DesktopGo: Skill for Claude Code

.claude/skills/maintain-modular-code/SKILL.md

maintain-modular-code is a skill for Claude Code, Codex from Aixbox/DesktopGo. It costs 92 tokens per session (1,242 once invoked), scanned A, original, MIT.

Keep DesktopGo changes modular, reusable, and maintainable. Use when implementing, fixing, refactoring, or reviewing React, TypeScript, JavaScript, or Rust code, especially when creating or modifying components, hooks, stores, domain rules, services, Tauri commands, shared utilities, or already-oversized files.…

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: reads ~/.codex paths; mentions Codex.

This is Aixbox/DesktopGo's own configuration. It tells Claude Code and Codex how to work on DesktopGo 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 DesktopGo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Aixbox/DesktopGo. 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/Aixbox/DesktopGo/desktop/.claude/skills/maintain-modular-code/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Aixbox/DesktopGo

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 maintain-modular-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/aixbox/desktopgo/maintain-modular-code/github.svg)](https://agentmods.dev/skills/aixbox/desktopgo/maintain-modular-code)
Your own site
<a href="https://agentmods.dev/skills/aixbox/desktopgo/maintain-modular-code"><img src="https://agentmods.dev/badge/skills/aixbox/desktopgo/maintain-modular-code/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 maintain-modular-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/aixbox/desktopgo/maintain-modular-code"><img src="https://agentmods.dev/badge/skills/aixbox/desktopgo/maintain-modular-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,242 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 $0.00092 $0.01242
Opus 5.5 $0.00037 $0.00497
Sonnet 5.5 $0.00018 $0.00248
Haiku 4.5 $0.00009 $0.00124

Measured today against content hash 5aed6bace136, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maintain-modular-code 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-changed-files.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/maintain-modular-code/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintain Modular Code

Apply this workflow to every code change. Optimize for clear ownership and stable boundaries, not merely fewer lines or more files.

Project Launch Ownership

  • Never start the DesktopGo application, a Tauri development process, a Vite development or preview server, a browser session, or a native application window for testing.
  • Do not run pnpm dev, pnpm tauri dev, vite, vite preview, tauri dev, cargo run, or any equivalent command that launches the project or keeps a project process running.
  • The user exclusively owns starting and stopping DesktopGo project processes, including processes used for runtime and visual verification.
  • Verify changes with unit tests, linting, builds, static inspection, and runtime evidence supplied by the user.
  • If verification requires launching DesktopGo or one of its servers, report that limitation and ask the user to run it.
  • Inspect an already-running DesktopGo instance only when the user explicitly requests it; never restart, replace, or stop the user's process as part of ordinary verification.

1. Inspect Before Designing

  • Read repository instructions and the relevant neighboring modules.
  • Measure every file likely to change. Treat an oversized file as refactoring pressure, not permission to add more responsibilities.
  • Search before creating a component, hook, helper, type, store action, domain rule, service, or Rust module. Use rg by name, behavior, visible copy, props, and imported APIs.
  • Identify the change's responsibilities: rendering, interaction orchestration, domain policy, state ownership, persistence, IPC, or platform integration.
  • Read references/component-reuse.md whenever UI, hooks, shared types, or utilities are involved.
  • Read references/architecture-boundaries.md whenever a change crosses modules, stores, IPC, persistence, or platform code.

2. Choose Boundaries Before Editing

  • Keep one primary reason to change per module.
  • Keep views focused on rendering and user interaction.
  • Put React lifecycle and workflow coordination in hooks or feature controllers.
  • Put deterministic business decisions and transformations in pure domain modules.
  • Put storage, network, Tauri IPC, filesystem, and operating-system access behind services or adapters.
  • Keep shared state minimal. Derive values instead of duplicating them in stores.
  • Preserve dependency direction; never make a lower-level or shared module import a feature view to save time.
  • Prefer a small cohesive extraction made for the current behavior over a speculative framework.

Read the full file on GitHub · 92 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today First seen · 92 lines · 92 tokens per session scan A 5aed6bace136

Subscribe to this mod's changes

maintain-modular-code is a skill published in the GitHub repository Aixbox/DesktopGo (63 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 1,242 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-07.

Related

maintain-modular-code compared with skills from other repositories

maintain-modular-code next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
maintain-modular-codeAixbox/DesktopGoSkill632d agoMITA92Claude Code, Codex
content-hash-cache-patternaffaan-m/ECCSkill298k4d agoMITA30Claude Code, Kiro
CreateCLIdanielmiessler/LifeOSSkill20kyesterdayMITA88Claude Code, Codex
segment-createJanDeDobbeleer/oh-my-poshSkill24k2d agoMITA42Claude Code, Codex
python-releaseComposioHQ/composioSkill31kyesterdayMITA53Claude Code, Codex
setup-ts-deep-modulesvinvcn/mattpocock-skills-zh-CNSkill5.6k9d agoMITA49Claude Code, Codex
frontend-ai-guideshinpr/claude-code-workflowsSkill7114d agoMITA41Claude Code