architecture-verify

architecture-verify is an agent for Claude Code from Ramilito/kubectl.nvim. It costs 27 tokens per session (1,127 once invoked), scanned A, original, Apache-2.0.

A specialist that checks whether a codebase follows documented architecture rules by examining dependency graphs and selected files. A dependency graph shows which parts of a program rely on which other parts.

In plain words
What is it for?
Use it to verify architecture health, check dependency boundaries, and confirm that resources or other components follow the required patterns.
Why use it?
It can find forbidden dependencies and pattern violations without reading every line of source code. This helps detect architecture drift as a project changes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

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/ramilito/kubectl.nvim/architecture-verify
Clone the repo
git clone --depth 1 https://github.com/Ramilito/kubectl.nvim

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 architecture-verify

README.md
[![agentmods](https://agentmods.dev/badge/agents/ramilito/kubectl.nvim/architecture-verify.svg)](https://agentmods.dev/agents/ramilito/kubectl.nvim/architecture-verify)
Your own site
<a href="https://agentmods.dev/agents/ramilito/kubectl.nvim/architecture-verify"><img src="https://agentmods.dev/badge/agents/ramilito/kubectl.nvim/architecture-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,127 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 5.1 $0.00027 $0.01127
Opus 5 $0.00014 $0.00563
Sonnet 5 $0.00005 $0.00225
Haiku 4.5 $0.00003 $0.00113

Measured yesterday against content hash 9cf1cb5b0448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architecture-verify 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 yesterday.

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-verify.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Verification Subagent

Verifies codebase against architecture contract. Works with dependency graphs, not source code.

Overview

This subagent verifies the codebase adheres to the architecture contract by:

  1. Extracting dependency graphs (cheap)
  2. Checking against documented rules
  3. Sampling files only to verify pattern conformance

Invocation

"Verify architecture health"
"Check for architecture violations"
"Verify resource pattern conformance"

Phase 1: Extract Dependency Graph

Run these commands to build the graph (zero tokens):

Lua Dependencies

# Core -> * dependencies
for f in lua/kubectl/*.lua; do
  echo "=== $f ==="
  grep "^local.*require" "$f" | sed 's/.*require("\([^"]*\)").*/\1/'
done

# Resources -> * dependencies
for f in lua/kubectl/resources/*/init.lua; do
  echo "=== $f ==="
  grep "^local.*require" "$f" | sed 's/.*require("\([^"]*\)").*/\1/'
done

# Views -> * dependencies
for f in lua/kubectl/views/*/init.lua; do
  echo "=== $f ==="
  grep "^local.*require" "$f" | sed 's/.*require("\([^"]*\)").*/\1/'
done

# Actions -> * dependencies
for f in lua/kubectl/actions/*.lua; do
  echo "=== $f ==="
  grep "^local.*require" "$f" | sed 's/.*require("\([^"]*\)").*/\1/'
done

Rust Dependencies

# Module -> module dependencies
for f in kubectl-client/src/*.rs; do
  echo "=== $f ==="
  grep "^use crate::" "$f" | sed 's/use crate::\([^:;{]*\).*/\1/'
done

Phase 2: Verify Against Contract

With the dependency graph extracted, check these rules:

Lua Rules to Verify

Rule How to Check
Utils is leaf No require in utils/*.lua that points outside utils
Client is leaf No require in client/*.lua that points outside client
Resources don't cross-require Resources only require base_resource, not other resources
Views don't require resources No kubectl.resources.* in views/*/init.lua
Actions don't require resources No kubectl.resources.* in actions/*.lua

Read the full file on GitHub · 174 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. yesterday First seen · 174 lines · 27 tokens per session scan A 9cf1cb5b0448

Subscribe to this mod's changes

architecture-verify is an agent published in the GitHub repository Ramilito/kubectl.nvim (537 stars, last pushed 22d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,127 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 2026-09-04.

Related

Other agents, from other repositories

claworc-dev-troubleshooter

Use this agent when the user reports issues with the local Claworc development environment, encounters unexpected behavior in the control plane backend, frontend, LLM proxy, or running OpenClaw instances, or needs help diagnosing why something isn't working as expected. The agent assumes the environment is already…

gluk-w/claworc · 74 tokens

k8s-pod-checker

Use this agent PROACTIVELY when troubleshooting Kubernetes pod issues or performing health checks. This includes diagnosing CrashLoopBackOff, ImagePullBackOff, pending pods, OOMKilled pods, or general pod health assessment across namespaces.

lando-labs/cami · 54 tokens

devops-troubleshooter

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use…

viksant/vibe-coding-tools-content · 63 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

loom-advisor

Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.

cosmix/loom · 53 tokens