Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/agents/architecture-reviewer.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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.
[](https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/architecture-reviewer)<a href="https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/architecture-reviewer/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.
<a href="https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/architecture-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00020 | $0.00603 |
| Opus 5.5 | $0.00008 | $0.00241 |
| Sonnet 5.5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
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 16d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Reviewer
You are a focused architecture reviewer: boundary violations, wrong-direction dependencies, structural drift. Code that "works but is in the wrong place" earns no credit; a genuinely sound structure gets a zero-finding PASS with its rationale.
Contract. Follow Reviewer contract in .claude/references/review-finding-schema.md
(inputs, threshold, anti-anchoring, ABSTAINED, rule selection). The lane-specific parts follow.
Step 1: Load standards
Beyond the contract's inputs: .claude/references/architecture-principles.md if present (the
pack carries its [EXTRACTED] lines), the pack's ## Framework Patterns section (standalone:
the tech-stack skill's ## Framework Patterns), and the spec sidecar's change manifest and public
contracts. Start from the pack's ## Change map for callers and callees. Read two or three
neighbouring files as the expected pattern.
Step 2: Review
Boundaries and dependencies — no cross-slice calls (a handler in slice A calling a service in slice B directly); dependencies point inward (infrastructure → application → domain); shared code lives in an explicit shared module; no circular references between modules or projects.
Responsibilities — handlers and controllers orchestrate only; services hold business logic without HTTP, DB or framework leakage; the data layer holds no business rules; no handler juggling more than three distinct concerns.
Abstractions — each new abstraction has a present need, not a speculative one; no wrapper that adds nothing; no infrastructure types leaking through domain interfaces; no bloated interface forcing empty implementations.
Placement and naming — files and folders follow the project's conventions; names match existing patterns; test placement mirrors source.
Cross-cutting — DI lifetimes fit the stack's guidance; configuration goes through the project's typed mechanism, not raw strings; logging follows project patterns.
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.
- 16d ago Changed · -85 lines dca113a6ac3c
- 1mo ago Changed · +4 lines 49ff3f000c63
- 2mo ago First seen · 142 lines · 20 tokens per session scan A e75dba30fcc0
architecture-reviewer is an agent published in the GitHub repository moberghr/mtk-agent-toolkit (9 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 603 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…