review-component

A command that reviews a Terraform infrastructure component from security, architecture, operations, and cost perspectives. Terraform is a tool for describing cloud and infrastructure resources in code.

In plain words
What is it for?
Checking a Terraform component, finding missing or misplaced configuration, and collecting findings from four specialised reviewers.
Why use it?
It brings several types of infrastructure review together and checks that the repository is structured correctly before the detailed review begins.

Command

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/infraspecdev/tesseract/review-component
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 623 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 $0.00022 $0.00623
Opus 5 $0.00011 $0.00311
Sonnet 5 $0.00004 $0.00125
Haiku 4.5 $0.00002 $0.00062

Measured 2d ago against content hash b99823932321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-component 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.

infra-review/commands/review-component.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Component Review

Run a comprehensive review of the current Terraform component from 4 perspectives. Follow this process exactly:

Pre-flight: Atmos Hygiene Check

Before dispatching agents, invoke the infra-review:atmos-component-hygiene skill to run a quick hygiene check. If critical issues are found (missing versions.tf, committed backend.tf), report them immediately — they should be fixed before a full review.

Step 1: Detect Component

Identify the component to review:

  1. Check if src/versions.tf exists → single-component repo, review src/
  2. Check if components/terraform/ exists → multi-component repo, ask user which component
  3. Neither → report "This doesn't appear to be a Terraform component repository"

Step 2: Dispatch Reviewers

Run all 4 reviewer agents sequentially against the component. For each agent, use the Agent tool with the appropriate agent type:

  1. Security Review — Dispatch the infra-review:security-reviewer agent

    • Provide all .tf files from the component directory
    • Collect findings
  2. Architecture Review — Dispatch the infra-review:architecture-reviewer agent

    • Provide all .tf files from the component directory
    • Collect findings
  3. Operations Review — Dispatch the infra-review:operations-reviewer agent

    • Provide all .tf files and CI workflows from .github/workflows/
    • Collect findings
  4. Cost Review — Dispatch the infra-review:cost-reviewer agent

    • Provide all .tf files from the component directory
    • Collect findings

Step 3: Consolidated Report

After all 4 agents complete, write a consolidated report to claude/infra-review/review.md in the repository root:

# Terraform Component Review

**Component:** [name]
**Date:** [date]
**Reviewers:** Security, Architecture, Operations, Cost

## Summary

| Dimension | Grade/Score | Key Finding |
|-----------|------------|-------------|
| Security | [posture] | [top finding] |
| Architecture | [grade] | [top finding] |
| Operations | [score]/10 | [top finding] |
| Cost | [efficiency] | [top finding] |

## Critical Issues (Action Required)

[List any Critical/Must-Fix issues from all 4 reviews]

## Detailed Findings

### Security
[Full security review output]

### Architecture
[Full architecture review output]

### Operations
[Full operations review output]

### Cost
[Full cost review output]

## Recommended Priority Order

1. [Most important fix across all dimensions]
2. [Second]
3. [Third]

Read the full file on GitHub · 87 lines

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 · 87 lines · 22 tokens per session scan A b99823932321

Subscribe to this mod's changes

review-component is a command published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 623 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.