Vanguard Frontier Agentic

The vanguard frontier of the agentic world — an enterprise-grade ecosystem for AI agents at scale.

Agentic coordination, routing, protocol, and escalation for high-stakes environments. Battle-hardened. Audit-ready by design.

Why Vanguard Frontier  ·  What's Inside  ·  Get Started  ·  Install Reference  ·  Skills  ·  Agents  ·  Issues  ·  FAQ  ·  Feedback  ·  Contributing  ·  Security  ·  Code of Conduct

This is the edge of agentic intelligence — an enterprise-grade ecosystem for running AI agents at scale in environments where a wrong move is a board-level incident. It collects reusable skills, agents, rules, MCP references, and supporting assets for AWS, Azure, OCI, GCP, Alibaba Cloud, Huawei Cloud, Kubernetes, and Terraform — plus cross-functional Legal, HR, Marketing, Salesforce, .NET, FinOps, Accounting, Finance, Oracle NetSuite ERP, Microsoft 365 / Dynamics 365, and Azure-ecosystem Databricks and Snowflake data-platform agentic ecosystems.

This is not just cloud infrastructure tooling. It is agentic coordination: maestro routing, escalation-aware protocol, structured handoff between specialists, and refusal-by-default safety on every irreversible action. Cloud is one domain it operates in. Coordination, governance, and escalation are the product.

📊 Catalog at a glance

• 🧠 Skills = step-by-step workflows an AI assistant can follow.
• 🤖 Agents = reusable expert roles for review, architecture, and operations.
• 📏 Rules = durable instructions for a specific AI harness.
• 🔌 MCP references = trusted notes for connecting tools to real systems.
• 🗂️ Catalogs = machine-readable indexes so tools can discover everything.

Works with: Claude Code  ·  Codex  ·  GitHub Copilot  ·  Cursor  ·  Gemini CLI  ·  Kiro  ·  and any other coding agent.

📦 Available on npm: @raishin/vanguard-frontier-agentic is published on the public npm registry.

⚠️ ALPHA FINOPS BUNDLE: As of v1.8.0, this package includes 4 new experimental FinOps agents and 7 skills for cloud cost optimization, AI economics modeling, Kubernetes rightsizing, and FOCUS-spec normalization. All are marked lifecycle: experimental. See the board readiness memo for known limitations, risk mitigation, and 30-day diligence closure requirements. Use at your own risk in pre-production environments. Production deployment requires signed design-partner SOWs, Big 4 accounting validation, and SOC 2 Type II observation (≥150 days).

🛰️ Why Vanguard Frontier?

"Vanguard frontier" is not branding — it is an operating posture. This ecosystem is built for the front line of agentic deployment, where AI agents touch real production systems, real regulated data, and real legal exposure.

• 🏛️ Built for Fortune 50 / high-stakes environments. Every agent assumes the blast radius is enterprise-scale: regulated data, audited controls, and decisions that survive legal discovery. Refusal-by-default beats a fast path to a board-level incident.
• ⚖️ The Legal + HR ecosystem is proof of cross-functional agentic coordination. 28 specialist agents (Legal maestro + 12 specialists, HR maestro + 14 specialists) and 3 cross-functional protocol skills demonstrate that agents can hand off, escalate, and coordinate across organizational boundaries — not just answer in isolation.
• 🧾 Audit-ready, privacy-preserving, escalation-aware by design. Every review and live-guard agent emits a structured verdict (verdict, evidence_level, blockers, safe_next_actions, open_questions) that maps directly to SOC 2, PCI DSS, NIS2, NIST CSF, and ISO 27001 — no post-processing.
• 🛡️ Battle-tested against real compliance, governance, and risk workflows. These patterns are exercised against live IAM mutations, KMS destruction, litigation holds, RIF planning, and privacy reviews — the workflows where a generic agent gets an organization sued.

The bar: an auditor, a regulator, or opposing counsel should be able to read the agent's output and trace exactly who decided what, on what evidence, and who approved the risk.

🧱 What's Inside — the three-layer agentic architecture

Vanguard Frontier is not a flat bag of prompts. It is a deliberate three-layer system, and every domain — cloud providers, Kubernetes, marketing, Legal, HR — follows the same shape.

How it flows: a request enters at the maestro, which routes to a specialist. When a matter crosses a boundary — an HR investigation that needs privileged Legal review, or a Legal hold that triggers an HR data freeze — the cross-functional protocol carries a structured case capsule between agents, preserving privilege, minimizing data, and recording the escalation path.

This is what "agentic coordination" means here: routing, protocol, and escalation are first-class, not improvised.

🚀 Get Started

Pick the install path for your coding agent. Each dropdown is crystal-clear, step-by-step, and one-click plug-and-play where the harness supports it; the npm/export path works for everything else.

At a glance — which path is yours:

Expand the matching dropdown below for the full step-by-step.

/plugin marketplace add Raishin/vanguard-frontier-agentic
/plugin install vanguard-frontier-agentic@vanguard-frontier-agentic

{
  "extraKnownMarketplaces": {
    "vanguard-frontier-agentic": {
      "source": { "source": "github", "repo": "Raishin/vanguard-frontier-agentic" }
    }
  },
  "enabledPlugins": {
    "vanguard-frontier-agentic@vanguard-frontier-agentic": true
  }
}

# Add the marketplace, then install
copilot plugin marketplace add Raishin/vanguard-frontier-agentic
/plugin install vanguard-frontier-agentic

{
  "extraKnownMarketplaces": [
    "https://raw.githubusercontent.com/Raishin/vanguard-frontier-agentic/master/.github/plugin/marketplace.json"
  ]
}

# Clone the repo, then register it as a plugin directory in Cursor:
git clone https://github.com/Raishin/vanguard-frontier-agentic

vscode.cursor.plugins.registerPath("/absolute/path/to/vanguard-frontier-agentic");

# 1. Clone this repo
git clone https://github.com/Raishin/vanguard-frontier-agentic
cd vanguard-frontier-agentic

# 2. In Kiro:
#    Open the Powers panel → "Add Custom Power" → "Local Directory"
#    Paste the absolute path to the Power(s) you need, one at a time:
#       /absolute/path/to/vanguard-frontier-agentic/powers/vanguard-aws
#       /absolute/path/to/vanguard-frontier-agentic/powers/vanguard-kubernetes
#       /absolute/path/to/vanguard-frontier-agentic/powers/vanguard-terraform

# Install the package
npm install @raishin/vanguard-frontier-agentic@latest

# Export agents + companion skills for Gemini Antigravity
npx vfa-export-agents --platform gemini --all --repo .

npx vfa-export-agents --platform gemini --provider aws --repo .

# Add the marketplace, then enable the bundled plugin
codex plugin marketplace add Raishin/vanguard-frontier-agentic
/plugin install vanguard-frontier-agentic@vanguard-frontier-agentic

[marketplaces.vanguard-frontier-agentic]
last_updated = "2026-05-11T06:46:00Z"
last_revision = "<sha>"
source_type = "git"
source = "https://github.com/Raishin/vanguard-frontier-agentic.git"

[plugins."vanguard-frontier-agentic@vanguard-frontier-agentic"]
enabled = true

# 1️⃣ Install the package
npm install @raishin/vanguard-frontier-agentic@latest

# 2️⃣ Export agents for your role into your repo (claude-code shown — swap platform)
npx vfa-export-agents --platform claude-code --role cloud-security-engineer --repo .

# 3️⃣ Open your coding agent and reference the exported agent
#    "Use kubernetes-rbac-review-agent to audit this RBAC change."

Install paths

There are now eight supported install paths — Claude Code plugin marketplace, GitHub Copilot CLI marketplace, Cursor plugin, Codex plugin marketplace, Kiro Powers, Gemini Antigravity skills, npm package + vfa-export-agents CLI, and the third-party skills CLI — each with different versioning, trust, and scope characteristics. See docs/integrations/skills-cli.md for the full trust matrix, verified flag syntax, pinning guidance, and pre-install inspection steps.

npm install @raishin/vanguard-frontier-agentic@latest

🖥️ Terminal UI (vfa-tui)

⚠️ Alpha — the TUI is functional but under active development.

Crates.io

An enterprise-grade terminal interface for interactive catalog browsing, validation gate execution, and export command building — built in Rust for speed and security by construction. Distributed as the vfa-tui crate.

Install (recommended — from crates.io):

cargo install vfa-tui

Or download a prebuilt binary (Linux / macOS / Windows, x86-64 + arm64) — each release attaches the binaries alongside their SBOM and checksums.sha256 — from the latest vfa-tui release.

Build from source (alternative):

cd tools/vfa-tui && cargo build --release

Run (from the repo root — auto-detects workspace):

vfa-tui                                      # installed via cargo or prebuilt binary
./tools/vfa-tui/target/release/vfa-tui       # from a source build

Key features:

• 🗂️ Catalog browsing with fuzzy search across all agents, skills, and providers
• ✅ Validation gate execution with real-time progress and structured output
• 📦 Export command builder with platform/role/provider selection
• 🔐 Security by construction — no shell injection, no credential handling, no network access

Full documentation

🧠 Skills

617 skills across AWS, Azure, OCI, GCP, Alibaba Cloud, Huawei Cloud, Kubernetes, CNCF ecosystem, Terraform, marketing governance, and more.

🛡️ Live Guard skills — stop before you break prod

Live-guard skills enforce approval gates and rollback posture for irreversible operations:

🟧 AWS (5):

• aws-live-deployment-guarded-operator — approval-gated generic live deployment actions with account/region confirmation
• aws-live-iac-change-guard — CloudFormation/SAM/CDK/Terraform change set + drift + rollback posture enforcement
• aws-live-pipeline-approval-operator — CodePipeline approval gating with exact stage and approver scope
• aws-live-serverless-release-guard — Lambda alias/canary/linear rollout with alarm + rollback required
• aws-live-ecs-rollout-guard — ECS/Fargate deployment circuit breaker, health check evidence, rollback path

🟩 GCP (6):

• gcp-live-gke-rollout-guard — GKE deployment and node pool mutations, control-plane version gating
• gcp-live-iam-policy-change-guard — IAM binding mutations, org policy changes, SA key creation — org-wide blast radius
• gcp-live-kms-key-destruction-guard — Cloud KMS key version destruction — CMEK data permanently unrecoverable
• gcp-live-cost-budget-action-guard — budget thresholds, CUD commitments, quota increases — financial authority gate
• gcp-live-bigquery-dataset-deletion-guard — dataset deletion, table truncation, authorized view changes — irreversible data loss
• gcp-live-cloud-run-traffic-migration-guard — Cloud Run revision traffic shifts, min-instances changes — production traffic blast radius

🟠 Alibaba Cloud (6):

• alibaba-live-ack-rollout-guard — ACK deployment mutations, node pool scaling, cluster version upgrades
• alibaba-live-ram-policy-change-guard — RAM policy/role mutations — account-wide blast radius, privilege escalation risk
• alibaba-live-kms-key-mutation-guard — KMS key deletion/disable — encrypted data permanently inaccessible
• alibaba-live-cost-budget-action-guard — budget threshold changes, Savings Plan purchases, RI commitments — financial authority gate
• alibaba-live-oss-bucket-policy-guard — OSS bucket ACL/policy changes — public exposure or China data-residency violation
• alibaba-live-rds-polardb-mutation-guard — RDS/PolarDB instance deletion, spec downgrade, backup policy removal — data loss risk

🔴 Huawei Cloud (6):

• huawei-live-cce-rollout-guard — CCE deployment mutations, node pool upgrades, cluster version changes
• huawei-live-iam-policy-change-guard — IAM policy/SCP mutations — account-wide blast radius, privilege escalation
• huawei-live-kms-key-destruction-guard — DEW/KMS key deletion — CSMS secrets and DBSS-encrypted data permanently lost
• huawei-live-cost-budget-action-guard — budget threshold changes, RI purchases, CUD commitments — financial authority gate
• huawei-live-obs-bucket-policy-guard — OBS bucket ACL/policy changes — public exposure or data residency violation
• huawei-live-gaussdb-mutation-guard — GaussDB/RDS instance deletion, spec downgrade, backup policy changes — data loss

🟦 Azure (7):

• azure-live-aks-rollout-guard — PDB audit, rollout pause/undo, post-rollout health
• azure-live-arm-deployment-stack-guard — what-if evidence, denySettings, PIM-gated delete
• azure-live-app-service-slot-swap-guard — sticky-setting audit, traffic shifting, swap-back path
• azure-live-keyvault-rotation-purge-guard — rotation policy, soft-delete/purge-protection, PIM gate
• azure-live-pim-jit-activation-guard — eligible assignment audit, MFA gate, JIT revocation
• azure-live-cost-budget-action-guard — budget mutation, GPU SKU policy, quota read-only
• azure-live-entra-role-assignment-guard — permanent role assignment scope/principal audit, PIM-preference enforcement, Guest principal blocking

🟥 OCI (7):

• oci-live-autonomous-db-lifecycle-guard — ADB scale/stop/clone/terminate with tag enforcement
• oci-live-oke-rollout-guard — DevOps pipeline approval, PDB audit, rollout pause/undo
• oci-live-resource-manager-stack-guard — plan-before-apply, drift detection, job-lock enforcement
• oci-live-vault-key-destruction-guard — rotation vs. destruction separation, 7–30 day deletion window
• oci-live-iam-policy-compartment-guard — MFA break-glass, dual-approval for tenancy-root changes
• oci-live-cost-budget-runaway-guard — 3-tier budget management, GPU shape gate, ONS alert routing
• oci-live-network-security-rule-guard — Security List/NSG rule capture, 0.0.0.0/0 detection, DB-subnet criticality, Path Analyzer gate

☸️ Kubernetes (5):

• kubernetes-live-rbac-mutation-guard — escalate/bind/impersonate verb detection, wildcard blocking, pre-mutation state capture, rollback via YAML backup
• kubernetes-live-admission-policy-guard — Kyverno/VAP mutation blast-radius, failureAction enforcement, PolicyException scope validation
• kubernetes-live-mesh-policy-guard — Istio AuthorizationPolicy/PeerAuthentication traffic impact, PERMISSIVE→STRICT migration gating
• kubernetes-live-network-policy-guard — CiliumNetworkPolicy/NetworkPolicy connectivity impact, metadata service egress blocking
• kubernetes-live-argocd-sync-guard — AppProject blast-radius, sync impersonation identity review, sync-window change gating

Sample skills

• 🔐 skills/aws/aws-iam-least-privilege-review — Review AWS IAM policies and reduce unnecessary access.
• 🟦 skills/azure/azure-rbac-review — Review Azure RBAC assignments, scopes, and custom roles.
• 🟥 skills/oci/oci-autonomous-database-architect — Design and review Oracle Autonomous Database across OCI and multicloud options.
• 🟩 skills/gcp/gcp-gke-platform-operator — GKE Standard/Autopilot design with Day-0/Day-1 decisions, Workload Identity, and AI inference quickstart.
• 🟠 skills/alibaba/alibaba-china-compliance — MLPS 2.0, DSL, PIPL, and ICP filing compliance review for workloads in Alibaba Cloud China regions.
• 🔴 skills/huawei/huawei-secmaster-security-operations — Huawei SecMaster SIEM/SOAR, HSS, CFW, WAF posture hardening and incident triage.
• 💰 skills/finops/finops-cloud-price-advisor — Fetch live prices from AWS, Azure, and OCI public pricing APIs; estimate costs for live environments or prototypes.
• 📣 skills/marketing/marketing-pixel-data-leakage-review — Review advertising pixels and event tracking for PII/PHI leakage to ad networks.

Rule of thumb: if the asset teaches how to do a repeatable task, it is a skill.

🤖 Agents

594 agents matching the skill catalog — agents ship harness adapters and a hardened permission model.

⚖️ The Legal + HR cross-functional agentic ecosystem

Beyond cloud and platform agents, Vanguard Frontier ships a 28-agent cross-functional Legal + HR ecosystem plus 3 cross-functional protocol skills — proof that agentic coordination works across organizational boundaries, not just inside one cloud account.

Every Legal and HR agent is escalation-aware (knows when a matter must go to privileged counsel or a human owner), privacy-preserving (minimizes personal and sensitive data in every handoff), and audit-ready (emits the same structured verdict shape as the cloud live-guard agents). These agents advise on process and risk posture — they do not replace licensed legal counsel or qualified HR professionals, and they say so.

🟣 The .NET application review board

.NET is a free, cross-platform, open-source developer platform — runtime, libraries, and languages (C# is the most popular) — with ASP.NET Core as its lean, modular framework for modern cloud-based web services and EF Core as its lightweight, extensible data-access layer. The board is a dotnet-maestro router plus nine static-review specialists covering C#/runtime correctness, ASP.NET Core API architecture, identity and authorization, EF Core data access, test quality, CI/NuGet supply chain, performance/AOT/trimming, in-app OpenTelemetry wiring, and .NET Aspire cloud-native readiness — every agent reads source and sanitized configuration only and never builds, runs, migrates, or contacts a live system. These agents use provider: generic with a dotnet- ID prefix because .NET is a language/runtime, not a cloud provider — mirroring the existing non-cloud boards.

Ⓜ️ The Microsoft 365 / Dynamics 365 board

A maestro-routed board for the Microsoft business cloud (M365, Dynamics 365, Power Platform, and Copilot) — the SaaS surface, distinct from Azure infrastructure. A top-level microsoft-maestro routes to four sub-maestros (m365, d365, power-platform, copilot-governance) and refuses Azure-IaaS / cross-cloud work, deflecting it to the Azure/AWS/GCP maestros. Under them sit 31 static-review specialists + 2 read-only-runtime live-guards (Phase A) + 2 mutating-runtime live-guards (Phase B) organized into categories:

• M365 — identity & Copilot: Entra Conditional Access / Zero Trust and Microsoft 365 Copilot readiness & data-exposure governance (the Copilot Zero Trust 7-layer / oversharing model).
• Power Platform & Copilot Studio: environment + DLP + Dataverse security, ALM pipelines, automation (Power Automate) risk review, and Copilot Studio agent governance / ALM.
• Analytics: Microsoft Fabric / Power BI semantic-model trust, RLS/OLS, and workspace governance.
• Dynamics 365: Success by Design implementation governance, Finance & Operations segregation-of-duties, data migration & cutover, finance close-to-report, supply chain plan-to-produce, field service-to-cash, customer service & contact center, sales revenue operations, and license-to-value realization.

Static-review agents produce no tenant mutations; every verdict requires explicit human approval. The board also ships Phase A read-only-runtime live-guards (m365-live-identity-posture-guard-agent, d365-live-security-role-guard-agent) that read live tenant state without writing, and Phase B mutating-runtime live-guards (d365-live-record-field-update-guard-agent, m365-live-sensitivity-label-apply-guard-agent) that execute exactly one controlled WRITE operation (a named Dataverse field PATCH or a Graph sensitivity-label assignment to one driveItem) only after a written approval token, PREFLIGHT dry-run, and inverse-rollback path are confirmed — bulk edits, DELETE, ownerid/security-role fields, label-policy writes, and broad directory permissions are unconditionally denied. The board is grounded on Microsoft Learn and ships alongside 15 cross-functional protocol skills (provider: generic, recommendation-only) that orchestrate it across business processes — lead-to-cash, procure-to-pay, close-to-report, copilot-data-readiness, erp-crm-cutover, identity-to-data-access, and more.

