AI-TadPole-OS: Skill for Claude Code

.agent/skills/improve-codebase-architecture/SKILL.md

improve-codebase-architecture is a skill for Claude Code from DDS-Solutions/AI-TadPole-OS. It costs 32 tokens per session (657 once invoked), scanned A, original, MIT.

A codebase architecture review skill that finds hard-to-maintain modules and suggests refactoring opportunities. A module is a part of a program with a defined interface and implementation.

In plain words
What is it for?
Scanning Git commit hotspots, identifying refactoring candidates, and producing visual HTML reports with Mermaid diagrams.
Why use it?
It exposes places where callers know too much or where small changes require edits across many files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is DDS-Solutions/AI-TadPole-OS's own configuration. It tells Claude Code how to work on AI-TadPole-OS 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 AI-TadPole-OS configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DDS-Solutions/AI-TadPole-OS. 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/DDS-Solutions/AI-TadPole-OS/main/.agent/skills/improve-codebase-architecture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OS

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 improve-codebase-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/improve-codebase-architecture/github.svg)](https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/improve-codebase-architecture)
Your own site
<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/improve-codebase-architecture/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 improve-codebase-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/improve-codebase-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 657 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 $0.00032 $0.00657
Opus 5 $0.00016 $0.00329
Sonnet 5 $0.00006 $0.00131
Haiku 4.5 $0.00003 $0.00066

Measured 6d ago against content hash c318798132f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

improve-codebase-architecture 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 6d 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.

.agent/skills/improve-codebase-architecture/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[!IMPORTANT] AI Context & Knowledge Heritage

  • Subsystem: Agent Skills Registry / improve-codebase-architecture
  • Architecture: @docs ARCHITECTURE:Documentation
  • Failure Path: Information drift, legacy terminology, or documentation mismatch.
  • Observability: Traceability via execution/parity_guard.py ([SKILL])

Codebase Architecture Improvement Protocol

Scan the codebase for architectural friction and propose deepening opportunities—refactors that transform shallow modules into deep ones.


1. Deep Module Vocabulary

Every proposal must strictly use deep module design terms:

  • Module: Scale-agnostic unit with an interface and implementation (function, struct, package, tier slice).
  • Interface: Everything a caller must know (type signature, invariants, error modes, performance bounds).
  • Depth: Ratio of implementation capability to interface complexity. (Deep = high capability behind small surface).
  • Seam: Location where behavior can be altered without editing callers.
  • Adapter: Concrete implementation filling a seam slot.
  • Leverage: Capability callers gain per unit of interface learned.
  • Locality: Concentration of changes, bugs, and verification in one place.

2. Exploration Phase

  1. Scan Commit Hot Spots: Run git log --oneline -n 30 to identify high-churn modules.
  2. Apply Deletion Test: If you delete a module, does it concentrate complexity (deep module), or merely scatter it (shallow module)?
  3. Identify Friction:
    • Shallow interfaces almost as complex as implementations.
    • Pure functions extracted for testing where real bugs hide in caller wiring (poor locality).
    • Tightly-coupled modules leaking across seams.

3. Generate Visual HTML Report

Write an offline HTML report to .tmp/reports/architecture-review-<timestamp>.html.

HTML Report Requirements

  • CDN Styling: Tailwind CSS CDN + Mermaid CDN.
  • Visual Cards: Render cards for each refactoring candidate:
    • Modules/Files Involved: Relative file paths.
    • Problem Statement: Architecture friction described in terms of locality & depth.
    • Proposed Solution: Clear refactoring description.
    • Before / After Diagrams: Mermaid sequence/flowcharts showing structural deepening.
    • Recommendation Badge: Strong, Worth Exploring, Speculative.
  • Top Recommendation: Clear summary of the highest-leverage candidate.

Read the full file on GitHub · 59 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. 6d ago First seen · 59 lines · 32 tokens per session scan A c318798132f2

Subscribe to this mod's changes

improve-codebase-architecture is a skill published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 657 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

walkeros-understanding-development

Use when contributing to walkerOS, before writing code, or when unsure about project conventions. Covers build/test/lint workflow, XP principles, folder structure, and package usage.

elbwalker/walkerOS · 41 tokens

architecture-audit

Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…

org2AI/ORG2 · 70 tokens

react-frontend

React, TypeScript, and Next.js patterns for frontend development. Use when building React components, managing state, fetching data, optimizing performance, or working with Next.js App Router. Covers React 18-19, hooks, Server Components, and type-safe patterns.

iliaal/whetstone · 57 tokens

review-external-prs

Triage open solana-foundation/solana-com pull requests from non-member authors with gh, screen every submission for scams and low-trust products, enforce the repository's signed-and-squashed commit requirement, safely close ineligible cruft when authorized, and write a maintainer report. Use when asked to review…

solana-foundation/solana-com · 94 tokens

react-application-structure

Establishes or reviews the directory layout, feature boundaries, state design, routing approach, and data-fetching conventions for a React 18+ TypeScript application. Invoked when the user asks to structure a React app, set up a scalable architecture, or review React project organization.

soulcodex/agentic · 63 tokens

next-application-structure

Establishes or reviews directory layout, server/client boundaries, routing, data-fetching strategy, and testing structure for Next.js 14+ App Router TypeScript applications. Invoked when the user asks to structure a Next app, set App Router conventions, or review architecture for React parity.

soulcodex/agentic · 64 tokens