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 instructions/smana/cloud-native-ref/claude-mdgit clone --depth 1 https://github.com/Smana/cloud-native-refWhat 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 | $0.05497 | $0.05497 |
| Opus 5 | $0.02749 | $0.02749 |
| Sonnet 5 | $0.01099 | $0.01099 |
| Haiku 4.5 | $0.00550 | $0.00550 |
Grade A, and why
cloud-native-ref CLAUDE.md 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
This is a comprehensive cloud-native platform reference repository implementing GitOps practices with Kubernetes. The repository demonstrates production-ready configurations for building, managing, and maintaining a secure, scalable cloud-native platform using AWS EKS and GCP GKE.
Infrastructure Architecture
The platform is deployed in three sequential stages:
- Network Layer (
opentofu/aws/network/): VPC, subnets, Route53, and Tailscale VPN - Security Layer (
opentofu/aws/openbao/): OpenBao cluster for secrets management and PKI - Kubernetes Layer (
opentofu/aws/eks/init/+opentofu/aws/eks/configure/): EKS cluster with Flux, Cilium, and Karpenter
Key Components
- OpenTofu: Infrastructure as Code (Terraform alternative)
- Terramate: OpenTofu orchestration and stack management
- Flux: GitOps continuous delivery
- Crossplane: Infrastructure composition from Kubernetes
- OpenBao: Secrets management and private PKI
- Cilium: Advanced networking and security with eBPF
- Gateway API: Modern ingress and traffic routing
- VictoriaMetrics: High-performance observability stack
EKS Bootstrap Architecture
Two-stage OpenTofu deployment: Stage 1 creates the EKS cluster with temporary CNI, Stage 2 replaces it with Cilium and installs Flux.
Why two stages? Helm provider needs cluster endpoint at plan time, so Stage 2 runs after the cluster exists.
Deploy: cd opentofu && terramate script run deploy — one command builds the
whole platform, EKS included. cd opentofu/aws/eks/init && terramate script run deploy
re-runs just this stack, e.g. after a failure.
Key Files:
opentofu/config.tm.hcl- Cilium/Flux versionsopentofu/aws/eks/init/main.tf- EKS module with bootstrap addonsopentofu/aws/eks/configure/main.tf- Cilium and Flux helm_releasesopentofu/aws/eks/init/helm_values/cilium.yaml- Cilium Helm values
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 · 385 lines · 5,497 tokens per session scan A 0fac6c0b7164
cloud-native-ref CLAUDE.md is an instructions file published in the GitHub repository Smana/cloud-native-ref (99 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,497 tokens to every session, about $0.0275 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 instructions, from other repositories
mirrord AGENTS.md
Instructions for metalbear-co/mirrord, covering mirrord, core crates, command reference, compiling and check the entire workspace at once.
mirrord CLAUDE.md
Instructions for metalbear-co/mirrord, a project described as: Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic.
devex AGENTS.md
Instructions for ParthKapoor-dev/devex: Summary Devex is a cloud development IDE with sandboxed “repl” sessions. The system is split into services. The core service handles auth and session orchestration, while the runner provides the interactive sandbox (WebSocket + PTY). Session data is persisted to S3-compatible…
timoni AGENTS.md
Instructions for stefanprodan/timoni, covering agents.md, what timoni is, common commands, architecture and cmd/timoni/ — cli (cobra).
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, mandatory development principles and sow system.
stackql AGENTS.md
Instructions for stackql/stackql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.