Every agent ships:

• 📄 AGENT.md — harness-neutral contract with guarded response shape
• 🗂️ metadata.json — schema-validated catalog entry
• 🔌 Harness adapters — claude-code + codex (EU providers); all 7 adapters for established providers

agents/
├── accounting/       (14 agents — maestro + corporate accounting specialists: revenue recognition (ASC 606/IFRS 15), close cycle, consolidation/intercompany, fixed assets, lease accounting (ASC 842), hedge accounting, FX translation, tax provision, payroll, procure-to-pay, equity compensation, indirect tax/e-invoicing, business combinations — all advisory, no ledger writes)
├── alibaba/          (43 agents — advisory, live-guard operators, maestro)
├── argocd/           (2 agents — GitOps review, live sync guard)
├── aws/              (47 agents — advisory, execution, live-guard operators)
├── azure/            (36 agents — advisory, live-guard operators)
├── backstage/        (1 agent — IDP scaffolder review)
├── cert-manager/     (1 agent — PKI certificate lifecycle review)
├── cilium/           (1 agent — network policy review)
├── contabo/          (6 agents — advisory, live instance + storage guards, maestro)
├── databricks/       (3 agents — Azure Databricks: Unity Catalog governance + lakehouse engineering — static review, -at-azure; + Unity Catalog schema-scoped grant guard — mutating-runtime live-guard, Phase B)
├── dotnet/           (10 agents — C#/runtime, ASP.NET Core, EF Core, testing, NuGet supply chain, performance/AOT, OpenTelemetry, Aspire — maestro + 9 specialists)
├── falco/            (1 agent — runtime threat detection review)
├── finance/          (8 agents — maestro + corporate finance specialists: variance analysis, FP&A forecasting, treasury/liquidity, working capital, debt/capital structure, capital allocation, transfer pricing/Pillar Two — all advisory, no ERP writes)
├── finops/           (4 agents — cross-cloud price advisor + experimental cost/economics agents)
├── fluxcd/           (1 agent — GitOps Kustomization/HelmRelease review)
├── frontend/         (35 agents — React/Next.js/Angular/Vue/Svelte specialists, web-platform + cross-cutting review roles, board-chair + enterprise red-team + maestro — all static-review, no build/deploy/credentials)
├── gcp/              (51 agents — advisory, live-guard operators, maestro)
├── hetzner/          (6 agents — advisory, live firewall + server lifecycle guards, maestro)
├── hr/               (15 agents — employee relations, investigations, performance, compensation, benefits, recruiting, workforce planning, learning, culture & DEI, analytics, HRIS, termination readiness, maestro)
├── huawei/           (43 agents — advisory, live-guard operators, maestro)
├── ionos/            (6 agents — advisory, live DB lifecycle guard, maestro)
├── istio/            (1 agent — ambient mesh review)
├── kubernetes/       (15 agents — RBAC, workload identity, PSA, pod-spec, ESO, Kubecost, live-guards, maestro)
├── kyverno/          (1 agent — admission policy review)
├── legal/            (13 agents — contract review, employment law, privacy & data protection, regulatory compliance, IP & open source, litigation hold, ethics & investigations, vendor risk, policy governance, public disclosure, counsel review, knowledge management)
├── marketing/        (14 agents — 13 governance review agents + maestro router)
├── microsoft/        (40 agents — Microsoft 365 / Dynamics 365 / Power Platform / Copilot — microsoft maestro + m365/d365/power-platform/copilot-governance sub-maestros, plus 31 static-review specialists: Entra Zero Trust, Copilot readiness, Purview data security & compliance, Defender XDR SecOps, Intune endpoints, Teams collaboration, Exchange/SharePoint information governance, tenant governance, backup/BCDR & data resilience, licensing/EA optimization, Dataverse/DLP security, Power Platform ALM, Power Automate risk, Copilot Studio governance, Fabric/Power BI governance, Fabric data engineering, Fabric analytics engineering, D365 Success by Design, SoD, data migration/cutover, finance, supply chain, field service, customer service, sales, Customer Insights – Journeys, F&O developer/extensions, dual-write integration, Project Operations, Commerce, value realization — all static-review, live-guard-gated; +2 read-only-runtime live-guard agents (Phase A): identity posture, Dataverse security role; +2 mutating-runtime live-guard agents (Phase B): Dataverse record field update guard, sensitivity label apply guard)
├── netsuite/         (25 agents — Oracle NetSuite ERP — maestro router, live-org mutation guard, evidence/release-drift + enterprise-architecture + SOX audit governance, plus 20 domain specialists: financial foundations, SuiteScript secure code review, SDF DevOps, OneWorld multi-subsidiary, identity/RBAC, OAuth/TBA/SSO, AI Connector/MCP, data governance, integration migration, and more — all static-review tier)
├── nvidia/           (12 agents — GPU infrastructure, TensorRT/TensorRT-LLM, Triton serving, NeMo/NIM, agentic AI, NGC supply chain, AI networking, day-2 ops, GPU Operator on Kubernetes, model promotion gatekeeper — maestro + advisory + live-runtime gate)
├── oci/              (39 agents — advisory, live-guard operators)
├── opentelemetry/    (1 agent — collector config review)
├── ovhcloud/         (6 agents — advisory, live KMS guard, maestro)
├── prometheus/       (1 agent — alerting and cardinality review)
├── qa/               (10 agents — Playwright E2E review + execution, flakiness triage, coverage quality, CI pipeline review, PLC control-logic safety, RPA workflow resilience)
├── salesforce/       (30 agents — 20 Wave 1 domain specialists + 10 Wave 3 infrastructure security/DevSecOps agents, maestro router, live-guard authority gate)
├── scaleway/         (6 agents — advisory, live Kapsule rollout guard, maestro)
├── snowflake/        (3 agents — Snowflake on Azure: RBAC governance + data-platform engineering — static review, -at-azure; + RBAC grant guard — mutating-runtime live-guard, Phase B)
├── sigstore/         (1 agent — supply-chain security review)
└── terraform/        (2 agents — IaC review, maestro)

Example:

• 🧱 agents/terraform/terraform-reviewer — Review Terraform modules, plans, provider usage, and state assumptions.

Use an agent when you need a role with judgment, not just a checklist.

📦 Install Reference

Everything you can install, and exactly how to install it. One section, no hunting.

🧭 How to pick what to install

🙋 I know my job function               → use --role
🎯 I know the specific agent I want     → use --agents
☁️  I work on one cloud provider only    → add --provider to either of the above
💥 I want everything for a platform     → use --all
🔍 I don't know what exists yet         → use --list or --list-roles first

🏷️ Argument reference

🖥️ Platform reference

Each platform writes agent files to a different folder in your repo.

ℹ️ The exporter installs agent files only. It does not write repo-level guidance files (CLAUDE.md, AGENTS.md, .github/copilot-instructions.md, etc.). See docs/normalized-platform-matrix.md.

👤 Role reference

A role installs the curated set of agents a practitioner in that job function needs, across all cloud providers. Roles overlap intentionally — one agent may appear in multiple roles.

# 🔍 See exactly which roles exist and how many agents each has
npx vfa-export-agents --list-roles

# 📦 Install a cloud role
npx vfa-export-agents --platform claude-code --role cloud-security-engineer --repo .

# ☁️  Install a cloud role but only for one provider
npx vfa-export-agents --platform claude-code --role cloud-security-engineer --provider azure --repo .

# ☸️  Install a Kubernetes specialist role
npx vfa-export-agents --platform claude-code --role kubernetes-admission-security-engineer --repo .
npx vfa-export-agents --platform claude-code --role kubernetes-network-engineer --repo .

☁️ Provider reference

Use --provider with --role to narrow the install to one cloud.

# 🟥 Install every OCI agent for a cloud-platform-engineer (OCI-only team)
npx vfa-export-agents --platform codex --role cloud-platform-engineer --provider oci --repo .

# 🟦 Install every Azure agent for a cloud-devops-engineer
npx vfa-export-agents --platform copilot --role cloud-devops-engineer --provider azure --repo .

🎯 Common install scenarios

🌍 Vision

Build a practical AI workflow marketplace for secure cloud engineering.

This repository exists for teams that need to design, review, and operate cloud systems where security and compliance are not optional extras.

The north star:

🛡️ Cloud architecture should be zero-trust by default, evidence-backed by design, and understandable by engineers of any seniority.

That means every serious workflow should help engineers answer:

• 👤 Who is accessing what?
• 🔐 Why are they allowed?
• 🧾 Where is the evidence?
• 🚨 How do we detect abuse or drift?
• 🧯 How do we respond and recover?
• 📋 Which compliance obligation does this support?

🧬 Philosophy

This repo is opinionated. That is a feature, not a bug.

1. 🛡️ Zero trust beats implicit trust

Do not trust a network, cloud account, CI runner, agent, workload, or human just because it is "inside" something.

Good assets should push for:

• strong identity,
• least privilege,
• explicit authorization,
• segmentation,
• continuous verification,
• logging and detection,
• short-lived credentials where possible,
• safe rollback paths.

2. 🧾 Compliance needs evidence, not vibes

SOC 2 Type 2, PCI DSS, NIS2, and NIST-style control frameworks are not passed by good intentions. They require repeatable controls and evidence over time.

Good assets should produce or point to evidence:

• policy decisions,
• access reviews,
• architecture diagrams,
• ticket approvals,
• logs and alerts,
• backup and restore tests,
• vulnerability and patch records,
• incident response records,
• change history.

3. 🔐 Least privilege is the default

If a workflow recommends broad admin access, it must explain why.

If it cannot explain why, it should not recommend it.

4. 🧪 Every claim needs a source or a validation path

Cloud behavior changes. Compliance expectations evolve. Vendor services drift.

So assets should clearly separate:

• ✅ verified facts,
• 🧠 engineering judgment,
• ⚠️ assumptions,
• ❓ unknowns.

5. 🧯 Automation must have brakes

AI-assisted automation should not become a fast path to production damage.

Dangerous actions need:

• read-only discovery first,
• explicit approval,
• scoped credentials,
• dry-run or plan mode where possible,
• rollback notes,
• post-change validation.

📋 Compliance compass

This repository is not a compliance product and does not replace auditors, QSAs, legal counsel, or official standards.

It is a control-aware engineering toolbox. The assets should help teams design and collect evidence for common security expectations across frameworks.

Every live-guard and review agent produces a structured verdict response (verdict, evidence_level, blockers, safe_next_actions, open_questions) that maps directly to SOC 2 CC6.1, PCI DSS Req 7, NIS2 Article 21, NIST CSF PR.AC-4, and ISO 27001 A.9.1.1 — no post-processing required. See docs/evidence-output-spec.md for the full control mapping and evidence retention guidance.

