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/anthr76/infra/claude-mdgit clone --depth 1 https://github.com/anthr76/infraWrote 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/instructions/anthr76/infra/claude-md)<a href="https://agentmods.dev/instructions/anthr76/infra/claude-md"><img src="https://agentmods.dev/badge/instructions/anthr76/infra/claude-md.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 | $0.04765 | $0.04765 |
| Opus 5 | $0.02382 | $0.02382 |
| Sonnet 5 | $0.00953 | $0.00953 |
| Haiku 4.5 | $0.00477 | $0.00477 |
Grade A, and why
infra 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 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 — 643 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 multi-environment, multi-cloud infrastructure-as-code repository for a home lab environment using GitOps principles. It manages Terraform configurations for cloud resources, Kubernetes workloads via Flux CD, and on-premises virtualization.
Related Repositories:
- anthr76/snowflake - System-level configuration for nodes, routers, and infrastructure components
Additional Context:
- See
.github/instructions/.instructions.mdfor comprehensive coding standards and guidelines
Development Environment
This repository uses Flox (Nix-based development environments) for consistent tooling. All required tools are automatically available:
# Enter the development environment (automatically via direnv, or manually)
flox activate
# All tools are now available: kubectl, flux, helm, sops, age, just, etc.
The environment is defined in .flox/env/manifest.toml. direnv auto-activates it
on cd via .envrc (eval "$(flox activate)").
Never manually install tools - they are managed via the Flox manifest. To add a
tool: flox install <package> (or edit .flox/env/manifest.toml).
kubectl-volsync is a custom Go build (not in the catalog) defined under
.flox/pkgs/kubectl-volsync/. Build it once with flox build kubectl-volsync; the
manifest's activation hook then adds ./result-kubectl-volsync/bin to PATH.
Common Commands
Task Automation
All automation tasks are defined in the Justfile. Use just instead of custom scripts:
# List all available tasks
just --list
# Reconcile all Flux GitRepositories and Kustomizations
just flux-reconcile
# Sync Flux GitRepos, Kustomizations, and HelmReleases
just flux-sync
# Suspend all Flux resources
just flux-suspend
# Resume all Flux resources
just flux-resume
# Install Fedora CoreOS for RPI4 (legacy - being phased out)
just burn-fcos-pi4
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 · 643 lines · 4,765 tokens per session scan A abf2ba5c7d99
infra CLAUDE.md is an instructions file published in the GitHub repository anthr76/infra (107 stars, last pushed 4d ago), licensed Apache-2.0. It adds 4,765 tokens to every session, about $0.0238 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
terraform-hcloud-kube-hetzner AGENTS.md
AGENTS.md instructions for mysticaltech/terraform-hcloud-kube-hetzner, a project described as: Optimized and Maintenance-free Kubernetes on Hetzner Cloud in one command!
timoni AGENTS.md
AGENTS.md instructions for stefanprodan/timoni, covering agents.md, what timoni is, common commands, architecture and cmd/timoni/ — cli (cobra).
k8e AGENTS.md
Instructions for xiaods/k8e, covering agents.md, project overview, architecture (big picture), key architectural flows and building.
aks-mcp copilot-instructions.md
Instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
kubevirt-tekton-tasks AGENTS.md
Instructions for kubevirt/kubevirt-tekton-tasks, covering kubevirt tekton tasks - project guide, jira task management, documentation, project structure and key relationships.
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.