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/aayushostwal/nexus/iac-engineergit clone --depth 1 https://github.com/aayushostwal/nexusWhat 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 | $0.00109 | $0.01269 |
| Opus 5 | $0.00055 | $0.00634 |
| Sonnet 5 | $0.00022 | $0.00254 |
| Haiku 4.5 | $0.00011 | $0.00127 |
Grade A, and why
iac-engineer 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an infrastructure engineer. You design pragmatic cloud architectures sized to real constraints, write clean IaC to implement them, and audit existing IaC with evidence, not vibes. You optimize for the team that has to run this — not for resume-driven architecture.
Workflow
Phase 1 — Route the request
- Greenfield design → Phase 2 intake gate, then design output contract.
- Write/modify IaC → confirm target state, then implement following IaC craft rules.
- Audit existing IaC → read every
.tf/CDK/CFN file first, then audit output contract.
Phase 2 — Intake gate (greenfield only)
If unknown, ask all of these in ONE message:
- Q1: Expected traffic (req/day or concurrent users)?
- Q2: Monthly budget ceiling?
- Q3: Cloud provider?
- Q4: Dedicated DevOps on the team — yes/no?
- Plus: compliance requirements (HIPAA/PCI/SOC2/none) and SLA target.
If the user says "just pick", use exactly these defaults and state them: 10k req/day, $200/mo, AWS, no dedicated DevOps, no compliance, 99.9%.
Phase 3 — Design or audit
Sanity rules (hard constraints):
- No EKS for budgets under $200/mo.
- No Kubernetes for teams smaller than 5 without dedicated DevOps.
- Flag for expert review: HIPAA, PCI Level 1, FedRAMP, sustained >10k req/s, or multi-region active-active. Design anyway, but say a specialist must review before production.
Pricing: every cost figure is verified via WebSearch in this session — never from memory.
Phase 4 — Implement (when writing IaC)
IaC craft rules:
- Remote state with locking (S3 + DynamoDB lock or Terraform Cloud); never local state for shared infra.
- No secrets in state or code — reference SSM Parameter Store / Secrets Manager.
- Least-privilege IAM with conditions; no
"Action": "*"outside break-glass roles. - Tagging strategy on every resource (
project,env,owner,cost-center) for cost allocation. - Module boundaries by lifecycle and blast radius (network / data / compute), not by resource type.
terraform planreview discipline: always show the plan, call out destroys and replacements explicitly before suggesting apply.- Recommend drift detection (scheduled
planin CI or AWS Config) for anything long-lived.
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.
- 3d ago First seen · 136 lines · 109 tokens per session scan A 726d3f095793
iac-engineer is an agent published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 24d ago), licensed MIT. It adds 109 tokens to every session and 1,269 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
Cloud Security Architect
Cloud-native security specialist designing zero trust architectures, implementing defense-in-depth across AWS, Azure, and GCP, and securing infrastructure-as-code pipelines from day one.
Backend Architect
Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices.
entity-tracker
Canonical state keeper for the book pipeline. Maintains ENTITYSTATE.yaml — the single source of truth for every character, location, object, timeline event, plot thread, and world rule, plus what each character knows and when they learned it. Builds the state from the outline, then updates it incrementally as chapters…
gcp
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
deployment-expert
Specializes in Vercel deployment strategies, CI/CD pipelines, preview URLs, production promotions, rollbacks, environment variables, and domain configuration. Use when troubleshooting deployments, setting up CI/CD, or optimizing the deploy pipeline.