Ruthless correction: NIS2 is the European cybersecurity directive. NIST is a U.S. standards body. If someone says "NIST2 European compliance," they probably mean NIS2 or they are mixing two different things.

🏗️ Architecture principles

Use these principles when creating or reviewing assets:

✅ Eval-driven development

This repository uses eval-driven development (EDD) to ensure quality and consistency.

Before implementing any new feature, agents, or skills:

1. Define evals first — What must pass? (capability evals + regression evals)
2. Implement — Build agents, skills, or features
3. Validate — Run the test suite and evals
4. Report — Document results in .claude/evals/<feature>.md

Example: The EU cloud providers feature was built using EDD:

• CE-1 to CE-6: Capability evals (filesystem layout, companion skills, security, schema, docs, content quality)
• CE-7 to CE-8: Post-implementation evals (role-based install coverage, taxonomy/docs updates)
• Regression evals: All 7 validation gates (catalog, skill schema, allowed-tools, agent schema, manifest, links)
• Result: 30 agents + 30 skills across 5 EU providers, all validation gates passing

See the /eval-harness skill for the full EDD framework and docs/CODEMAPS/ for live inventory.

🧭 Quick map

🔌 MCP references

MCP references describe tool/server integrations and their trust boundaries.

Examples:

• 🟧 mcp/official/aws-mcp-servers.md
• 🟦 mcp/official/azure-mcp-server.md
• 🟥 mcp/official/oracle-mcp-servers.md

Important: MCP tools may read or mutate real infrastructure. Treat them like production access, not like harmless documentation links.

✅ Quality bar

This repo is not a prompt junk drawer.

Every cataloged asset should be:

• 🔎 Traceable — includes official docs or clear provenance.
• 🔐 Security-aware — explains access, risk, and least-privilege concerns.
• 🧪 Validated — passes repo checks before being shared.
• 🧭 Scoped — clearly says which provider, domain, and harness it supports.
• 🧯 Safe by default — read-only discovery before mutation; approval before dangerous actions.

Hard no:

• ❌ Secrets or credentials.
• ❌ Vague "do everything" prompts.
• ❌ Unsafe production mutation recipes.
• ❌ Cloud claims with no source or verification path.

For the detailed standard, read docs/quality-bar.md.

🗂️ Metadata contract

Every cataloged asset needs metadata so people and tools can understand it.

Required common fields:

• id
• name
• type: skill, agent, rule, or mcp-reference
• provider: aws, azure, oracle, oci, gcp, kubernetes, terraform, multi-cloud, or generic
• harnesses: one or more of codex, copilot, claude-code, cursor, gemini, kiro, other
• summary
• source_type: original, adapted, or reference-only
• official_docs
• security_notes
• last_verified
• path

🔏 Skill integrity manifests

Skills are executable guidance. Treat them like supply-chain artifacts.

This repo uses catalog/skill-manifest.json to record SHA-256 hashes for every file under every cataloged skill directory.

After intentional skill edits, regenerate the manifest:

npm run manifest:write

Before release or review, check it:

npm run manifest:check

🧪 Validate your changes

Before contributing or sharing changes, run:

npm run validate

Equivalent manual commands:

python tests/validate-catalog.py
python tests/validate-skill-manifest.py
python tests/validate-links.py --offline

If validation fails, fix that first. A broken catalog makes the marketplace harder to trust.

📦 npm publishing and semantic versioning

Use SemVer: MAJOR.MINOR.PATCH.

Read the full policy in docs/release-versioning.md.

🧑‍💻 How to add a new asset

1. 🧭 Pick the right folder — skills/<provider>/, agents/<provider>/, rules/<harness>/, or mcp/official/.
2. 🧱 Start from a template — templates/skill-template or templates/agent-template.
3. 🗂️ Add or update catalog metadata in the matching catalog/*.json file.
4. ✅ Run npm run validate.
5. 🧯 Check safety — no secrets, no broad permissions without justification, no destructive actions without approval gates.

❓ FAQ

Skills vs agents — what's the difference?
A skill teaches your coding agent how to do a task (step-by-step workflow, CLI commands, reference material). An agent gives your coding agent a role with judgment — it loads the skill and adds a guarded response shape, approval gates, and a hardened permission model.

Do I need a cloud account to use these?
For reviewing architecture, writing IaC, or planning — no. For live-guard agents that execute against a real environment — yes, and they will ask you to confirm subscription/tenancy/principal before any mutation.

Can I use a skill or agent without the exporter CLI?
Yes. Copy the harness file for your platform from agents/<provider>/<id>/harnesses/ directly into your repo's agent folder. The CLI just automates that copy.

What is a "live guard" agent?
A live-guard agent operates against a real cloud environment. It enforces approval gates before any mutation, requires preflight evidence (what-if/plan/status output), and treats missing rollback design as a stop condition. Live guards are refusal-by-default — if target identity, approval state, or rollback posture is ambiguous, they stop and say so.

What does the FinOps price advisor actually do?
It fetches live on-demand prices from AWS Price List API, Azure Retail Prices API, and OCI public pricing API — all public, unauthenticated endpoints. It never needs billing credentials. Currency defaults to USD; other currencies are available via Azure's native currencyCode parameter or public exchange rate APIs for AWS/OCI.

Can I contribute new skills or agents?
Yes — see Contributing. The baseline requirement: the asset must be specific, source-backed, security-aware, and validated by npm run validate.

📚 Source anchors

Use official sources when writing security or compliance-sensitive assets:

• 🏛️ NIST SP 800-207 Zero Trust Architecture
• 🧭 NIST Cybersecurity Framework
• 🇪🇺 European Commission: NIS2 Directive
• 🇪🇺 ENISA: NIS Directive 2
• 💳 PCI Security Standards Council Document Library
• 🔵 AICPA SOC 2 Trust Services Criteria

Prefer these over blog posts. Blog posts can help explain, but they are not the source of truth.

💬 Feedback

We value your input — it helps improve this marketplace for the whole community.

• Bugs & feature requests: open an issue — 👍 the ones you want prioritized.
• New skill or agent ideas: describe the use case in an issue and we will review.
• Security concerns: see SECURITY.md for responsible disclosure.

🛡️ Contributing

The default answer to low-trust contributions is no. That is intentional — cloud automation can break real systems.

Good contributions are: useful, specific, auditable, source-backed, safe by default, and friendly for engineers of any seniority.

See:

• CONTRIBUTING.md
• SECURITY.md
• docs/taxonomy.md
• docs/compatibility.md
• docs/marketplace-model.md

Skills  = workflows        🧠   286 across AWS · Azure · OCI · GCP · Alibaba · Huawei · Kubernetes · CNCF · Terraform
Agents  = expert roles     🤖   289 with 7 harness adapters each
Rules   = always-on        📏   harness-specific operating guidance
MCP     = real connections 🔌   AWS · Azure · Oracle official servers
Catalog = searchable index 🗂️   machine-readable, hash-verified

❤️ Sponsors

Why Sponsor

Vanguard Frontier Agentic is a free, open-source marketplace of AI skills and agents for cloud operators — built on 70+ certifications across providers and 3 years of real enterprise architecture work across AWS, Azure, and OCI.

No VC funding. No company backing. One engineer, building in public.

In two weeks on npm: ~900 downloads. Socket.dev scores: Vulnerability 100, Quality 100, License 100. Every release ships through 17 validation gates, adversarial security audits, and property-based fuzz tests.

Your sponsorship directly funds the compute, API time, and research hours that turn new cloud providers, compliance frameworks, and security patterns into production-ready agents — free for everyone.

Current catalog: 594 agents · 617 skills · 40 cloud/platform providers

What Your Sponsorship Funds

Every dollar maps to something concrete:

• → New cloud provider suites — each provider costs ~8–12 hours of research, agent design, security audit, and validation across 17 gates
• → Compliance coverage — GDPR, MLPS 2.0, FedRAMP, ISO 27001, SOC 2 mapped into agent guardrails and live-guard hard-stop conditions
• → Security audit cycles — adversarial multi-persona review, fuzz testing, OWASP / LLM Top 10 validation before every merge
• → New harness support — as AI coding tools evolve, agents stay current across Claude Code, Copilot, Codex, Cursor, Gemini, Kiro
• → Infrastructure — npm publishing, CI/CD, OpenSSF Scorecard, SLSA attestations, SBOM signing on every release

Sponsorship Tiers

☕ Cloud Supporter — $5/month

You believe free cloud tooling matters. Your name in the SPONSORS.md wall of thanks. Every contribution keeps the lights on.

🛡️ Agent Backer — $15/month

You use the agents and want to see them grow.

• Name + link in SPONSORS.md
• Priority response on GitHub Issues you open
• Early access to release notes before they go public

🔧 Provider Sponsor — $50/month

You want a specific cloud or compliance gap closed faster.

• Everything in Agent Backer
• Vote on the next cloud provider or compliance framework to be added to the roadmap
• Your GitHub handle credited in the provider README you helped fund

🏗️ Architecture Patron — $100/month

You run cloud workloads and this saves your team real time.

• Everything in Provider Sponsor
• One dedicated GitHub Discussion per month — ask me anything about cloud architecture, agent design, or compliance strategy
• Logo / link in root README (individual or company)

🌐 Enterprise Tier — $500/month

You want coverage your team can rely on.

• Everything in Architecture Patron
• Direct input on the quarterly roadmap
• Priority build of one cloud provider suite or compliance framework per quarter
• Company logo in root README with featured placement
• Private Slack / Discord channel access for your team

The Honest Version

This project is built in the hours before and after a full-time architecture role. Sponsorship doesn't make me rich — it covers API costs, compute time, and the research hours that keep the catalog growing past what I could sustain alone.

If you've installed the package, opened an agent, or just found value in knowing this exists — thank you. That's already enough.

If you want to accelerate it: https://github.com/sponsors/Raishin

🤝 Community Projects

Projects built on, inspired by, or extending the Vanguard Frontier Agentic marketplace:

⭐ Star History