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 ngocsangyem/MeowKit --skill typescriptgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/typescript)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/typescript"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/typescript/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/ngocsangyem/meowkit/typescript"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/typescript.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 | $0.00043 | $0.01390 |
| Opus 5 | $0.00022 | $0.00695 |
| Sonnet 5 | $0.00009 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
mk:typescript 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Expert
Strict TypeScript patterns for type safety, null handling, and modern best practices.
When to Use
Auto-activate on: .ts, .tsx, .js, .jsx files, type errors, ESLint issues, "fix types", "add types", "TypeScript help"
Explicit: /mk:typescript [concern]
Do NOT invoke for: Vue-specific patterns (use mk:vue), visual design (use mk:frontend-design)
Workflow Integration
Operates in Phase 3 (Build GREEN). Output supports the developer agent.
Process
- Detect concern — type error? new code? refactor? ESLint config?
- Load relevant reference — strict-null, type-safety, utility-types, or eslint
- Apply patterns — implement using strict TS patterns from references
- Verify —
npx tsc --noEmitmust pass with zero errors
Core Rules (always apply)
- NEVER use
any— useunknown+ type guards (security-rules.md) - NEVER use
type assertion— useunknown+ type guards (security-rules.md) - NEVER use implicit truthiness for null checks — use explicit
=== null || === undefined - ALWAYS use strict TypeScript config:
strict: true,noUncheckedIndexedAccess: true - ALWAYS use
typeimports:import type { X } from 'y' - PREFER named exports over default exports
- PREFER discriminated unions over type assertions
Anti-Patterns
| Don't | Do Instead |
|---|---|
as any or as unknown as X |
Proper type narrowing with guards |
if (value) for null check |
if (value !== null && value !== undefined) |
export default |
export const X / export function X |
Object type |
Record<string, unknown> |
| Implicit return types | Explicit return type annotations |
enum (runtime overhead) |
as const satisfies or union types |
What ships with it
2 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.
- 5d ago First seen · 113 lines · 43 tokens per session scan A 020d812c7e10
mk:typescript is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,390 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 2026-09-03.
Other skills, from other repositories
phx-investigate
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.
phx-trace
Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes, or understanding how a bug reaches code.
ag-corrigir-tipos
Corrige erros TypeScript com auto-routing. Scan (diagnosticar), Fix (batch incremental), Sweep (varredura com ratchet), Audit-any (auditoria proativa de any/inferencias fracas). Substitui workflow manual de typecheck.
biome-linting
Analyze, fix, and validate Biome linting workflows. Use when JavaScript or TypeScript projects need Biome commands, diagnostics, safe fixes, or CI lint gates.
bun-runtime
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
build-debug
Diagnose TypeScript, Vite, webpack, Rollup, esbuild, and Sass build errors that reproduce locally and are unrelated to CI/CD or npm toolchain failures. Load ONLY for pure build-tool errors. Bounded, non-destructive triage; never auto-runs cache wipes or version downgrades without explicit confirmation.