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.
curl -O https://raw.githubusercontent.com/Aixbox/DesktopGo/desktop/.claude/skills/maintain-modular-code/SKILL.mdgit clone --depth 1 https://github.com/Aixbox/DesktopGoWrote 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.
[](https://agentmods.dev/skills/aixbox/desktopgo/maintain-modular-code)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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
rgby 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.
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.
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.
- today First seen · 92 lines · 92 tokens per session scan A 5aed6bace136
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.
maintain-modular-code compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maintain-modular-codeAixbox/DesktopGo | Skill | 63 | 2d ago | MIT | A | 92 | Claude Code, Codex |
| content-hash-cache-patternaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 30 | Claude Code, Kiro |
| CreateCLIdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 88 | Claude Code, Codex |
| segment-createJanDeDobbeleer/oh-my-posh | Skill | 24k | 2d ago | MIT | A | 42 | Claude Code, Codex |
| python-releaseComposioHQ/composio | Skill | 31k | yesterday | MIT | A | 53 | Claude Code, Codex |
| setup-ts-deep-modulesvinvcn/mattpocock-skills-zh-CN | Skill | 5.6k | 9d ago | MIT | A | 49 | Claude Code, Codex |
| frontend-ai-guideshinpr/claude-code-workflows | Skill | 711 | 4d ago | MIT | A | 41 | Claude Code |