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 nahisaho/katashiro --skill musubix-best-practicesgit clone --depth 1 https://github.com/nahisaho/katashiroWrote 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/nahisaho/katashiro/musubix-best-practices)<a href="https://agentmods.dev/skills/nahisaho/katashiro/musubix-best-practices"><img src="https://agentmods.dev/badge/skills/nahisaho/katashiro/musubix-best-practices/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/nahisaho/katashiro/musubix-best-practices"><img src="https://agentmods.dev/badge/skills/nahisaho/katashiro/musubix-best-practices.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 | $0.00041 | $0.01761 |
| Opus 5.5 | $0.00016 | $0.00704 |
| Sonnet 5.5 | $0.00008 | $0.00352 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
musubix-best-practices 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 2mo 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MUSUBIX Best Practices Skill
This skill guides you through applying the 17 best practices learned from MUSUBIX virtual projects.
Overview
MUSUBIX has learned these best practices from implementing 14+ virtual projects. Apply them consistently for high-quality code.
Code Patterns (5)
BP-CODE-001: Entity Input DTO
Use Input DTO objects for entity creation instead of multiple parameters.
// ✅ Recommended: Input DTO
interface CreatePetInput {
name: string;
species: string;
ownerId: string;
}
function createPet(input: CreatePetInput): Pet {
return new Pet(input);
}
// ❌ Avoid: Multiple parameters
function createPet(name: string, species: string, ownerId: string): Pet {
// Hard to extend, easy to mix up parameter order
}
BP-CODE-002: Date-based ID Format
Generate IDs with PREFIX-YYYYMMDD-NNN format for sortability.
// ✅ Recommended: Date-based ID
const id = `PET-20260104-001`; // Sortable, traceable
// ❌ Avoid: UUID only
const id = crypto.randomUUID(); // Not human-readable
BP-CODE-003: Value Objects
Use Value Objects for domain concepts.
// ✅ Recommended: Value Object
interface Price {
readonly amount: number;
readonly currency: 'JPY';
}
// ❌ Avoid: Primitive types
const price: number = 1000; // No currency context
BP-CODE-004: Function-based Value Objects
Use interface + factory function instead of classes for Value Objects.
// ✅ Recommended: Interface + Factory Function
interface Price {
readonly amount: number;
readonly currency: 'JPY';
}
function createPrice(amount: number): Result<Price, ValidationError> {
if (amount < 100 || amount > 1_000_000) {
return err(new ValidationError('Price must be between 100 and 1,000,000 JPY'));
}
return ok({ amount, currency: 'JPY' });
}
// ❌ Avoid: Class-based (doesn't work well with TypeScript structural typing)
class Price {
private constructor(readonly amount: number) {}
static create(amount: number): Price { ... }
}
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.
- 2mo ago First seen · 316 lines · 41 tokens per session scan A 995ca8976f78
musubix-best-practices is a skill published in the GitHub repository nahisaho/katashiro (0 stars, last pushed 9mo ago), licensed MIT. It adds 41 tokens to every session and 1,761 once invoked, about $0.0002 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 2026-08-31.
musubix-best-practices compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| musubix-best-practicesnahisaho/katashiro | Skill | 0 | 9mo ago | MIT | A | 41 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |