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.
git clone --depth 1 https://github.com/MCKRUZ/claude-code-masteryWrote 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/rules/mckruz/claude-code-mastery/coding-style)<a href="https://agentmods.dev/rules/mckruz/claude-code-mastery/coding-style"><img src="https://agentmods.dev/badge/rules/mckruz/claude-code-mastery/coding-style/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/rules/mckruz/claude-code-mastery/coding-style"><img src="https://agentmods.dev/badge/rules/mckruz/claude-code-mastery/coding-style.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 | $0.00532 | $0.00532 |
| Opus 5.5 | $0.00213 | $0.00213 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
coding-style 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Style
Immutability (CRITICAL)
- C#: IReadOnlyList/IReadOnlyDictionary<K,V> for public surfaces, readonly arrays for private backing fields, init-only properties for DTOs/config. Use records for simple value types, but NOT for polymorphic hierarchies (use classes with factory methods instead).
- TypeScript: spread operators, never mutate objects/arrays.
{ ...obj, key }and[...arr, item]. - NgRx reducers: always return new state objects.
File Organization
- Clean Architecture with type-organized layers (Exceptions, Extensions, Interfaces, Models, Services — not feature folders within layers).
- Many small files > few large files. Most files under 150 lines, 400 max.
- High cohesion, low coupling. One class per file.
Naming
- C#: PascalCase (classes/methods/props),
_camelCase(private fields), camelCase (locals/params),Iprefix for interfaces. - TypeScript: PascalCase (types/classes), camelCase (vars/funcs), kebab-case (files).
- Python: snake_case (functions/variables), PascalCase (classes), UPPER_SNAKE_CASE (constants).
Error Handling
- C#: Result for expected failures (validation, auth, business rules). Exceptions only for truly exceptional conditions. Factory methods:
Result<T>.Success(value),Result<T>.Fail(message),Result.ValidationFailure(errors). - Angular: catchError in pipes, use logger service (no console.log), notify user.
- Always: structured JSON logging, never swallow errors silently.
Validation
- C#: FluentValidation on all DTOs, auto-discovered via assembly scanning, applied through MediatR pipeline behavior. Parallel validation with
Task.WhenAll. - Angular: Reactive Forms with validators.
- Validate at system boundaries only — trust internal code.
Dependency Injection
- Each layer provides
DependencyInjection.cswithAdd*Dependencies()extension methods. - Use keyed DI (
AddKeyedSingleton/Transient) for extensible registrations (tools, connectors). - MediatR pipeline behavior order matters — document registration order in DI.
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 · 41 lines · 532 tokens per session scan A 08a23799c596
coding-style is a cursor rule published in the GitHub repository MCKRUZ/claude-code-mastery (11 stars, last pushed 5mo ago), licensed MIT. It adds 532 tokens to every session, about $0.0021 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 cursor rules, from other repositories
caliber-conventions
Caliber project conventions for TypeScript CLI development.
skill-fastapi-api
Padrões DARE para APIs REST em Python + FastAPI + Pydantic v2 + SQLAlchemy 2.0 async + alembic. Routers, dependency injection, schemas Pydantic, OAuth2+JWT, slowapi rate limit, pytest+httpx, OpenAPI auto-gerado.
skill-nestjs-api
Padrões DARE para APIs REST em NestJS + TypeScript + Prisma + Swagger. Modules, Controllers, Services, DTOs com class-validator, Guards JWT, throttler, exceções globais, Jest + Supertest, OpenAPI auto-gerado.
django-python
Rules for writing Python services at PostHog (Python servers powered by the Django framework).
react-typescript
Rules for writing frontend code at PostHog (mostly React + Typescript with Kea).
python--typescript-guide-cursorrules-prompt-file
Cursor rules for Python development with TypeScript guide integration.