review-component

review-component is a command for Claude Code from AhmedHabiba/architor. It costs 0 tokens per session (526 once invoked), scanned A, original, MIT.

A skeptical review command for testing the design of one architecture component. It checks the design against the project requirements, chosen technology, surrounding architecture, and organizational constraints.

In plain words
What is it for?
Use it to review a component design after it has been written and compare it with the broader architecture and accepted component designs.
Why use it?
It helps find missing requirements, unsuitable choices, integration problems, and other weaknesses before implementation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to review a component design after it has been written and compare it with the broader architecture and accepted component designs.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ahmedhabiba/architor/review-component
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.

Clone the repo
git clone --depth 1 https://github.com/AhmedHabiba/architor

Made for: Claude Code.

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 review-component

README.md
[![agentmods](https://agentmods.dev/badge/commands/ahmedhabiba/architor/review-component/github.svg)](https://agentmods.dev/commands/ahmedhabiba/architor/review-component)
Your own site
<a href="https://agentmods.dev/commands/ahmedhabiba/architor/review-component"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/review-component/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 review-component

Your own site · 80×15
<a href="https://agentmods.dev/commands/ahmedhabiba/architor/review-component"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/review-component.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 526 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 $0.00000 $0.00526
Opus 5 $0.00000 $0.00263
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00053

Measured 9d ago against content hash 5714e3cf8725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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/review-component.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This command launches an adversarial architecture review of a component.

Read .arch/state.json. The component to review is specified in $ARGUMENTS. If empty, use the current_component.

GATE CHECK: The component must have a design file in .arch/components/[name].md. If not, STOP: "No design found for component [name]. Design it first with /design-component [name]."

Act as a different architect — a skeptical principal architect conducting a formal design review. Forget that you proposed this design. Your job is to find problems.

Read:

  • .arch/components/[component-name].md — the design under review
  • .arch/phase2-methodology.md — the overall architecture
  • .arch/phase2-components-overview.md — how this fits in the system
  • .arch/org-context.md — organizational constraints
  • Any other accepted components in .arch/components/ — for consistency

Review Criteria

1. Requirements Alignment

  • Does this component fully satisfy its stated requirements?
  • Are there requirements from the PRD that this component should address but doesn't?

2. Technology Fitness

  • Is the chosen technology appropriate for the scale?
  • Is it appropriate for the team's skill level?
  • Are there licensing, cost, or vendor lock-in concerns?

3. Integration Integrity

  • Do the API contracts match what connected components expect?
  • Are data formats consistent across boundaries?
  • Is the communication pattern (sync/async) appropriate?

4. Failure Analysis

  • What's the blast radius if this component fails?
  • Is the fallback strategy realistic or wishful thinking?
  • What happens to data consistency during failures?

5. Security Review

  • Are there unprotected endpoints?
  • Is sensitive data properly encrypted in transit and at rest?
  • Is the authentication/authorization model sufficient?

6. Operational Readiness

  • Can the team realistically monitor this?
  • Are the alerting thresholds meaningful or arbitrary?
  • How difficult is debugging when things go wrong?

Read the full file on GitHub · 62 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. 9d ago First seen · 62 lines · 0 tokens per session scan A 5714e3cf8725

Subscribe to this mod's changes

review-component is a command published in the GitHub repository AhmedHabiba/architor (6 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 526 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.