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 travisjneuman/.claude --skill devex-sdk-designgit clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/devex-sdk-design)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00864 |
| Opus 5.5 | $0.00021 | $0.00346 |
| Sonnet 5.5 | $0.00010 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
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.
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,
--flagfor customization - Progressive output: Spinners for long ops,
--verbosefor debug,--jsonfor machines - Confirmation prompts: Destructive actions require
--yesor interactive confirm - Shell completion: Generate for bash/zsh/fish/PowerShell
- Exit codes: 0 = success, 1 = error, 2 = usage error
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.
- 2mo ago First seen · 115 lines · 52 tokens per session scan A b273e029ba30
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.
devex-sdk-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| devex-sdk-designtravisjneuman/.claude | Skill | 108 | yesterday | MIT | A | 52 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 316k | 7d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |