devex-sdk-design

devex-sdk-design is a skill for Claude Code from travisjneuman/.claude. It costs 52 tokens per session (864 once invoked), scanned A, original, MIT.

A guide to designing software development kits, APIs, command-line tools, documentation, and onboarding experiences. An SDK is a package that helps developers use a service from their own code.

In plain words
What is it for?
Use it to design readable APIs, builder-style interfaces, structured errors, CLI tools, SDKs, and documentation-led onboarding.
Why use it?
It helps make developer tools easier to understand, harder to misuse, and clearer when something goes wrong.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tjn-backend plugin — 24 skills shipped together , and of tjn-skills

Good fit Use it to design readable APIs, builder-style interfaces, structured errors, CLI tools, SDKs, and documentation-led onboarding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/travisjneuman/.claude/devex-sdk-design
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.

Any agent
npx skills add travisjneuman/.claude --skill devex-sdk-design
Clone the repo
git clone --depth 1 https://github.com/travisjneuman/.claude

Made for: Claude Code.

Or install tjn-backend, the plugin that ships this one along with the rest of its 24 skills.

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 devex-sdk-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/travisjneuman/.claude/devex-sdk-design/github.svg)](https://agentmods.dev/skills/travisjneuman/.claude/devex-sdk-design)
Your own site
<a href="https://agentmods.dev/skills/travisjneuman/.claude/devex-sdk-design"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/devex-sdk-design/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.

agentmods 80×15 button for devex-sdk-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/travisjneuman/.claude/devex-sdk-design"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/devex-sdk-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 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
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00052 $0.00864
Opus 5.5 $0.00021 $0.00346
Sonnet 5.5 $0.00010 $0.00173
Haiku 4.5 $0.00005 $0.00086

Measured 2mo ago against content hash b273e029ba30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

devex-sdk-design 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 2mo 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.

skills/devex-sdk-design/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Experience & SDK Design

SDK Design Principles

API Ergonomics

// Bad: too many required params, unclear ordering
createUser(name, email, role, true, false, null, 'active');

// Good: builder pattern with named properties
const user = await sdk.users.create({
  name: 'Alice',
  email: '[email protected]',
  role: 'admin',
});

// Good: fluent API for complex operations
const results = await sdk.query('users')
  .where('role', '=', 'admin')
  .orderBy('createdAt', 'desc')
  .limit(10)
  .execute();

Progressive Disclosure

// Simple case: just works with defaults
const client = new MySDK('api-key');
const result = await client.doThing();

// Advanced case: full control available
const client = new MySDK({
  apiKey: 'api-key',
  baseUrl: 'https://custom.endpoint.com',
  timeout: 30000,
  retries: { maxAttempts: 3, backoff: 'exponential' },
  middleware: [loggingMiddleware, authRefreshMiddleware],
});

Error Design

// SDK errors should be structured and actionable
class SDKError extends Error {
  constructor(
    message: string,
    public readonly code: string,        // machine-readable
    public readonly statusCode?: number,  // HTTP status if applicable
    public readonly retryable: boolean = false,
    public readonly docs?: string,        // link to relevant docs
  ) {
    super(message);
  }
}

// User sees:
// SDKError: Rate limit exceeded (rate_limit_exceeded)
//   Retryable: true, retry after 2.3s
//   Docs: https://docs.example.com/rate-limits

CLI Design

Command Structure

mycli <command> <subcommand> [flags]

mycli init                    # Interactive setup
mycli deploy --env production # Explicit flags
mycli logs --follow           # Streaming output
mycli config set key value    # Noun-verb pattern

CLI Best Practices

  • Sensible defaults: Work out of the box, --flag for customization
  • Progressive output: Spinners for long ops, --verbose for debug, --json for machines
  • Confirmation prompts: Destructive actions require --yes or interactive confirm
  • Shell completion: Generate for bash/zsh/fish/PowerShell
  • Exit codes: 0 = success, 1 = error, 2 = usage error

Read the full file on GitHub · 115 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. 2mo ago First seen · 115 lines · 52 tokens per session scan A b273e029ba30

Subscribe to this mod's changes

devex-sdk-design is a skill published in the GitHub repository travisjneuman/.claude (108 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 864 once invoked, about $0.0002 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.

Related

devex-sdk-design compared with skills from other repositories

devex-sdk-design next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
devex-sdk-designtravisjneuman/.claudeSkill108yesterdayMITA52Claude Code
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k7d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code