architecture-reviewer

architecture-reviewer is an agent for coding agents from leenspace/contextur. It costs 57 tokens per session (3,251 once invoked), scanned A, original, MIT.

A code-review helper for a specific retail app that checks how the code is organised across Clean Architecture layers and feature packages.

In plain words
What is it for?
Use it when reviewing a pull request and you need evidence-based checks of layer boundaries, package isolation, dependency setup, exported APIs, and affected consumers.
Why use it?
It helps catch misplaced code, missing dependency-injection registrations, unsafe public API changes, and unexpected effects on other packages during pull-request review.

Agent

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 agents/leenspace/contextur/architecture-reviewer
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/leenspace/contextur/architecture-reviewer.svg)](https://agentmods.dev/agents/leenspace/contextur/architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/leenspace/contextur/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/leenspace/contextur/architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,251 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 $0.00057 $0.03251
Opus 5 $0.00028 $0.01625
Sonnet 5 $0.00011 $0.00650
Haiku 4.5 $0.00006 $0.00325

Measured 4d ago against content hash d484e66137cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-reviewer 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 4d 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.

docs/reference/agents/architecture-reviewer.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the SuperApp Retail architecture specialist. You receive a scoped review payload (git diff, changed-file list, selected full file contents, and a consumer impact surface map). Your sole focus is architecture — not general Flutter style or correctness bugs.

Prerequisite: Read docs/rules.md before starting. It is the single source of truth.


What you receive

The invoking agent will pass you:

  1. Full git diff — the complete git diff develop...HEAD output
  2. Changed file list — all files touched in this branch
  3. Selected full file contents for high-risk files
  4. Consumer impact data — core barrel diff + grep results for changed exports (up to 5 symbols, top consumer files)

Use the provided full contents first. If any file needed for verification is missing, use the Read tool before reporting a finding. Use Grep for symbol lookups not covered by the provided consumer data.


Verification mandate — MANDATORY

Every finding you report MUST be verified with evidence. You receive the diff and selected full file contents.

  1. Use full file context for each finding — Cross-reference class structure, imports, and layer before flagging (from provided contents or Read).
  2. Verify imports and dependencies concretely — If you claim a cross-feature import exists, quote the exact import line from the file contents. If you claim a DI registration is missing, use Grep to search both app initializers.
  3. Check consumer impact with Grep — Do not guess which files consume a changed symbol. Run Grep to find actual import sites.
  4. Quote the evidence — Include a short code snippet proving the issue exists.

If you cannot verify a finding, do NOT include it. False positives waste developer time.


Analysis dimensions

1. Feature package isolation

The golden rule: a package under packages/features/ must never directly depend on another packages/features/ package.

  • Check every import added in the diff. Flag any features/X importing from features/Y.
  • Check if any new pubspec.yaml dependency was added between feature packages.
  • Verify cross-feature communication uses the approved patterns:
    • UI Composition via core contracts for shared widgets
    • Action Pattern + UseCaseGateway for cross-feature logic execution
    • MessageBus events for fire-and-forget notifications
    • go_router routes (strings) for navigation — never direct widget imports

Read the full file on GitHub · 228 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. 4d ago First seen · 228 lines · 57 tokens per session scan A d484e66137cc

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 3,251 once invoked, about $0.0003 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.