design.md: Skill for Claude Code

.agents/skills/typed-service-contracts/SKILL.md

typed-service-contracts is a skill for Claude Code, Codex from google-labs-code/design.md. It costs 38 tokens per session (1,349 once invoked), scanned A, original, Apache-2.0.

A TypeScript design for services that define their inputs, successful outputs, and known failures as explicit data. It uses separate specifications and handlers so business logic has a clear boundary.

In plain words
What is it for?
Use it when building CLIs, libraries, or complex business logic that needs strict validation, input parsing, typed results, and separate tests for validation and behavior.
Why use it?
It helps prevent invalid input and unexpected exceptions from spreading through an application, especially when every failure must be handled deliberately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is google-labs-code/design.md's own configuration. It tells Claude Code and Codex how to work on design.md itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything design.md configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is { val: '../etc/passwd', err: 'No traversal allowed' },.

About the project

DESIGN.md is a file format that records a visual identity for coding agents using structured design tokens alongside written guidance. It helps agents apply a design system consistently when generating user interfaces.

google-labs-code/design.md · 27,774 stars · on GitHub · stitch.withgoogle.com

Reuse

Borrowing it

Nothing to install: this file belongs to google-labs-code/design.md. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/google-labs-code/design.md/main/.agents/skills/typed-service-contracts/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/google-labs-code/design.md

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for typed-service-contracts

README.md
[![agentmods](https://agentmods.dev/badge/skills/google-labs-code/design.md/typed-service-contracts.svg)](https://agentmods.dev/skills/google-labs-code/design.md/typed-service-contracts)
Your own site
<a href="https://agentmods.dev/skills/google-labs-code/design.md/typed-service-contracts"><img src="https://agentmods.dev/badge/skills/google-labs-code/design.md/typed-service-contracts.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 22 Apr 2026
  • Snyk pass 22 Apr 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 152
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 5.1 $0.00038 $0.01349
Opus 5 $0.00019 $0.00674
Sonnet 5 $0.00008 $0.00270
Haiku 4.5 $0.00004 $0.00135

Measured 8d ago against content hash f97ead50cc4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

typed-service-contracts 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 8d 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.

.agents/skills/typed-service-contracts/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Typed Service Contracts (Spec & Handler Pattern)

This skill defines a Vertical Slice Architecture backed by Design by Contract (DbC) principles. It treats application logic as rigorously defined Units of Work where inputs are parsed (not just validated) and errors are treated as values (Result Pattern) rather than exceptions.

When to use this skill

  • Building CLIs or Libraries: When you need strict boundaries between user input and system logic.
  • Complex Validation: When inputs require transformation (parsing) before being useful (e.g., ensuring a string is a valid file path).
  • High-Reliability Requirements: When you cannot afford unhandled runtime exceptions and need exhaustive error handling.
  • Testing Focus: When you want to separate data validation tests from business logic tests.

Architecture Components

1. The Spec (spec.ts)

The "Contract" or "Port". It defines the What. It must contain:

  • Input Schema: A Zod schema that parses raw input into a valid DTO.
  • Output Schema: A Zod schema defining the successful data structure.
  • Error Schema: A discriminated union of specific failure modes (not generic errors).
  • Result Type: A DiscriminatedUnion of Success | Failure.
  • Interface: The capability definition (e.g., interface ConfigureSpec).

2. The Handler (handler.ts)

The "Implementation" or "Adapter". It defines the How. It must:

  • Implement the Interface defined in the Spec.
  • Be an "Impure" class that handles side effects (File System, API calls).
  • NEVER throw exceptions. It must catch internal errors and map them to the Result type.

How to use it

Step 1: Define the Contract (spec.ts)

Follow this template to define the boundaries.

import { z } from 'zod';

// 1. VALIDATION HELPERS (Reusable Refinements)
export const SafePathSchema = z.string()
  .min(1)
  .refine(p => !p.includes('..'), "No traversal allowed");

// 2. INPUT (The Command) - "Parse, don't validate"
export const MyTaskInputSchema = z.object({
  path: SafePathSchema,
  force: z.boolean().default(false),
});
export type MyTaskInput = z.infer<typeof MyTaskInputSchema>;

// 3. ERROR CODES (Exhaustive)
export const MyTaskErrorCode = z.enum([
  'FILE_NOT_FOUND',
  'PERMISSION_DENIED', 
  'UNKNOWN_ERROR'
]);

// 4. RESULT (The Monad)
export const MyTaskSuccess = z.object({
  success: z.literal(true),
  data: z.string(), // The output payload
});

export const MyTaskFailure = z.object({
  success: z.literal(false),
  error: z.object({
    code: MyTaskErrorCode,
    message: z.string(),
    suggestion: z.string().optional(),
    recoverable: z.boolean(),
  })
});

export type MyTaskResult = 
  | z.infer<typeof MyTaskSuccess> 
  | z.infer<typeof MyTaskFailure>;

// 5. INTERFACE (The Capability)
export interface MyTaskSpec {
  execute(input: MyTaskInput): Promise<MyTaskResult>;
}

Read the full file on GitHub · 190 lines

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. 8d ago First seen · 190 lines · 38 tokens per session scan A f97ead50cc4a

Subscribe to this mod's changes

typed-service-contracts is a skill published in the GitHub repository google-labs-code/design.md (27,774 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,349 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

adapter-express

Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.

trpc/trpc · 67 tokens

trpc-router

Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.

trpc/trpc · 59 tokens

stripe-projects

Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.

e2b-dev/E2B · 51 tokens

chat-sdk

Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…

vercel-labs/open-agents · 191 tokens

nestjs-expert

Creates and configures NestJS modules, controllers, services, DTOs, guards, and interceptors for enterprise-grade TypeScript backend applications. Use when building NestJS REST APIs or GraphQL services, implementing dependency injection, scaffolding modular architecture, adding JWT/Passport authentication, integrating…

Jeffallan/claude-skills · 107 tokens

fastify-best-practices

Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify application — including defining routes, implementing plugins, setting up JSON Schema validation, handling errors, optimising performance, managing authentication…

mcollina/skills · 137 tokens