What is ag-7-qualidade?

An automated quality-checking workflow for websites or local applications. It checks whether an app is running, behaves correctly, looks right, and feels usable, then can fix issues and test again.

Testing an app from a URL or local project, correcting discovered issues, repeating checks until a chosen quality score is reached, and producing a quality report.

It helps find problems that a build or type check may miss, such as broken pages, visual defects, or incomplete user flows.

ag-7-qualidade — Skill for Claude Code by andregusman-raiz

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 andregusman-raiz/a-gusman-claude --skill ag-7-qualidade

Clone the repo

git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-7-qualidade/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-7-qualidade)

Your own site

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-7-qualidade"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-7-qualidade/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-7-qualidade"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-7-qualidade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 764 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 warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 4
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00764
Opus 5.5	$0.00025	$0.00306
Sonnet 5.5	$0.00012	$0.00153
Haiku 4.5	$0.00006	$0.00076

Measured 2mo ago against content hash 7a4fc0d34d7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ag-7-qualidade 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/ag-7-qualidade/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QUALIDADE — Maquina Autonoma de Qualidade (MERIDIAN)

Invocacao

/qualidade https://app.example.com
/qualidade ~/Claude/GitHub/raiz-platform
/qualidade https://app.example.com --threshold 90
/qualidade --audit-only https://app.example.com
/qualidade --resume

O que faz

Delega para ag-meridian (MERIDIAN) — a maquina autonoma de QA com 5 fases:

PRE-FLIGHT: Detecta modo (URL vs local), verifica recursos
SCOUT: Descobre app, mapeia rotas, detecta auth
SIEGE: Testa 5 dimensoes (ALIVE, REAL, WORKS, LOOKS, FEELS)
FORGE: Corrige bugs encontrados (ciclo convergente)
DELIVER: Quality Certificate, baselines, Fix PR

Convergencia: MQS >= threshold (default 85). Max 5 ciclos.

Implementacao

Este skill delega diretamente para ag-meridian:

Agent({
  subagent_type: "ag-meridian",
  prompt: "[input completo do usuario]",
  model: "fable", // model-fallback:managed
  run_in_background: true
})

Toda a logica, state management e convergencia estao em ag-meridian.

Regras Criticas de Verificacao (feedback SophiA — 21 PRs)

O MERIDIAN DEVE seguir estas regras aprendidas de falhas reais:

NUNCA declarar fix completo baseado em build/typecheck — reproduzir bug via Playwright
Presenca != Corretude — "pagina tem dados" nao significa "dados corretos"
API 200 != E2E funcional — tracar dados: API → adapter → state → DOM
Snapshot estatico != Teste — se nao houve click/select/type, feature NAO foi testada
Testar interacoes adjacentes — mudar filtro, trocar tab, selecionar outro item apos fix

Regra PDF → Markdown (obrigatoria — economia de tokens)

Qualquer PDF consumido por esta machine DEVE ser convertido ANTES via markitdown: bash ~/Claude/.claude/scripts/pdf2md.sh <arquivo.pdf> → Read/Grep no .md gerado (cache automatico). NUNCA Read direto de .pdf para extrair texto. Excecao visual (layout/slides): converter primeiro, Read multimodal depois. Enforcement: hook pdf-read-guard.sh. Detalhes: .claude/rules/pdf-markitdown.md.

Read the full file on GitHub · 68 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.

2mo ago First seen · 68 lines · 62 tokens per session scan A 7a4fc0d34d7c

Subscribe to this mod's changes

ag-7-qualidade is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 764 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 2026-08-30.

Claude Code Frontend Testing ai-agents automation developer-tools

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

ag-7-qualidade