An Azure infrastructure governance add-on for reviewing and managing cloud setups built with Bicep, Microsoft's language for defining Azure resources as code. It covers areas such as security, naming, monitoring, disaster recovery, costs, and deployment.

Use it to review Azure infrastructure, identify and fix Bicep or deployment-workflow issues, and plan areas such as AKS, API Management, landing zones, multi-region recovery, and service reliability.

It helps find rule violations and infrastructure problems before they cause security issues, outages, unexpected costs, or unsafe deployments. Live Azure diagnostics are optional.

pilot-azure — Plugin by AgenticPawan

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add AgenticPawan/FullStack-Pilot

agentmods

npx agentmods add plugins/agenticpawan/fullstack-pilot/pilot-azure

Clone the repo

git clone --depth 1 https://github.com/AgenticPawan/FullStack-Pilot

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

pilot-azure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/pilot-azure/.claude-plugin/plugin.json · 54 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "pilot-azure",
  "displayName": "Pilot Azure",
  "version": "0.20.0",
  "dependencies": [
    {
      "name": "pilot-core"
    }
  ],
  "description": "Azure / Bicep / ACA governance: CAF naming, security baseline, Well-Architected review, Bicep patterns, observability, CI/CD security (OIDC), multi-region DR, cost/FinOps, AKS, API Management, landing zones, SLO/error budgets, and container image security. Ships @infra-reviewer (finds violations), @infra-implementor (fixes them), and @infra-support (diagnoses live infrastructure issues; live Azure MCP diagnostics are opt-in via .mcp.json.example)",
  "author": {
    "name": "AgenticPawan",
    "url": "https://github.com/AgenticPawan"
  },
  "homepage": "https://github.com/AgenticPawan/FullStack-Pilot#pilot-azure",
  "repository": "https://github.com/AgenticPawan/FullStack-Pilot",
  "license": "MIT",
  "keywords": [
    "azure",
    "bicep",
    "aca",
    "cost-guardrails",
    "deployment",
    "naming",
    "observability",
    "disaster-recovery",
    "cicd-security",
    "finops",
    "aks",
    "kubernetes",
    "apim",
    "landing-zone",
    "enterprise-scale",
    "slo",
    "error-budget",
    "container-security",
    "image-scanning",
    "signalr-scaleout",
    "storage-dataplane",
    "user-delegation-sas",
    "container-apps",
    "aca",
    "app-service",
    "edge-waf",
    "front-door",
    "web-application-firewall",
    "data-residency",
    "implementor-agent",
    "support-agent",
    "root-cause"
  ]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 54 lines scan A 7c5ccb0d2b15

Subscribe to this mod's changes

pilot-azure is a plugin published in the GitHub repository AgenticPawan/FullStack-Pilot (2 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Code review Security ai-coding-agent ai-coding-agents angular azure claude-code claude-code-marketplace

azure-kusto-graph-skills

Kusto graph analysis, IRQL security hunting pipelines, and graph visualization skills for Azure Data Explorer.

microsoft/skills · not measured

handbook-agent-spec-kit

Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.

NikiforovAll/claude-code-rules · not measured

martinloop

Govern coding-agent work with budgets, stop conditions, and verifier-backed evidence.

Keesan12/martin-loop · not measured

smk

Plugin marketplace listing 13 plugins: cursor-delegate, spring-clean, portal-skills, readable, decode.

smk-labs/claude-plugins · not measured

dmitriy-claude-plugins

Personal collection of Claude Code plugins for development workflows and productivity.

DmitriyYukhanov/claude-plugins · not measured

spring-clean

Two passes over a repo. spring-clean measures against a declared scoreboard, deletes or gitignores what does not belong, relocates dev docs, notes, clones and dumps to a -workspace repo, splits oversized files, draws package boundaries and writes its plan to a numbered unit list that survives a dead context. w.