lowy

A method for deciding where code boundaries should go by grouping together things likely to change for the same reason. It is based on software-design ideas associated with Juval Löwy and David Parnas.

In plain words
What is it for?
Use it to evaluate module structure, identify unstable areas, improve interfaces, and decide whether a design will remain easier to change.
Why use it?
Grouping code only by its current function can make future changes spread across many modules. This review looks for boundaries that isolate likely sources of change.

Skill for Claude CodeCodex

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 skills/nrdxp/predicate/lowy
Any agent
npx skills add nrdxp/predicate --skill lowy
Clone the repo
git clone --depth 1 https://github.com/nrdxp/predicate

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,151 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 $0.00044 $0.03151
Opus 5 $0.00022 $0.01576
Sonnet 5 $0.00009 $0.00630
Haiku 4.5 $0.00004 $0.00315

Measured 2d ago against content hash c15ee14d166a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lowy 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 2d 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.

skills/lowy/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Volatility Decomposition Review

Evaluate module boundaries and decomposition decisions using Juval Löwy's volatility-based decomposition framework. The core question: do your boundaries encapsulate axes of change, or do they just group related functionality?

[!NOTE] This workflow is the temporal half of the code-spacetime review pair. It reads code as a world-line — what will pull apart, and when? For the spatial half — what's tangled right now? — see /hickey. Run both for full coverage. See engineering.md §8.1.

Attribution: Adapted from Juval Löwy's Righting Software (2019), building on David Parnas, "On the Criteria to Be Used in Decomposing Systems into Modules" (1972). Workflow structure adapted from Srid Ratnakumar's implementation. See also: Volatility-Based Decomposition (book excerpt).


Core Distinction

Functional decomposition groups code by what it does (UserService, PaymentController, AuthModule). Volatility-based decomposition groups code by what is likely to change — and encapsulates each axis of change behind a stable interface.

"This principle governs the design of all practical systems, from houses, to laptops, to jumbo planes, to your own body. To survive and thrive they all encapsulate the volatility of their constituent components." — Löwy

Löwy's electricity analogy: a house's power supply has enormous volatility (AC/DC, 110v/220v, 50/60Hz, solar/grid/generator, wire gauges). All of it is encapsulated behind a receptacle. Without that encapsulation, you'd need an oscilloscope every time you plugged something in. The receptacle is the stable interface; the volatility behind it can change without affecting consumers.

Functional decomposition maximizes the blast radius of change. When boundaries track functionality rather than volatility, a single change cuts across multiple modules. "Functional decomposition is as diverse as the required functionality across all customers and points in time. The resulting huge diversity in the architecture leads directly to out-of-control complexity." Volatility-based decomposition contains the grenade in the vault.

Read the full file on GitHub · 158 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. 2d ago First seen · 158 lines · 44 tokens per session scan A c15ee14d166a

Subscribe to this mod's changes

lowy is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 3,151 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens