Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/0xMassi/claude-skillsnpx agentmods add skills/0xmassi/claude-skills/typescript-strictWrote 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/0xmassi/claude-skills/typescript-strict)<a href="https://agentmods.dev/skills/0xmassi/claude-skills/typescript-strict"><img src="https://agentmods.dev/badge/skills/0xmassi/claude-skills/typescript-strict/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/0xmassi/claude-skills/typescript-strict"><img src="https://agentmods.dev/badge/skills/0xmassi/claude-skills/typescript-strict.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 | $0.00081 | $0.03079 |
| Opus 5.5 | $0.00032 | $0.01232 |
| Sonnet 5.5 | $0.00016 | $0.00616 |
| Haiku 4.5 | $0.00008 | $0.00308 |
Grade A, and why
typescript-strict 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Strict Standard
Rules extracted from 10+ production TypeScript codebases. All projects use strict: true.
CRITICAL: Type Safety Rules
TS-01: Never use any
// BAD
function process(data: any) { return data.value; }
const handler = (e: any) => console.log(e);
// GOOD
function process(data: Record<string, unknown>) { return "value" in data ? data.value : undefined; }
const handler = (e: MouseEvent) => console.log(e.target);
// ACCEPTABLE: Library integration boundaries (shadcn/ui props, Tauri responses)
// Must add a comment explaining why
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- CodeMirror extension type
Exceptions (document each with a comment):
- Third-party library props that genuinely require
any - Generic catch blocks:
catch (e: unknown)then narrow
TS-02: Avoid as type assertions
// BAD
const user = response as User;
const el = document.getElementById("root") as HTMLDivElement;
// GOOD: use type guards
function isUser(data: unknown): data is User {
return typeof data === "object" && data !== null && "id" in data;
}
if (isUser(response)) { /* response is User here */ }
// GOOD: use generics
const el = document.getElementById("root");
if (el instanceof HTMLDivElement) { /* el is HTMLDivElement here */ }
// ACCEPTABLE (rare): When you KNOW the type and can't prove it
// Must be `as unknown as T` with a SAFETY comment
const validated = session as unknown as AuthenticatedSession; // SAFETY: verified user.id exists above
When as is acceptable:
- Prisma generated types requiring cast at boundaries
- After runtime validation (Zod parse → safe to assert)
- Event target narrowing after guard:
e.target as Nodeafterif (e.target)
TS-03: Use unknown over any for untyped data
// BAD
function parse(input: any): Config { ... }
// GOOD
function parse(input: unknown): Config {
if (typeof input !== "object" || input === null) throw new Error("Invalid input");
// Narrow from unknown
}
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 · 451 lines · 81 tokens per session scan A 1597ecd08607
typescript-strict is a skill published in the GitHub repository 0xMassi/claude-skills (8 stars, last pushed 6mo ago), licensed MIT. It adds 81 tokens to every session and 3,079 once invoked, about $0.0003 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.
Other skills, from other repositories
react-component-generator
Generate React components with TypeScript, proper props, hooks, and accessibility. Use when creating new React components, UI elements, or refactoring existing components.
kysely
Guidelines for developing with Kysely, a type-safe TypeScript SQL query builder with autocompletion support.
drizzle-orm
Guidelines for developing with Drizzle ORM, a lightweight type-safe TypeScript ORM with SQL-like syntax.
deno-typescript
Guidelines for developing with Deno and TypeScript using modern runtime features, security model, and native tooling.
express-typescript
Guidelines for building robust APIs with Express.js and TypeScript, covering middleware patterns, routing, and security best practices.
fastify-typescript
Guidelines for building high-performance APIs with Fastify and TypeScript, covering validation, Prisma integration, and testing best practices.