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 thaifurforo/ai-toolkit --skill harness-interfacegit clone --depth 1 https://github.com/thaifurforo/ai-toolkitWrote 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/thaifurforo/ai-toolkit/harness-interface)<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-interface"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-interface/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/thaifurforo/ai-toolkit/harness-interface"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-interface.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00111 | $0.01049 |
| Opus 5.5 | $0.00044 | $0.00420 |
| Sonnet 5.5 | $0.00022 | $0.00210 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
harness-interface 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 13d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness: Interface e Design System (Etapa 03)
Persona: Designer de produto / design systems com rigor de engenharia de contratos.
Integrações
Verificar disponibilidade antes de usar (consultar
harness.config.yaml). Se não disponível → usarharness-engineering/references/12-fallback-skills.md.
brainstorming(se disponível) — se a direção visual ainda está nebulosa; fallback:12-fallback-skills.md § brainstorming- Ferramentas de geração de imagem do harness (
GenerateImage/ companion visual) — gerar logo, concept art, referências e mockups; não apenas descrever em texto mermaid-studio(se disponível) — fluxos de navegação / mapa de telas
Quando Usar
Ativadores: "interface", "design system", "logo", "UX", "UI", "identidade visual", "mockup", "wireframe"
Pule esta etapa quando o projeto não tiver superfície de UI (CLI, biblioteca, API-only, job/batch, worker) → vá direto para harness-tasks.
Requer: PRD + arquitetura (.catalog/architecture.md / tech-solution) como entrada.
O Que Produzir
- Identidade visual — marca, tom, direção de logo (e variantes se aplicável)
- Design system — tokens (cor, tipografia, espaçamento, radius, elevação); componentes base
- UX das telas/fluxos principais do PRD — layout, hierarquia, navegação
- Estados empty / loading / error por tela crítica
- Acessibilidade mínima — contraste, foco, labels, redução de movimento quando relevante
- Assets visuais (gerar arquivos, não só texto):
- logo e variantes
- imagens de referência / moodboard
- concept art
- ícones de marca quando fizer sentido
- Mockups / wireframes das telas principais (estáticos ou links) para validar UX antes do breakdown de tasks
- Impactos em arquitetura/contratos — lista explícita (ver gate abaixo)
Gate: Interface → Arquitetura
Antes de avançar para harness-tasks, verifique:
| Impacto | Sim? |
|---|---|
| Contratos de API / payloads mudaram por causa do UX? | |
| Novas rotas, deep links ou navegação alteram boundaries? | |
| Estado cliente vs servidor redistribuído? | |
| Auth, permissões ou fluxos multi-step mudam o backend? | |
| Boundaries UI ↔ Runtime / SSR-CSR / ownership de módulos mudaram? | |
| Componentes compartilhados viram pacote/módulo novo? |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 86 lines · 111 tokens per session scan A 8807869aa495
harness-interface is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 14d ago), licensed MIT. It adds 111 tokens to every session and 1,049 once invoked, about $0.0004 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 2026-10-19.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.