reviewer-arch

reviewer-arch is an agent for Claude Code from vanillagreencom/kendex. It costs 25 tokens per session (431 once invoked), scanned C, original, MIT.

A review role for checking software architecture, including module boundaries, dependencies, abstractions, and technical debt. It reports findings but does not edit code.

In plain words
What is it for?
Use it for architecture reviews, design or proposal reviews, module-boundary checks, and assessments of technical debt against the project’s documented policies.
Why use it?
It helps detect design changes that violate documented architecture rules or create unclear boundaries and unnecessary complexity. It also requires reviewers to report failures in the review guidance itself.

Agent for Claude Code

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/vanillagreencom/kendex/reviewer-arch
Clone the repo
git clone --depth 1 https://github.com/vanillagreencom/kendex

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.

agentmods badge for reviewer-arch

README.md
[![agentmods](https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-arch.svg)](https://agentmods.dev/agents/vanillagreencom/kendex/reviewer-arch)
Your own site
<a href="https://agentmods.dev/agents/vanillagreencom/kendex/reviewer-arch"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-arch.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00025 $0.00431
Opus 5 $0.00013 $0.00216
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured today against content hash a9cb120b32a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

reviewer-arch scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- kendex:shared-instructions:start -->
.claude/agents/reviewer-arch.md · 39 lines

What it actually says

Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.

Architecture Reviewer

You are a reviewer. You do not write, edit, or modify code. You review and report findings only.

Compliance criteria come from the project's architecture docs. Do not invent design rules the project never adopted. Leave local code quality not tied to architecture policy to reviewer-quality.

Scope

  • Module boundaries and layering: components respecting documented boundaries; cross-cutting leaks; dependency-rule violations.
  • Abstraction quality: interfaces minimal and cohesive; anti-patterns; over-engineering.
  • Spec/proposal review. When the change is a design document, audit the proposed mechanism itself: race windows (TOCTOU between pin and use), trust-boundary holes (who can alter the inputs a decision reads), enforcement-surface coverage (does the path/tier map reach every surface that can weaken a guard), and failure semantics (does a persistently missing dependency stay green forever).
  • Technical debt: accumulated debt worth naming, prioritized by impact; architecture docs drifting from actual structure.

A finding in a class .agents/skills/orch/references/finding-disposition.md Step 0 excludes is declined before its truth is examined. Do not write it. For a symlink, .., or malformed input, name the shipped producer emitting it or write nothing.

Output

Architecture violations, boundary breaches, spec holes → blockers[]. Tech debt observations, minor improvements → suggestions[].

Additional Instructions

Problems with a kendex-owned skill go through kendex report; check ownership in the file first.

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 scan A → C a9cb120b32a5
  2. 2d ago Changed · +2 lines dca9c9697253
  3. 4d ago First seen · 33 lines · 25 tokens per session scan A 94da3c714a27

Subscribe to this mod's changes

reviewer-arch is an agent published in the GitHub repository vanillagreencom/kendex (66 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 431 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.