review-architecture

review-architecture is a skill for Claude Code from mrinalwadhwa/fluent. It costs 37 tokens per session (313 once invoked), scanned A, original, Apache-2.0.

A review of a codebase's architecture, meaning how its modules, boundaries, abstractions, and dependencies are organized.

In plain words
What is it for?
Use it to review architectural changes in a code diff, check module boundaries, or audit the structure of an entire codebase.
Why use it?
It identifies structural choices that make software harder to understand, change, or ship, including circular dependencies and overly coupled components.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fluent plugin — 6 skills shipped together

Good fit Use it to review architectural changes in a code diff, check module boundaries, or audit the structure of an entire codebase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mrinalwadhwa/fluent/review-architecture
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.

Any agent
npx skills add mrinalwadhwa/fluent --skill review-architecture
Clone the repo
git clone --depth 1 https://github.com/mrinalwadhwa/fluent

Made for: Claude Code.

Or install fluent, the plugin that ships this one along with the rest of its 6 skills.

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-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrinalwadhwa/fluent/review-architecture/github.svg)](https://agentmods.dev/skills/mrinalwadhwa/fluent/review-architecture)
Your own site
<a href="https://agentmods.dev/skills/mrinalwadhwa/fluent/review-architecture"><img src="https://agentmods.dev/badge/skills/mrinalwadhwa/fluent/review-architecture/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-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrinalwadhwa/fluent/review-architecture"><img src="https://agentmods.dev/badge/skills/mrinalwadhwa/fluent/review-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 313 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00037 $0.00313
Opus 5 $0.00018 $0.00156
Sonnet 5 $0.00007 $0.00063
Haiku 4.5 $0.00004 $0.00031

Measured 9d ago against content hash 7298b6be14aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-architecture 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.

skill-migrations/v0.1.4/review-architecture/SKILL.md · 29 lines

What it actually says

Purpose

Decide whether the code's architecture is fit to ship. Identify improvements that would make the codebase simpler, more coherent, and easier to change.

Scope

The invoking layer decides what's in scope. For a diff-scoped review, that's the structural choices in the diff. For a full-codebase audit, that's the codebase's overall structure. Even in a diff-scoped review, evaluate the changes in the context of the entire codebase — a boundary that looks fine in isolation can be wrong in context. Check each choice for structural quality and check the codebase as a whole for coherence.

Method

  1. Read the code under review to understand its structure — module boundaries, key abstractions, dependencies.

  2. Read references/architecture.md for architectural principles. Read any related guides it points to for the code under review.

  3. For each in-scope structural choice:

    • Evaluate against the principles in references/architecture.md.
    • Identify improvements.
  4. Check for anti-patterns from references/architecture.md.

  5. For each improvement, decide if it blocks shipping. Circular dependencies, god objects, and coupling that will block near-term work typically block. Small simplifications, naming preferences, and style choices typically don't.

The invoking layer may add checks in addition to those above.

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 29 lines · 37 tokens per session scan A 7298b6be14aa

Subscribe to this mod's changes

review-architecture is a skill published in the GitHub repository mrinalwadhwa/fluent (88 stars, last pushed 8d ago), licensed Apache-2.0. It adds 37 tokens to every session and 313 once invoked, about $0.0002 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 2026-08-30.