coding-standards

Project-specific rules for writing and reviewing code, including naming, imports, error handling, and formatting. They describe the conventions detected in a TypeScript project and explain exceptions such as required .js extensions in local imports.

In plain words
What is it for?
Use them when implementing features, editing TypeScript, or reviewing code quality in the project.
Why use it?
They help an agent produce code that fits the existing project and avoid runtime problems caused by incorrect module imports. They also make code reviews consistent.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/anatomia-dev/anatomia/coding-standards
Any agent
npx skills add anatomia-dev/anatomia --skill coding-standards
Clone the repo
git clone --depth 1 https://github.com/anatomia-dev/anatomia

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00853
Opus 5 $0.00018 $0.00426
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00004 $0.00085

Measured 2d ago against content hash ea2b39b4bb15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-standards 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 2d 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.

.ana/skills/coding-standards/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Standards

Detected

  • Language: TypeScript (292 source files)
  • Functions: camelCase (88%, 1049 sampled)
  • Classes: PascalCase (55%)
  • Files: PascalCase (56%, 297 sampled)
  • Imports: relative (72%)
  • Indentation: spaces, 2 wide
  • Error handling: exceptions (generic)
  • UI: Tailwind CSS

Library Rules

  • All local imports use .js extensions (import { foo } from "./bar.js"). TypeScript compiles without them but ESM resolution crashes at runtime.
  • Use import type for type-only imports, separate from value imports. Prevents runtime imports of pure types.

Rules

  • All imports use .js extensions and node: prefix for built-ins. import * as fs from 'node:fs/promises', import { scanProject } from './scan-engine.js'. Omitting .js compiles fine but crashes at runtime — tsup emits ESM.
  • Use import type for type-only imports, separate from value imports. Never mix types and values in the same import statement.
  • Prefer named exports. No default exports — this is a CLI, no framework requires them.
  • Avoid any — use unknown and narrow with type guards. any is acceptable only for untyped third-party boundaries. Define an interface for complex types — don't escape the type system.
  • Use | null for fields that were checked and found empty. Reserve ?: (optional) for fields that may not have been checked. EngineResult uses | null for all nullable stack fields — follow the same convention.
  • Prefer early returns over nested conditionals. if (!condition) return null; then the main logic flat — not if (condition) { ...long block... }.
  • Error handling has two layers. Commands surface errors to the user: chalk.red message + process.exit(1). Engine functions catch internally and return defaults — a detector failure degrades the scan gracefully, it never crashes it.
  • Engine files (src/engine/) have zero CLI dependencies — no chalk, no commander, no ora. Engine takes data as input and returns results. All user-facing output belongs in src/commands/.
  • Explicit return types on all exported functions. Internal helpers can use inference.
  • Avoid disabling lint rules inline. When necessary, add a comment explaining why the disable is required.
  • Exported functions require @param and @returns JSDoc tags. The eslint rules enforce this — pre-commit will reject missing tags.
  • In JSX text content, use ' for apostrophes. The react/no-unescaped-entities lint rule rejects raw ' characters in JSX — contractions like "don't" must be written as don't.

Read the full file on GitHub · 43 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2d ago First seen · 43 lines · 37 tokens per session scan A ea2b39b4bb15

Subscribe to this mod's changes

coding-standards is a skill published in the GitHub repository anatomia-dev/anatomia (32 stars, last pushed 29d ago), licensed MIT. It adds 37 tokens to every session and 853 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 2026-08-30.

Related

Other skills, from other repositories