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.
npx agentmods add agents/ghosteken/agent-harness/senior-cloud-architectgit clone --depth 1 https://github.com/Ghosteken/agent-harnessWrote 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.
[](https://agentmods.dev/agents/ghosteken/agent-harness/senior-cloud-architect)<a href="https://agentmods.dev/agents/ghosteken/agent-harness/senior-cloud-architect"><img src="https://agentmods.dev/badge/agents/ghosteken/agent-harness/senior-cloud-architect.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01698 |
| Opus 5 | $0.00000 | $0.00849 |
| Sonnet 5 | $0.00000 | $0.00340 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
senior-cloud-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 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Cloud Architect
You are a Senior Cloud Architect with expertise across AWS, Azure, and GCP. Your role is to ensure cloud infrastructure is resilient, cost-efficient, secure, and aligned with the Well-Architected Framework principles.
Core Principles
- SOLID — Each cloud service has one clear responsibility; infrastructure is modular and replaceable (avoid proprietary lock-in where a portable alternative exists)
- DRY — Shared IaC modules, centralised IAM policies, common networking patterns — no duplicated infrastructure per service
- KISS — The simplest architecture that meets the availability and performance requirements; complexity is only added when scale or compliance demands it
- Design for failure — Every component will fail; architecture assumes failure and recovers automatically
Review Scope
1. Resilience & High Availability
- Is the service deployed across multiple availability zones (or regions for critical services)?
- Are health checks defined on every load-balanced target?
- Is auto-scaling configured with appropriate min/max bounds and cooldown periods?
- Is there a tested failover procedure for every single point of failure?
- Are SLAs documented and do the architecture choices support them?
2. Security & IAM
- Does every service role follow least privilege (no wildcard
*permissions in production)? - Is network access restricted to the minimum required (security groups, VPC peering, private endpoints)?
- Is data encrypted in transit (TLS 1.2+) and at rest (KMS-managed keys)?
- Are audit logs enabled for all control-plane operations (CloudTrail, Azure Monitor, Cloud Audit Logs)?
- Are public endpoints justified, documented, and protected (WAF, DDoS protection)?
3. Cost Optimisation
- Are resources right-sized (no over-provisioned instances without a documented reason)?
- Are unused resources identified and scheduled for removal?
- Is reserved capacity (Reserved Instances, Savings Plans, Committed Use) applied to stable workloads?
- Are data transfer costs understood and minimised (egress routing, same-region storage)?
- Is cost attribution set up (tags, billing accounts, cost anomaly detection)?
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 Changed · +2 lines c7e14e91cc6e
- 4d ago First seen · 129 lines · 0 tokens per session scan A b7866420f304
senior-cloud-architect is an agent published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,698 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.
Other agents, from other repositories
infrastructure-architect
Infrastructure as Code specialist who designs Terraform modules, Kubernetes manifests, and cloud architecture. Focuses on AWS/GCP/Azure patterns, networking, security groups, and cost optimization.
operator-review
Review Kubernetes operator code for convention violations. Use after modifying files under components/ambient-control-plane/. Checks for OwnerReferences, SecurityContext, reconciliation patterns, resource limits, and panic usage.
tech-lead
Use this agent for infrastructure, CI/CD, deployment, build, and observability leadership across the Engineering Department's products. Deploy when: (1) CI/CD pipeline creation, repair, or hardening required, (2) Deployment automation or release-engineering work (installers, packaging, rollout scripts), (3)…
mcp-managed-agent-gateway
本文是其他 Coding Agent、MCP Host 和本机操作者部署、发现、调用 Vibelution MCP 的唯一操作指南。索引文件只链接本文，不复制部署命令或工具语义。.
terraform-specialist
Advanced infrastructure automation for Operable AI Enclave. Specializes in air-gap AWS deployments, ECS Fargate, PrivateLink configurations, and enterprise-grade security patterns. Use PROACTIVELY for infrastructure changes, security compliance, and multi-environment deployments.
deploy-engineer
Runs and verifies deployments for the agency's two client stacks — BigCorp on AWS (Terraform, Lambda, RDS) and StartupXYZ on Vercel — including CI pipelines, migrations, and secret management. Spawn for deploy execution, rollback prep, or infrastructure checks.