewerreviewModule contract review only — input validation, output stability, breaking-change classification, golden paths. Plan, state, policy, and upgrade work belong to the specialists above

💰 FinOps / Multi-cloud — <!-- count:dir:finops:agents -->4<!-- /count --> agents → agents/finops/README.md

AgentTierLoad when
finops-cloud-price-advisor-agentreviewLive public pricing from AWS + Azure + OCI APIs; cost estimation for live or prototype environments

Operational rules

  • Move agents by updating both metadata.json and catalog/agents.json in the same commit.
  • Run npm run validate after any agent metadata change.
  • Never auto-dispatch a live-guard agent from a router or orchestration flow — the human must confirm target + current state first.
  • Never flatten harness variants into the provider root; canonical identity always lives in AGENT.md.
  • IDs are always -agent suffixed to avoid collision with skill IDs.
  • AGENT.md and Markdown harness adapters must be flush-left after frontmatter; indented content renders as code blocks.

Load sequence for multi-domain tasks

  1. Start with the domain's maestro (AWS / Azure / OCI / Kubernetes / Terraform).
  2. Maestro classifies and dispatches ≤4 specialists in parallel.
  3. For Kubernetes tasks spanning mesh + network + admission: load kubernetes-maestro-agent — it holds the full K8s routing table and multi-domain dispatch logic.
  4. Never load a live-guard agent without explicit operator intent; maestros surface the live-guard name but do not call it directly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.