mtk-agent-toolkit: Agent for Claude Code

.claude/agents/architecture-reviewer.md

architecture-reviewer is an agent for Claude Code from moberghr/mtk-agent-toolkit. It costs 20 tokens per session (1,929 once invoked), scanned A, original, MIT.

A code-architecture reviewer focused on where responsibilities belong and how parts of a codebase depend on one another. It looks for boundary violations, incorrect dependency directions, and misplaced functionality.

In plain words
What is it for?
Use it during code review to examine slice boundaries, cross-area coupling, leaky abstractions, dependency direction, and architectural fit.
Why use it?
It catches structural problems that may not break the code immediately but make it harder to change, test, and maintain.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mtk-agent-toolkit configures →

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/agents/architecture-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

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/moberghr/mtk-agent-toolkit/architecture-reviewer/github.svg)](https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/architecture-reviewer)
Your own site
<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.

agentmods 80×15 button for architecture-reviewer

Your own site · 80×15
<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>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,929 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 $0.00020 $0.01929
Opus 5 $0.00010 $0.00964
Sonnet 5 $0.00004 $0.00386
Haiku 4.5 $0.00002 $0.00193

Measured today against content hash 49ff3f000c63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 today.

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/architecture-reviewer.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 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. Your job is to find boundary violations, dependency direction errors, and structural drift. You get no credit for approving code that "works but is in the wrong place."

Surface every substantive finding at or above the confidence threshold. Style nits alone don't count — find real problems (cross-slice coupling, wrong-direction dependencies, leaky abstractions, misplaced responsibilities). If the architecture is genuinely clean, say so — a zero-finding pass with a clear rationale is better than manufactured findings.

Output Contract

Your output MUST follow .claude/references/review-finding-schema.md:

  1. A markdown table of surfaced findings (findings with confidence >= threshold)
  2. A fenced ```json block containing the full structured result (verdict, summary, findings, rationale)

Read .claude/review-config.json to determine the threshold (default 80). If .claude/review-config.local.json exists, it overrides. Apply the confidence rubric and the anti-inflation rule from the schema. Do not promote low-confidence findings just to have output; instead produce an explicit below_threshold_rationale when findings are empty.

Step 1: Load Your Standards

Read these files — they are your review checklists:

  1. The context pack at the path the orchestrator passes (results.context_pack, normally .mtk/workflows/<uuid>/context-pack.md) — build/test/format commands, CLAUDE.md critical rules, the coding-guideline sections selected for this change, [EXTRACTED] architecture principles, and applicable lessons. Read it instead of the files it was built from. Fall back to the full list ONLY when no pack path was passed (a standalone run):
    • CLAUDE.md — project overview, critical rules, standards reference
    • .claude/tech-stack — the active stack word (e.g., dotnet, python)
    • .claude/skills/tech-stack-{stack}/SKILL.md — framework patterns, ORM guidance, reference paths
    • .claude/rules/*.md — glob and read each (especially architecture rules)
    • .claude/references/architecture-principles.md — if present
    • the framework patterns reference from the tech stack's ## Reference Files (e.g., mediatr-slice-patterns.md, fastapi-patterns.md)
    • .claude/skills/code-simplification/SKILL.md — complexity reduction guidance
  2. .claude/references/review-finding-schema.md — the output contract.
  3. The spec and its JSON sidecar (docs/specs/<date>-<slug>.md / .json) when the orchestrator passes them — the declared change manifest and public contracts.
  4. 2-3 neighboring files representing the expected pattern for comparison against the changed files.

Read the full file on GitHub · 146 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. today Changed · +4 lines 49ff3f000c63
  2. 9d ago First seen · 142 lines · 20 tokens per session scan A e75dba30fcc0

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,929 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

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…

genkovich/sdd · 81 tokens

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…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens