ares: Skill for Claude Code

.ai/skills/spaghetti-code-review/SKILL.md

spaghetti-code-review is a skill for Claude Code, Codex from okfriansyah-moh/ares. It costs 0 tokens per session (864 once invoked), scanned A, original, Apache-2.0.

A review of a codebase for tangled code that is difficult and risky to change. It classifies functions, files, and folders by maintainability risk and suggests concrete improvements.

In plain words
What is it for?
Use it to assess a repository or selected change, identify healthy areas and critical hotspots, and plan focused refactoring with recommendations.
Why use it?
It shows where mixed responsibilities, hidden side effects, duplication, unclear dependencies, or brittle control flow make future work harder.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is okfriansyah-moh/ares's own configuration. It tells Claude Code and Codex how to work on ares 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 ares configures →

Reuse

Borrowing it

Nothing to install: this file belongs to okfriansyah-moh/ares. 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/okfriansyah-moh/ares/main/.ai/skills/spaghetti-code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/okfriansyah-moh/ares

Made for: Claude Code, Codex.

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 spaghetti-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/okfriansyah-moh/ares/spaghetti-code-review.svg)](https://agentmods.dev/skills/okfriansyah-moh/ares/spaghetti-code-review)
Your own site
<a href="https://agentmods.dev/skills/okfriansyah-moh/ares/spaghetti-code-review"><img src="https://agentmods.dev/badge/skills/okfriansyah-moh/ares/spaghetti-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 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 $0.00000 $0.00864
Opus 5 $0.00000 $0.00432
Sonnet 5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00086

Measured 7d ago against content hash eeaa5459efd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spaghetti-code-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 7d 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.

.ai/skills/spaghetti-code-review/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spaghetti Code Review

Purpose

Review a codebase for tangled, hard-to-change code and classify functions, files, and folders by maintainability risk with concrete recommendations and solutions.

Inputs

  • Repository structure, source files, tests, generated artifacts, and build configuration.
  • Existing architecture, contribution, style, and testing guidance.
  • Recent diffs or target scope when the review is limited to a feature, PR, package, or module.
  • Available static analysis, test coverage, dependency graph, complexity, duplication, and lint output.

Classification

  • Healthy: clear responsibility, low coupling, readable flow, focused tests, and stable boundaries.
  • Watchlist: mostly understandable, but showing early signs of growth, duplication, long functions, weak names, or scattered knowledge.
  • Tangled: multiple responsibilities, hidden side effects, unclear dependencies, brittle conditionals, or tests that make change difficult.
  • Spaghetti: control flow, state, dependencies, naming, and boundaries are so mixed that local changes are risky without refactoring.
  • Critical Hotspot: high-change or high-impact spaghetti code that also affects security, data integrity, user-visible behavior, releases, or core architecture.

Review Method

  • Start with a repository map: identify languages, entry points, major folders, generated code, test boundaries, and ownership conventions.
  • Review from broad to narrow: classify folders first, then files, then the functions or methods that explain the risk.
  • Use evidence, not taste: cite concrete signals such as branching depth, function length, global state, cyclic dependencies, duplicate logic, mixed abstraction levels, temporal coupling, poor error handling, missing tests, or architecture drift.
  • Separate symptoms from causes: describe what is tangled, why it became risky, and what change pressure will make it worse.
  • Distinguish code smells from intentional design: do not penalize adapters, generated files, simple scripts, or framework glue without evidence of change risk.
  • Prefer incremental repair plans over rewrites unless the code is isolated, low-risk, and cheaper to replace than untangle.

Read the full file on GitHub · 63 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. 7d ago First seen · 63 lines · 0 tokens per session scan A eeaa5459efd7

Subscribe to this mod's changes

spaghetti-code-review is a skill published in the GitHub repository okfriansyah-moh/ares (2 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 864 tokens. 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 skills, from other repositories