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 adonai-labs/agent-runway --skill skill-typescript-coregit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/skill-typescript-core)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/skill-typescript-core"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/skill-typescript-core/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/adonai-labs/agent-runway/skill-typescript-core"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/skill-typescript-core.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 | $0.00087 | $0.00741 |
| Opus 5.5 | $0.00035 | $0.00296 |
| Sonnet 5.5 | $0.00017 | $0.00148 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
typescript-core 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Core
How to invoke
After agent-runway add typescript, the skill is installed at .cursor/skills/typescript-core/. Use:
- Cursor:
@typescript-coreor ask a TypeScript question while editing*.ts/*.tsx(rules auto-attach) - Claude Code: reference
.agent-runway/skills/typescript-core/SKILL.mdor ask in context of TypeScript files
Examples:
- How should I structure this service layer?
- Is this generics pattern idiomatic?
- How do I test this use-case function?
- How do I add structured logging with correlation IDs?
Not sure which skill to use? Start with
/start— it classifies intent and routes to the right skill.
Role
Act as a senior TypeScript engineer with deep experience in scalable application architecture, type system design, testing strategy, and production observability for Node.js and browser targets.
This skill is TypeScript-specific. For system design and trade-off reasoning, combine with the architect skill.
Guiding principles
Simplicity first. SOLID, DRY, and Clean Architecture apply at the right scale — not ceremonially.
- Start with the simplest structure that satisfies the requirement
- Add layers, interfaces, and patterns only when there is a proven reason (variation, instability, scale)
- One responsibility per unit; no mixed concerns in a single function or module
- DRY for business logic and decision rules; duplication in glue code is acceptable
- Prefer explicit code over clever code; readability is a feature
What this skill helps with
- Project structure scaled to complexity — flat for small, layered for large
- Type-safe patterns — service layer, repository, Result types, DI
- Testing: unit, integration, and API testing with Vitest/Jest
- Security: input validation, JWT, secrets hygiene, dependency audit
- Observability: structured logging with Pino, OpenTelemetry
- Toolchain: tsconfig, ESM/CJS, build scripts
Skill files
| File | Contents |
|---|---|
| architecture.md | Project structure, layering, dependency rules, monorepo patterns |
| patterns.md | DI, service layer, repository, Result types, CQRS-lite |
| testing.md | Test strategy, Vitest/Jest setup, mocking, integration testing |
| security.md | Input validation, OWASP, JWT, secrets, dependency hygiene |
| observability.md | Pino logging, OpenTelemetry, correlation IDs, health checks |
| reference.md | Toolchain, tsconfig options, common scripts, ESM/CJS |
What ships with it
6 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.
- 1mo ago First seen · 72 lines · 87 tokens per session scan A ed62884fcb52
typescript-core is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 28d ago), licensed MIT. It adds 87 tokens to every session and 741 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 2026-09-03.
Other skills, from other repositories
node-typescript-service
Use when building or extending a TypeScript service on Node.js - Fastify, NestJS, Express or Hono, runtime validation at the boundary, strict types, the repository's ORM and migrations, async error handling, graceful shutdown.
code-review-typescript
Deep TypeScript-specific code review covering type safety, ESM/CJS, async correctness, money precision, and domain modeling. Applied in addition to the generic code-review skill when TypeScript/JavaScript code is detected. Invoked when reviewing TS/JS PRs, TypeScript changes, or performing TypeScript-specific quality…
react-component-design
Designs or reviews React component APIs. Handles prop drilling decisions, composition patterns, controlled/uncontrolled contracts, and minimal public API surfaces for React 18+ TypeScript components. Invoked when creating new components, refactoring existing ones, or reviewing component contracts.
bun
Expert Bun runtime assistance covering high-performance JS/TS execution, built-in bundler, package manager, and test runner. Use when executing TypeScript natively, running fast scripts, or serving HTTP APIs.
express
Expert Express.js assistance covering routing, middleware pipelines, error handling, and REST API design. Use when building Node.js backend services and web APIs.
hono
Expert Hono framework assistance covering ultra-fast routing, Web Standards, multi-runtime support (Cloudflare Workers, Deno, Bun, Node), and RPC. Use when developing edge APIs and lightweight microservices.