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/techequitycloud/rad-modules/claude-mdgit clone --depth 1 https://github.com/techequitycloud/rad-modulesWhat 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 | $0.10282 | $0.10282 |
| Opus 5 | $0.05141 | $0.05141 |
| Sonnet 5 | $0.02056 | $0.02056 |
| Haiku 4.5 | $0.01028 | $0.01028 |
Grade C, and why
rad-modules CLAUDE.md scanned grade C with 1 finding 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 2d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
**Credentials are machine-global, not session-scoped.** `gcloud auth application-default login` overwrites the single `~/.config/gcloud/application_default_credentials.json` for every terminal and every tool on the machi How it starts
The opening of the file, as written. The whole thing — 501 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.
What This Repo Is
rad-modules is a catalog of standalone OpenTofu/Terraform modules that deploy educational Google Cloud and multi-cloud Kubernetes reference architectures ("RAD Lab"). Modules are deployed via the interactive rad-launcher CLI or via Cloud Build pipelines driven by the RAD platform UI.
Common Commands
All Terraform commands run from within a module directory (e.g. cd modules/Istio_GKE):
# Validate and format-check a module
tofu init -backend=false
tofu validate
tofu fmt -check
# Run module-level tests (uses mock providers, no GCP credentials needed)
tofu test
# Plan/apply with a real project
tofu plan -var="project_id=my-gcp-project"
tofu apply -var="project_id=my-gcp-project"
tofu destroy -var="project_id=my-gcp-project"
Lint all modules from the repo root:
# Format check (CI uses terraform, but tofu also works)
terraform fmt -check -recursive modules/
# tflint (run from within a module directory)
tflint --init --config ../../.tflint.hcl
tflint --config ../../.tflint.hcl --format compact
Run the interactive launcher:
cd rad-launcher
python3 installer_prereq.py # install prerequisites once
python3 radlab.py # interactive module deploy/destroy
Non-interactive launcher:
python3 rad-launcher/radlab.py \
-m Istio_GKE -a create \
-p my-mgmt-project -b my-mgmt-project-radlab-tfstate \
-f /path/to/my.tfvars
Before running tofu plan/apply directly against a module directory (bypassing the launcher), check for leftovers from a prior manual run:
ls *.auto.tfvars— OpenTofu loads these automatically with no-var-fileflag. A stale one from an earlier lab pinsproject_id(or other vars) to a project you may no longer have access to, and the failure mode is a confusing 403 deep inplan, not an obviously-wrong-input error.Bank_GKEhas shipped one before; there is no repo convention preventing another.ls *.tfstate*— local state from a previous run against a different project makesplantry to reconcile resources that don't exist in the target project. The launcher andrad-uialways use a GCS backend and never hit this; a baretofu init/applyin a module directory does.
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.
- 2d ago First seen · 501 lines · 10,282 tokens per session scan C 39c324951bff
rad-modules CLAUDE.md is an instructions file published in the GitHub repository techequitycloud/rad-modules (2 stars, last pushed 8d ago), licensed MPL-2.0. It adds 10,282 tokens to every session, about $0.0514 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
apex-accelerator iac-bicep-best-practices.instructions.md
Bicep-specific IaC best practices for Azure templates. Security baseline, naming, AVM mandate, anti-patterns.
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
terraform-provider-pipefy AGENTS.md
Instructions for pipefy/terraform-provider-pipefy, covering agents.md, project overview, setup and requirements, essential commands and project layout.
plan-forge azd.instructions.md
Azure Developer CLI (azd) patterns — azure.yaml structure, infra folder, tags, hooks, pipelines.
plan-forge terraform.instructions.md
Terraform Azure patterns — file structure, providers, state, naming, security, testing.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.