audit

audit is a command for Claude Code from AlexK020908/infra-designer. It costs 13 tokens per session (408 once invoked), scanned A, original, MIT.

A command that compares deployed infrastructure with a written specification and reports differences by component.

In plain words
What is it for?
Capturing Terraform state, checking infrastructure against a specification, and reporting passed or failed checks with severity.
Why use it?
It makes configuration drift visible, such as resources that no longer match the intended setup.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the infra-designer plugin — 19 skills, 5 commands shipped together

Good fit Capturing Terraform state, checking infrastructure against a specification, and reporting passed or failed checks with severity.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AlexK020908/infra-designer
Claude Code
/plugin install infra-designer

Made for: Claude Code.

Or install infra-designer, the plugin that ships this one along with the rest of its 19 skills, 5 commands.

Wrote 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.

agentmods badge for audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexk020908/infra-designer/audit/github.svg)](https://agentmods.dev/commands/alexk020908/infra-designer/audit)
Your own site
<a href="https://agentmods.dev/commands/alexk020908/infra-designer/audit"><img src="https://agentmods.dev/badge/commands/alexk020908/infra-designer/audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexk020908/infra-designer/audit"><img src="https://agentmods.dev/badge/commands/alexk020908/infra-designer/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00013 $0.00408
Opus 5 $0.00006 $0.00204
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 8d ago against content hash aa51cfb4291b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit 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 8d 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.

infra-plugin/commands/audit.md · 46 lines

What it actually says

Audit infrastructure

Check that the live infrastructure still matches the spec, and report any drift using the user's own component names.

Spec path: $ARGUMENTS. If omitted, look under infra/ in the current working directory for a <project-name>/spec.json; if there are several projects, ask the user which one. All paths are relative to the user's cwd, never ${CLAUDE_PLUGIN_ROOT}. Below, <dir> is the folder the spec lives in (e.g. infra/todo-app).

1. Capture live state

From the Terraform working directory:

cd <dir>/terraform
terraform show -json > ../state.json

terraform show -json is the source of truth for what's actually deployed. If there's no Terraform state (infra wasn't deployed via /deploy), tell the user — auditing unmanaged infra is a later capability.

2. Run the checks

python ${CLAUDE_PLUGIN_ROOT}/engine/audit.py <dir>/spec.json <dir>/state.json

Each component ships an audit.yaml of declarative checks; the runner evaluates them against the live state. Exit code is non-zero if any check fails (useful in CI).

3. Report and offer fixes

  • Summarize by node: what passed, what drifted, severity.
  • For each drift, explain what changed and why it matters (read the component's SKILL.md if the user asks why a setting matters).
  • Offer to reconcile: update <dir>/spec.json to match reality (accept the change) or re-run /deploy to push the spec back onto the infra (revert the drift). Let the user choose per item — don't auto-apply.
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. 8d ago First seen · 46 lines · 13 tokens per session scan A aa51cfb4291b

Subscribe to this mod's changes

audit is a command published in the GitHub repository AlexK020908/infra-designer (2 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 408 once invoked, about $0.0001 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 2026-08-31.