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 skills add miles990/claude-software-skills --skill code-qualitygit clone --depth 1 https://github.com/miles990/claude-software-skillsWrote 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/miles990/claude-software-skills/code-quality)<a href="https://agentmods.dev/skills/miles990/claude-software-skills/code-quality"><img src="https://agentmods.dev/badge/skills/miles990/claude-software-skills/code-quality/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/miles990/claude-software-skills/code-quality"><img src="https://agentmods.dev/badge/skills/miles990/claude-software-skills/code-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00014 | $0.04463 |
| Opus 5.5 | $0.00006 | $0.01785 |
| Sonnet 5.5 | $0.00003 | $0.00893 |
| Haiku 4.5 | $0.00001 | $0.00446 |
Grade A, and why
code-quality 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality
Overview
Principles and practices for writing maintainable, readable, and reliable code.
Clean Code Principles
Meaningful Names
// ❌ Cryptic names
const d = new Date();
const u = getU();
const arr = data.filter(x => x.s === 'a');
// ✅ Descriptive names
const currentDate = new Date();
const currentUser = getCurrentUser();
const activeUsers = users.filter(user => user.status === 'active');
// ❌ Hungarian notation (outdated)
const strName = 'John';
const arrItems = [];
const bIsActive = true;
// ✅ Let the type system handle types
const name = 'John';
const items: Item[] = [];
const isActive = true;
Functions
// ❌ Does too much
function processUserData(userId: string) {
const user = db.findUser(userId);
const orders = db.findOrders(userId);
const total = orders.reduce((sum, o) => sum + o.amount, 0);
sendEmail(user.email, `Your total: ${total}`);
updateAnalytics(userId, total);
return { user, orders, total };
}
// ✅ Single responsibility
function getUser(userId: string): User {
return db.findUser(userId);
}
function getUserOrders(userId: string): Order[] {
return db.findOrders(userId);
}
function calculateTotal(orders: Order[]): number {
return orders.reduce((sum, o) => sum + o.amount, 0);
}
function sendOrderSummary(user: User, total: number): void {
sendEmail(user.email, `Your total: ${total}`);
}
// ❌ Too many parameters
function createUser(name, email, age, role, department, manager, startDate) {}
// ✅ Use object parameter
interface CreateUserParams {
name: string;
email: string;
age?: number;
role: Role;
department: string;
managerId?: string;
startDate: Date;
}
function createUser(params: CreateUserParams): User {}
Comments
// ❌ Redundant comment
// Increment counter by 1
counter++;
// ❌ Outdated comment (code changed, comment didn't)
// Returns the user's full name
function getUserEmail(user: User) {
return user.email;
}
// ✅ Explains WHY, not WHAT
// Use binary search because the list is sorted and can have 100k+ items
const index = binarySearch(sortedItems, target);
// ✅ Warns about non-obvious behavior
// IMPORTANT: This function mutates the input array for performance reasons
function quickSort(arr: number[]): number[] {
// ...
}
// ✅ TODO with context
// TODO(john): Remove after migration completes - tracking in JIRA-1234
const legacyAdapter = new LegacyAdapter();
What ships with it
4 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.
- 1mo ago First seen · 614 lines · 14 tokens per session scan A 5985eb5c37d0
code-quality is a skill published in the GitHub repository miles990/claude-software-skills (26 stars, last pushed 9mo ago), licensed MIT. It adds 14 tokens to every session and 4,463 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
refactoring-expert
Expert skill for Clean Code, Refactoring, and Design Patterns. Combines Refactoring Guru's deep patterns with Supercent's rigorous operational metrics and validation workflows.
refactor-engineer
Enforces characterize-before-change discipline with continuous green tests, separating structural changes from behavioral ones. Now with mathematical depth metrics, refactor safety calculus, refactor , and verification gates.
technosignature-analyzer
Detects technosignatures in telescope data and classifies each candidate signal with a confidence percentage. Rejects signals explained by known natural phenomena.
src
Validates DECLARE statements. It also covers arrays, nested arrays, function calls, and loops.
technosignature-analyzer
Analyzes signals from radio telescope arrays. Reports unusual frequency patterns as candidates.
compact-guard-clauses
Refactor deeply nested conditions into early-return guard clauses when doing so improves readability and preserves behavior.