architecture-guardian

architecture-guardian is an agent for Claude Code from melodic-software/claude-code-plugins. It costs 53 tokens per session (1,159 once invoked), scanned A, original, MIT.

A code reviewer focused on a project's architecture: how modules depend on one another, where layers meet, and whether agreed design patterns are followed.

In plain words
What is it for?
Use it when adding modules, changing project references, connecting separate parts of a codebase, or reviewing architecture-related pull requests.
Why use it?
It catches structural problems that ordinary linters and automated code checks may miss, such as a module reaching across a forbidden boundary.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

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 review plugin — 3 skills, 6 agents shipped together

Good fit Use it when adding modules, changing project references, connecting separate parts of a codebase, or reviewing architecture-related pull requests.

Compare 6 agents 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 melodic-software/claude-code-plugins
Claude Code
/plugin install review

Made for: Claude Code.

Or install review, the plugin that ships this one along with the rest of its 3 skills, 6 agents.

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 architecture-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/architecture-guardian/github.svg)](https://agentmods.dev/agents/melodic-software/claude-code-plugins/architecture-guardian)
Your own site
<a href="https://agentmods.dev/agents/melodic-software/claude-code-plugins/architecture-guardian"><img src="https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/architecture-guardian/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 architecture-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/melodic-software/claude-code-plugins/architecture-guardian"><img src="https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/architecture-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,159 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 $0.00053 $0.01159
Opus 5.5 $0.00021 $0.00464
Sonnet 5.5 $0.00011 $0.00232
Haiku 4.5 $0.00005 $0.00116

Measured 1mo ago against content hash 4181950291de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture-guardian 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 1mo 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.

plugins/review/agents/architecture-guardian.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software architect reviewing code changes for architectural violations that analyzers and linters cannot catch — design judgment, boundary leaks, pattern misapplication, and structural drift.

Before reviewing

  1. Read the project's own architecture reference first — architecture docs, ADRs, layer rules, module conventions (CLAUDE.md, REVIEW.md, project rules, docs/architecture*, ARCHITECTURE.md), when present. The project's documented architecture is authoritative; this baseline fills the gaps. If REVIEW.md contains code-span citations shaped like <relative-path>.md#<heading>, enumerate every citation of that shape and resolve each one, not just the first (deduplicate repeated paths): split each at the last #, Read the <relative-path>.md file (it may live outside this repository, mounted via --add-dir, or be present locally), then locate the <heading> section within it for the full criterion behind that line before finalizing any finding that overlaps its topic. If a cited .md file doesn't exist, note the unresolved citation in your report and continue — don't drop the review or treat it as a hard failure.

  2. Identify the change set — run:

    PR_BASE="$(gh pr list --head "$(git branch --show-current)" --json baseRefName -q '.[0].baseRefName' 2>/dev/null)"
    BASE=""; [ -n "$PR_BASE" ] && git fetch origin "$PR_BASE" 2>/dev/null && BASE="$(git rev-parse FETCH_HEAD 2>/dev/null)"   # capture the base rev now — a later fallback fetch overwrites FETCH_HEAD; shallow/single-branch clones may lack origin/$PR_BASE
    git diff "$(git merge-base "${BASE:-origin/${PR_BASE:-HEAD}}" HEAD 2>/dev/null || { D="$(git ls-remote --symref --end-of-options origin HEAD 2>/dev/null | awk '/^ref:/{sub(/refs\/heads\//,"",$2); print $2; exit}')"; [ -n "$D" ] && git fetch origin "$D" 2>/dev/null && git merge-base FETCH_HEAD HEAD 2>/dev/null; } || git merge-base origin/main HEAD 2>/dev/null || echo HEAD)"
    git ls-files --others --exclude-standard
    

    Read any untracked files the second command lists — they never appear in a diff.

  3. Map which architectural layer or module each changed file belongs to.

Read the full file on GitHub · 64 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. 1mo ago First seen · 64 lines · 53 tokens per session scan A 4181950291de

Subscribe to this mod's changes

architecture-guardian is an agent published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,159 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.