check-conventions

A command for checking every independent module in a repository against shared coding and configuration rules.

In plain words
What is it for?
Use it to inspect variables, file layout, provider authentication, and other conventions across all modules, with optional strict warning handling.
Why use it?
It finds differences that can break validation tools or make modules behave inconsistently, including issues that an automatic checker cannot judge.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/techequitycloud/rad-modules/check-conventions
Clone the repo
git clone --depth 1 https://github.com/techequitycloud/rad-modules

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00639
Opus 5 $0.00000 $0.00319
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 2d ago against content hash d037bbcb8e1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-conventions 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 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.

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.

.claude/commands/check-conventions.md · 69 lines

What it actually says

Check every module under modules/ for convention drift against the binding rules in .agent/skills/module-conventions/SKILL.md and CLAUDE.md.

rad-modules has NO shared foundation module — each module is independent. "Drift" here means a module diverging from the repo-wide conventions, not from a parent module.

Start by running the mechanical checker, then add the judgement-based checks it can't do:

python3 scripts/check_conventions.py            # FAIL findings break, WARN findings inform
python3 scripts/check_conventions.py --strict   # treat warnings as failures too

Summarise its output, then verify the following across all modules.


Step 1 — STANDARD VARIABLE CONSISTENCY

Collect every module's variables.tf. For the ten standard variables (module_description, module_dependency, module_services, credit_cost, require_credit_purchases, enable_purge, public_access, deployment_id, resource_creator_identity, trusted_users) verify: a) The variable is present (note the legitimate exceptions: AKS_GKE, EKS_GKE and Migration_Center omit enable_services; Container_Migration, Migration_Center and VMware_Engine omit trusted_users). b) Its TYPE matches across modules (e.g. trusted_users is always list(string)). c) resource_creator_identity default is the standard SA ("[email protected]"). d) trusted_users carries the duplicate-and-whitespace validation blocks from AKS_GKE/variables.tf.

Report per module: ": — ".


Step 2 — UIMETA COMPLETENESS

Every variable in every module must have a {{UIMeta group=N order=M}} tag in its description. List any variable missing it, grouped by module.


Step 3 — API ENABLEMENT INVARIANT

For every google_project_service across all modules, confirm disable_dependent_services = false and disable_on_destroy = false, and that none use lifecycle { prevent_destroy = true }. Report any violation — this is a hard rule.


Step 4 — LICENSE HEADERS & SYMLINKS

a) Report any .tf file missing the Apache 2.0 header. b) Report any symlink found inside a module directory (modules must never share files).


Output

Group findings by module; skip modules with none. If everything is consistent, say: "All modules are consistent with the repo conventions."

If asked to FIX drift: for a missing standard variable, copy the complete variable block (description with its {{UIMeta}} tag, type, default, validations) from a module that has it correct (prefer AKS_GKE for the standard ten), inserting it in the right SECTION/order. Never invent a hardcoded credential default. After fixing, run tofu fmt -recursive modules/ and re-run the checker.

Changes

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.

  1. 2d ago First seen · 69 lines · 0 tokens per session scan A d037bbcb8e1d

Subscribe to this mod's changes

check-conventions is a command published in the GitHub repository techequitycloud/rad-modules (2 stars, last pushed 8d ago), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 639 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.