What is 05-architecture-validator?

An automated architecture review agent for a Rust workspace with several crates, such as core, formatting, browser-control, and command-line crates.

Use it when changing crate boundaries, Cargo.toml dependencies, or adding a crate. It reports either “Verdict: APPROVE” or “Verdict: REQUEST_CHANGE”.

It catches dependency-layer violations, unsafe code in restricted areas, nondeterministic output, missing API documentation, and unjustified lint exceptions.

How aram-devdocs/plumb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to aram-devdocs/plumb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/aram-devdocs/plumb/main/.claude/agents/05-architecture-validator.md

Clone the repo

git clone --depth 1 https://github.com/aram-devdocs/plumb

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/aram-devdocs/plumb/05-architecture-validator/github.svg)](https://agentmods.dev/agents/aram-devdocs/plumb/05-architecture-validator)

Your own site

<a href="https://agentmods.dev/agents/aram-devdocs/plumb/05-architecture-validator"><img src="https://agentmods.dev/badge/agents/aram-devdocs/plumb/05-architecture-validator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/aram-devdocs/plumb/05-architecture-validator"><img src="https://agentmods.dev/badge/agents/aram-devdocs/plumb/05-architecture-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 420 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00420
Opus 5.5	$0.00014	$0.00168
Sonnet 5.5	$0.00007	$0.00084
Haiku 4.5	$0.00003	$0.00042

Measured 2mo ago against content hash c3ad5f78497a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

05-architecture-validator 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 2mo 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/agents/05-architecture-validator.md · 43 lines

What it actually says

You validate that a change respects Plumb's architectural invariants.

What you check

Layering. Read .agents/rules/dependency-hierarchy.md. Confirm every [dependencies] entry in the touched Cargo.toml files obeys the hierarchy: plumb-core depends on nothing internal; plumb-format depends only on plumb-core; plumb-cdp depends only on plumb-core; plumb-cli sits at the top.
No unsafe leakage. unsafe_code = "forbid" holds everywhere except plumb-cdp. If a new unsafe block appears outside plumb-cdp, that is a hard block.
Determinism. Read .agents/rules/determinism.md. Any new dependency that pulls in SystemTime::now, Instant::now, a RNG, or an unordered HashMap at an output boundary is a block.
Public API shape. A new pub item in a library crate needs missing_docs coverage and, if fallible, a # Errors section.
Lint overrides. Any #[allow(...)] added at file scope is justified in the line above it.

What you do NOT check

Spec compliance — 02-spec-reviewer.
Code idioms — 03-code-quality-reviewer.
Test exhaustiveness — 04-test-runner.

Output format

End with one of:

Verdict: APPROVE
Verdict: REQUEST_CHANGES
Verdict: BLOCK

Punch list above the verdict. Cite file:line for every issue.

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.

2mo ago First seen · 43 lines · 34 tokens per session scan A c3ad5f78497a

Subscribe to this mod's changes

05-architecture-validator is an agent published in the GitHub repository aram-devdocs/plumb (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 420 once invoked, about $0.0001 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 2026-08-31.

Code review Languages Rust chromium cli css design-system design-tokens developer-tools

rust-critic

Adversarial critic specializing in finding logical gaps, flawed assumptions, scalability limits, and missing edge cases in architectural designs, implementation proposals, and ideas. Use PROACTIVELY after architecture design, before committing to an approach, or when a user wants their idea stress-tested. Never writes…

bug-ops/zeph · 109 tokens

rust-code-reviewer

Rust code reviewer specializing in quality assurance, standards compliance, constructive feedback, and ensuring best practices. Use PROACTIVELY before committing code, after feature implementation, or when pull request review is needed.

bug-ops/zeph · 45 tokens

rust-developer

Rust developer specializing in idiomatic code, ownership patterns, error handling, and daily feature implementation. Use PROACTIVELY for implementing features, writing business logic, and refactoring code.

bug-ops/zeph · 41 tokens

auv-code-reviewer

AUV SceneBridge / view-memory lane code quality reviewer. Proactively reviews Rust diffs for correctness, hermetic tests, contract boundaries, and CONTRIBUTING.local.md veto items. Use immediately after implementing or modifying auv-view, auv-netease-music, or scenebridge docs.

moeru-ai/auv · 65 tokens

rust-security-maintenance

Rust security and maintenance specialist focused on cargo-deny, dependency management, vulnerability scanning, and secure coding practices. MUST BE USED for unsafe code blocks, authentication, authorization, cryptography, or external input validation.

bug-ops/zeph · 47 tokens

muriel-forger

Forger juror seat for a muriel jury. Asserts "I can reproduce this from a generic template in four minutes," then actually builds the counterfeit from a default stack, diffs it against the original, and reports the residue — the decisions that survive. Judges one thing only, distinguishability from competent generic…

andyed/muriel · 103 tokens

plumb: Agent for Claude Code