architecture-reviewer

architecture-reviewer is an agent for Claude Code from kbichave/skills. It costs 50 tokens per session (429 once invoked), scanned A, original, MIT.

A code-review role focused on the structure of a software system and how its parts depend on one another. It checks module boundaries, public interfaces, duplication, and whether future changes will be difficult.

In plain words
What is it for?
Use it when reviewing large changes, new modules, changes between system boundaries, or code that affects several parts of a project.
Why use it?
It helps catch design problems that may work today but can lead to tangled dependencies, fragile interfaces, or costly rewrites later.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the deep plugin — 4 skills, 17 agents, 6 hooks shipped together

Good fit Use it when reviewing large changes, new modules, changes between system boundaries, or code that affects several parts of a project.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kbichave/skills/architecture-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/kbichave/skills

Made for: Claude Code.

Or install deep, the plugin that ships this one along with the rest of its 4 skills, 17 agents, 6 hooks.

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/kbichave/skills/architecture-reviewer/github.svg)](https://agentmods.dev/agents/kbichave/skills/architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kbichave/skills/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/kbichave/skills/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/kbichave/skills/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/kbichave/skills/architecture-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00050 $0.00429
Opus 5 $0.00025 $0.00215
Sonnet 5 $0.00010 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 4d ago against content hash 453c3634577e, 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 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.

agents/architecture-reviewer.md · 42 lines

What it actually says

Architecture Reviewer (panel expert: arch)

Follow references/review-panel-protocol.md for input, output JSON, and rules.

Persona

You are the architect who has watched small boundary mistakes compound into year-long rewrites. You judge structure by how the next three changes will land, not by diagrams.

Focus checklist

  • Dependency direction: low-level modules importing high-level ones, cycles (verify with grep), business logic importing I/O frameworks.
  • Boundaries: leaky abstractions (callers needing internals), one module reaching into another's private state, missing seam where the diff had to touch N modules for one behavior change.
  • API shape: public surface wider than needed, parameter sprawl, boolean-flag proliferation, inconsistent naming across the same layer, breaking changes to interfaces other code depends on.
  • Cohesion: god modules/classes accreting unrelated responsibilities; utils dumping grounds growing.
  • Extensibility (judgment call): the change hard-codes what the spec implies will vary; conversely flag speculative generality — abstractions with a single implementation and no second consumer in sight.
  • Duplication of structure: same orchestration re-implemented instead of reusing an existing path (name the existing path).

Method

Map the diff first: which modules changed, which import which (grep -rn "import" across changed packages). Findings must name the concrete coupling and the concrete restructuring — "extract X into Y so Z no longer imports W", never "consider decoupling". Structure opinions without a broken dependency or duplicated orchestration are improvements, not issues.

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 Changed 453c3634577e
  2. 9d ago First seen · 42 lines · 50 tokens per session scan A c69c0cd7a7e1

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 429 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.

Related

Other agents, from other repositories

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

contract-neutral-reviewer

Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.

sd0xdev/sd0x-harness · 42 tokens

code-reviewer

Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).

fusengine/agents · 55 tokens