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.
npx agentmods add skills/getlytos/lytos-cli/code-structurenpx skills add getlytos/lytos-cli --skill code-structuregit clone --depth 1 https://github.com/getlytos/lytos-cliWhat 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 | $0.00048 | $0.02162 |
| Opus 5 | $0.00024 | $0.01081 |
| Sonnet 5 | $0.00010 | $0.00432 |
| Haiku 4.5 | $0.00005 | $0.00216 |
Grade A, and why
code-structure 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 yesterday.
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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Code Structure
This skill defines the rules for file structure, naming, and code organization on a project using Lytos. An agent loaded with this skill produces clean, consistent, and maintainable code.
When to invoke this skill
- When writing any new code
- During a refactoring
- As a complement to the code-review skill to verify structure
- When creating a new module or component
Foundational principles
The rules in this skill are practical applications of established software design principles:
- Single Responsibility (SRP) — each file, class, or function has one reason to change. This is why we enforce the 300-line rule and one-function-one-job.
- Dependency Inversion (DIP) — depend on abstractions, not implementations. High-level modules should not import low-level details directly. This enables testing and swapping implementations.
- High cohesion, low coupling — related code stays together (cohesion), unrelated modules interact through narrow interfaces (coupling). A module that needs to import half the codebase is a design smell.
- YAGNI — You Aren't Gonna Need It. Do not build abstractions for hypothetical future requirements. Three similar lines of code is better than a premature abstraction.
You do not need to memorize these names. The rules below make them concrete.
Fundamental rule — 300 lines max per file
A file must never exceed 300 lines of code (excluding comments and blank lines).
Why: a file that's too long is a sign of multiple responsibilities. It is harder to read, test, and maintain.
When a file exceeds 300 lines:
- Identify the distinct responsibilities in the file
- Extract each responsibility into its own file
- Keep the original file as an entry point if needed
- Update imports and dependencies
Separation of concerns
Principle
Each file, each function, each class has one single reason to change.
In practice
| Bad | Good |
|---|---|
| One file handling the route, validation, business logic, and response | Route -> Controller -> Service -> Repository |
| One function that computes, formats, and sends | compute() + format() + send() |
| A React component that fetches, processes, and displays | Hook useProducts() + Component ProductList |
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.
- yesterday First seen · 320 lines · 48 tokens per session scan A 6dd34f10fb69
code-structure is a skill published in the GitHub repository getlytos/lytos-cli (2 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 2,162 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…