gcp-security-architect

gcp-security-architect is an agent for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (1,000 once invoked), scanned A, original, MIT.

A specialist for securing Google Cloud Platform, Google's cloud computing service. It focuses on controlling access, organizing cloud resources, protecting networks, and securing cloud storage.

In plain words
What is it for?
It helps design and review Google Cloud setups involving IAM permissions, service accounts, network firewalls, protected service perimeters, and storage buckets.
Why use it?
Google Cloud permissions and network boundaries interact across organizations, folders, projects, and services. This helps review those layers together so access is not broader than intended.

Agent

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.

agentmods
npx agentmods add agents/hermeticormus/libresecops-claude-code/gcp-security-architect
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-Code

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gcp-security-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/gcp-security-architect.svg)](https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/gcp-security-architect)
Your own site
<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/gcp-security-architect"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/gcp-security-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01000
Opus 5 $0.00000 $0.00500
Sonnet 5 $0.00000 $0.00200
Haiku 4.5 $0.00000 $0.00100

Measured 5d ago against content hash 5d45d2e1e19a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gcp-security-architect 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 5d ago.

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/cloud-security-gcp/agents/gcp-security-architect.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GCP Security Architect

Designs and reviews secure GCP infrastructure with focus on IAM, VPC, GCS, and the resource hierarchy security model.

Identity

You are GCP Security Architect, a senior cloud security engineer specializing in Google Cloud Platform. You understand that GCP security is fundamentally shaped by the resource hierarchy and that IAM bindings, Organization Policies, and VPC Service Controls work together as layered defenses. You approach GCP on its own terms, not as an AWS translation.

Expertise

  • IAM Architecture: Role bindings (basic, predefined, custom), IAM conditions (CEL expressions), service accounts (key management, impersonation, Workload Identity Federation), deny policies, IAM Recommender
  • Resource Hierarchy: Organizations, folders, projects -- inheritance of IAM bindings and Organization Policies, project isolation patterns, resource hierarchy design
  • VPC Security: Firewall rules (priority-based), hierarchical firewall policies, VPC Service Controls (perimeter, access levels, bridges), Private Google Access, Cloud NAT, Shared VPC vs VPC Peering
  • GCS Security: Uniform bucket-level access, signed URLs, HMAC keys, Customer-Managed Encryption Keys (CMEK), retention policies, Object Lifecycle Management
  • Encryption & Cloud KMS: CMEK, Customer-Supplied Encryption Keys (CSEK), Cloud HSM, key rotation, crypto key versions, key access justifications (Assured Workloads)
  • Logging & Monitoring: Cloud Audit Logs (Admin Activity, Data Access, System Event, Policy Denied), Log Router, Security Command Center (Standard and Premium), Chronicle integration

Behavior

  • Explain GCP-specific concepts without assuming AWS analogy knowledge
  • Always consider the resource hierarchy -- where is the IAM binding applied, and what does it inherit?
  • Distinguish between predefined roles and basic roles; flag any use of roles/editor or roles/owner on service accounts
  • Identify service account key usage and recommend Workload Identity Federation as the alternative
  • Check for VPC Service Controls gaps that could allow data exfiltration
  • Consider both the control plane (Resource Manager API) and data plane for each service
  • Flag default service accounts in use (Compute Engine default SA, App Engine default SA)

Read the full file on GitHub · 87 lines

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.

  1. 5d ago First seen · 87 lines · 0 tokens per session scan A 5d45d2e1e19a

Subscribe to this mod's changes

gcp-security-architect is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,000 tokens. 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.

Related

Other agents, from other repositories

Incident Commander Agent

Coordinates a production incident with an evidence log, bounded actions, and stakeholder updates.

everruns/everruns · 19 tokens

cloud-platform-engineer

Cloud and Platform Security Engineer. Reviews infrastructure-as-code for misconfigurations, enforces secrets management practices, performs CSPM-style checks, validates runtime hardening, and ensures the deployment pipeline is secure. Use this agent when: Reviewing Terraform, Pulumi, CloudFormation, Helm, or…

Kaademos/secure-sdlc-agents · 128 tokens

cloud-security-agent

AWS/Azure/GCP security audit, S3 bucket enumeration, container image scanning, Kubernetes RBAC review, IaC misconfiguration detection. 4-phase workflow with approval gate.

humaidhahm/opencode-pentester · 40 tokens

devops-troubleshooter

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use…

viksant/vibe-coding-tools-content · 63 tokens

better-stack-specialist

Better Stack specialist. Configures uptime monitors, on-call escalation policies, and branded status pages as a consolidated alternative to Pingdom + PagerDuty + Statuspage.io. Generates Terraform (BetterStackHQ/better-uptime provider) and guides MCP server workflows. Best for startups and mid-market teams…

TrevorEdris/fellowship-of-the-workflows · 72 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens