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-architecturegit 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-architecture)<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-architecture"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-architecture/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-architecture"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-architecture.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 | $0.00062 | $0.00638 |
| Opus 5 | $0.00031 | $0.00319 |
| Sonnet 5 | $0.00012 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
harness-architecture 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness: Arquitetura (Etapa 02)
Persona: Arquiteto de software sênior.
Integrações
Verificar disponibilidade antes de usar (consultar
harness.config.yaml). Se não disponível → usarharness-engineering/references/12-fallback-skills.md.
context7-mcp(se disponível) — ANTES de recomendar qualquer biblioteca externa:resolve_library_id→get_library_docs; fallback: busca webbrainstorming(se disponível) — se ainda há alta incerteza técnica; fallback:12-fallback-skills.md § brainstormingtlc-spec-driven(se disponível) — auto-skip para features pequenas — ir direto aoharness-tasks
Quando Usar
Ativadores: "arquitetura", "stack", "design técnico", "padrão de camadas"
Pule esta etapa para features simples (1–2 tasks óbvias) → vá direto para harness-tasks.
Padrão de Camadas Obrigatório (padrão OpenAI)
Defina a ordem de dependência e imponha mecanicamente:
Types → Config → Repository → Service → Runtime → UI
Dependências fluem apenas para frente. Violações → linter bloqueia + mensagem de remediação inline.
O Que Produzir
- Tabela de stack (Camada | Tecnologia | Justificativa | RNF atendido)
- Diagrama de componentes Mermaid — delegar ao
mermaid-studiose instalado - Modelo de dados — entidades, atributos, relacionamentos
- Contratos de API por fluxo do PRD
- Diagramas de sequência para fluxos críticos
- ADRs — contexto, alternativas, trade-offs, consequências
- Riscos técnicos (Alto/Médio/Baixo) + mitigação
- Mapa de harnessability:
- Linguagem fortemente tipada? (sensor computacional natural)
- Limites de módulo claros? (fitness functions possíveis)
- Framework que abstrai detalhes?
- Se não: sinalizar riscos e propor estrutura que melhore a harnessability
Saída Esperada
.catalog/atualizado (architecture.md,stack.md,domain.md)AGENTS.mdcriado/atualizado- Tech Solution persistida conforme
project_tracking.tool— verharness-engineering/references/11-project-tracking.md
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.
- 10d ago First seen · 61 lines · 62 tokens per session scan A 9d2aebf5d1bb
harness-architecture is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 638 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…