sw-engineering

sw-engineering is a skill for Claude Code from jillesca/gNMIBuddy. It costs 58 tokens per session (541 once invoked), scanned A, original, BSD-3-Clause.

A set of software-engineering rules for writing and changing code, covering simplicity, avoiding duplication, modular design, and readable structure.

In plain words
What is it for?
Use it during coding, refactoring, code review, or design work. It guides naming, module boundaries, comments, type choices, and the placement of public functions and helpers.
Why use it?
It gives an agent consistent standards for implementation, refactoring, and object design, helping limit unnecessary complexity and repeated logic.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

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/jillesca/gnmibuddy/sw-engineering
Any agent
npx skills add jillesca/gNMIBuddy --skill sw-engineering
Clone the repo
git clone --depth 1 https://github.com/jillesca/gNMIBuddy

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 sw-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/jillesca/gnmibuddy/sw-engineering.svg)](https://agentmods.dev/skills/jillesca/gnmibuddy/sw-engineering)
Your own site
<a href="https://agentmods.dev/skills/jillesca/gnmibuddy/sw-engineering"><img src="https://agentmods.dev/badge/skills/jillesca/gnmibuddy/sw-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 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 $0.00058 $0.00541
Opus 5 $0.00029 $0.00270
Sonnet 5 $0.00012 $0.00108
Haiku 4.5 $0.00006 $0.00054

Measured 5d ago against content hash dc29ebc46823, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sw-engineering 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 5d 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.

.agents/skills/sw-engineering/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Engineering Standards

Core Principles

Apply all of the following to every code change:

  • DRY — Centralise shared logic; do not duplicate it across modules
  • KISS — Choose the simplest solution that satisfies the requirement
  • YAGNI — Implement only what is needed now; do not add speculative features
  • SOLID — Follow Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion
  • Modularity — Encapsulate distinct concerns in separate modules so each is independently testable
  • Zen of Python — Favour simplicity, readability, and explicitness (import this)

Readability and Structure

Code must read like a book — a reader should be able to follow the flow top to bottom without jumping around:

  • Use clear, descriptive names for every symbol; abbreviations are not acceptable
  • Place public/external functions at the top of a module
  • Place helper functions used by a public function directly below it
  • Place internal/private functions after the helpers
  • Comments explain why something is done, never what — the code itself must be self-explanatory
  • Follow Martin Fowler's refactoring principles: write code that humans understand easily

Object Design and Boilerplate Avoidance

Using dictionaries to encapsulate related data or behaviour is prohibited — use objects instead.

Before creating any new class or abstraction, ask:

  1. Does this object add genuine value, or is it duplicating an existing data structure?
  2. Am I solving a real problem, or adding complexity for the sake of design purity?
  3. Can I work directly with an existing immutable object (e.g. a dataclass)?
  4. Am I copying fields between objects with no transformation? If so, work directly with the source.

Critical balance: readability for humans is the most important quality and must never be sacrificed for theoretical purity. A simple, direct approach that reads well beats a "properly architected" complex solution.

Read the full file on GitHub · 50 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. 5d ago First seen · 50 lines · 58 tokens per session scan A dc29ebc46823

Subscribe to this mod's changes

sw-engineering is a skill published in the GitHub repository jillesca/gNMIBuddy (14 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 58 tokens to every session and 541 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.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens