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 Dragoon0x/everything-design-taste --skill developer-portalgit clone --depth 1 https://github.com/Dragoon0x/everything-design-tasteWrote 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/dragoon0x/everything-design-taste/developer-portal)<a href="https://agentmods.dev/skills/dragoon0x/everything-design-taste/developer-portal"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/developer-portal.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00354 |
| Opus 5 | $0.00010 | $0.00177 |
| Sonnet 5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
developer-portal 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.
What it actually says
Developer Portal Design
Documentation Structure
- Getting started guide (0 to first API call in 5 minutes)
- Authentication section (clear, with working examples)
- Endpoint reference (complete, searchable)
- Code examples in multiple languages
- Error reference (every error code explained)
- Changelog (what changed, when, migration notes)
API Reference
- Endpoint: method + path (GET /api/v1/users)
- Description: what it does in one sentence
- Parameters: name, type, required/optional, description
- Request example: complete, copy-paste ready
- Response example: with all fields annotated
- Error responses: every possible error
- Try it: interactive API console
Code Examples
- Multiple languages (min: cURL, Python, JavaScript)
- Complete and runnable (not snippets that need context)
- Copy button on every code block
- Syntax highlighting
- Show expected output
Design Principles
- Dark mode default (developers prefer it)
- Monospace font for code, sans-serif for prose
- Left sidebar navigation with search
- Full-page search with instant results
- Versioned docs (v1, v2 with selector)
- Print-friendly / export to PDF
Developer Experience
- Onboarding: signup → API key → first request in under 5 minutes
- Sandbox/test environment
- Rate limit dashboard
- Status page link (is the API up?)
- Support channels (GitHub issues, Discord, email)
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.
- 4d ago First seen · 47 lines · 21 tokens per session scan A c0101cf2919e
developer-portal is a skill published in the GitHub repository Dragoon0x/everything-design-taste (11 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 354 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
agent-desktop-ffi
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…
api-security-scan
Review a REST/HTTP API — from its OpenAPI spec or route code — for security gaps like missing auth, broken object-level authorization, no rate limiting, and verbose errors. Reports file:line. Pure Claude Code, no signup.
fastify-best-practices
This skill should be used when working on any Fastify project or when the user asks about Fastify best practices, conventions, or patterns. Trigger when: working on a Fastify project, creating Fastify plugins, registering routes, using decorators, organizing Fastify application structure, using @fastify/autoload…
fastify-hooks-lifecycle
This skill should be used when implementing Fastify hooks, understanding hook execution order, using onRequest/preParsing/preValidation/preHandler/preSerialization/onError/onSend/onResponse hooks, using onReady/onListen/onClose/onRoute/onRegister application hooks, debugging hook chain issues, adding authentication…
fastify-production
This skill should be used when deploying Fastify to production, configuring Fastify security headers, setting up reverse proxy with Fastify, implementing graceful shutdown, configuring @fastify/helmet, @fastify/cors, @fastify/rate-limit, trustProxy settings, Kubernetes Fastify deployment, Fastify performance tuning…
fastify-troubleshooting
This skill should be used when debugging Fastify issues, identifying Fastify anti-patterns, diagnosing common Fastify mistakes, performing Fastify error troubleshooting, investigating request.body undefined in hook, fixing decorator shared across requests, resolving hook executing twice, handling reply already sent…