Kubeli: Skill for Claude Code

.claude/skills/software-design-review/SKILL.md

software-design-review is a skill for Claude Code from atilladeniz/Kubeli. It costs 53 tokens per session (4,912 once invoked), scanned A, original, MIT.

A software architecture review based on John Ousterhout’s principles for reducing complexity. It examines code for dependencies, hidden information, unnecessary complexity, and modules that do too little.

In plain words
What is it for?
Use it during architecture reviews, pull-request reviews, refactoring, or code-quality work to find design problems and complexity risks.
Why use it?
It helps identify designs that work today but are difficult to understand or change later. The review focuses on underlying causes instead of only pointing out surface-level defects.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is atilladeniz/Kubeli's own configuration. It tells Claude Code how to work on Kubeli 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 Kubeli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to atilladeniz/Kubeli. 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/atilladeniz/Kubeli/main/.claude/skills/software-design-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/atilladeniz/Kubeli

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 software-design-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/atilladeniz/kubeli/software-design-review/github.svg)](https://agentmods.dev/skills/atilladeniz/kubeli/software-design-review)
Your own site
<a href="https://agentmods.dev/skills/atilladeniz/kubeli/software-design-review"><img src="https://agentmods.dev/badge/skills/atilladeniz/kubeli/software-design-review/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 software-design-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/atilladeniz/kubeli/software-design-review"><img src="https://agentmods.dev/badge/skills/atilladeniz/kubeli/software-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,912 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 239
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 240
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 248
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • low Excessive Agency · line 339
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00053 $0.04912
Opus 5 $0.00026 $0.02456
Sonnet 5 $0.00011 $0.00982
Haiku 4.5 $0.00005 $0.00491

Measured 11d ago against content hash e3c0bcc78fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

software-design-review 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 11d 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.

.claude/skills/software-design-review/SKILL.md · 658 lines

How it starts

The opening of the file, as written. The whole thing — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Design Review (Ousterhout)

You are a software architecture expert following John Ousterhout's "A Philosophy of Software Design" principles strictly.

Your goal is to fight complexity. Complexity is defined as anything that makes a system hard to understand or hard to modify. It is caused by dependencies and obscurity.

Kubeli Tech Stack Context

This codebase uses:

  • Frontend: Vite 7+, React 19, TypeScript
  • Desktop: Tauri 2.0 with Rust backend
  • State: Zustand stores
  • Styling: Tailwind CSS
  • K8s Client: kube-rs (Rust)

When analyzing code ($ARGUMENTS), evaluate against ALL criteria below and watch for Red Flags.


1. Strategic vs. Tactical Programming

Principle: Working code is not enough. You must produce a great design that also works. Tactical programming (quick hacks) accumulates complexity. Strategic programming invests 10-20% extra time for clean designs.

Check: Does this code show investment in design, or quick fixes that will cause problems later?

Red Flags:

  • Tactical tornado: Fast code that leaves a mess for others
  • Quick fixes that add complexity instead of solving root causes
  • Technical debt without plans to repay it

Kubeli Example:

// TACTICAL (bad): Quick fix that leaks implementation
const [pods, setPods] = useState<Pod[]>([]);
const [loading, setLoading] = useState(false);
const [error, setError] = useState<Error | null>(null);
// Every component repeats this pattern...

// STRATEGIC (good): Invest in a proper abstraction
const { data: pods, isLoading, error } = useKubeQuery('pods', namespace);

2. Module Depth (Deep vs. Shallow)

Principle: Modules should be "deep" - hiding significant functionality behind a simple interface. The best modules provide powerful functionality with minimal interface complexity.

Check: Does this code have a complex interface for little functionality?

Red Flags:

  • Shallow modules: Components/functions that do little but expose many props/parameters
  • Classitis: Too many small classes/components
  • Pass-through methods: Functions that only forward arguments to another method

Read the full file on GitHub · 658 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. 11d ago First seen · 658 lines · 53 tokens per session scan A e3c0bcc78fbf

Subscribe to this mod's changes

software-design-review is a skill published in the GitHub repository atilladeniz/Kubeli (380 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 4,912 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 2026-08-30.