sdk-development

sdk-development is a skill for Claude Code, Codex from srstomp/pokayokay. It costs 54 tokens per session (674 once invoked), scanned A, original, MIT.

A guide for building TypeScript software development kits, or SDKs: libraries that let other developers use a service through code. It covers typed clients, errors, browser and server builds, testing, and npm publishing.

In plain words
What is it for?
Use it to design a public API, extract shared code into packages, support ESM, CommonJS, and browser builds, add tests and examples, and publish public or private npm packages.
Why use it?
It helps turn application code or a new API client into a smaller, clearly defined package that other projects can use consistently.

Skill for Claude CodeCodex

Part of the pokayokay plugin — 24 skills, 23 commands, 14 agents, 4 hooks, 1 MCP server shipped together

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/srstomp/pokayokay/sdk-development
Any agent
npx skills add srstomp/pokayokay --skill sdk-development
Clone the repo
git clone --depth 1 https://github.com/srstomp/pokayokay

Made for: Claude Code, Codex.

Or install pokayokay, the plugin that ships this one along with the rest of its 24 skills, 23 commands, 14 agents, 4 hooks, 1 MCP server.

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 sdk-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/srstomp/pokayokay/sdk-development.svg)](https://agentmods.dev/skills/srstomp/pokayokay/sdk-development)
Your own site
<a href="https://agentmods.dev/skills/srstomp/pokayokay/sdk-development"><img src="https://agentmods.dev/badge/skills/srstomp/pokayokay/sdk-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 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 $0.00054 $0.00674
Opus 5 $0.00027 $0.00337
Sonnet 5 $0.00011 $0.00135
Haiku 4.5 $0.00005 $0.00067

Measured 4d ago against content hash 31d1904098ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdk-development 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 4d 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.

plugins/pokayokay/skills/sdk-development/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDK Development

Create professional TypeScript SDKs from scratch or by extraction.

Key Principles

  • Clean public API — Export only what consumers need, hide internals
  • Type everything — Full type coverage for config, methods, responses, and errors
  • Meaningful errors — Typed error classes with codes and context
  • Sensible defaults — Works out of the box with minimal config
  • Framework agnostic — Core SDK has no framework dependencies; add bindings separately

Quick Start Checklist

  1. Analyze scope: new SDK or extraction from existing app
  2. Design public API surface (exports, types, config)
  3. Implement client with typed methods and error handling
  4. Configure build for ESM/CJS/types (tsup recommended)
  5. Write tests (unit + integration) and examples
  6. Publish to npm with proper package.json exports field

When NOT to Use

  • For consuming external APIs — see api-integration skill
  • For publishing to npm only — this skill covers full SDK lifecycle

References

Reference Description
extraction-scope-and-boundaries.md Scope identification, dependency analysis, boundary definition
extraction-usages-and-planning.md Finding usages, test coverage, phased extraction plan
package-structure-and-clients.md SDK layout, client design patterns (single, modular, factory)
configuration-and-api-design.md Config interfaces, defaults, barrel exports, method signatures
internal-architecture-and-best-practices.md HTTP client, state management, tree-shaking, environment agnostic
type-design.md Strict types, branded types, generics, discriminated unions
error-handling-and-async.md Error class hierarchy, retry logic, request queues, token management
events-storage-and-logging.md Event emitter, storage abstraction, logger interface
build-tools-and-output.md tsup config, output formats, package.json exports, TypeScript config
bundle-optimization-and-distribution.md Bundle size, multi-platform builds, dual packages, monorepo
publishing-and-registries.md npm publishing, private registries, versioning, changelogs
ci-cd-and-documentation.md GitHub Actions, documentation, pre-publish checklist, deprecation

Read the full file on GitHub · 48 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. 4d ago First seen · 48 lines · 54 tokens per session scan A 31d1904098ee

Subscribe to this mod's changes

sdk-development is a skill published in the GitHub repository srstomp/pokayokay (9 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 674 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

web-browser

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.

mitsuhiko/agent-stuff · 64 tokens

traceway-setup

Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…

tracewayapp/traceway · 134 tokens