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 andregusman-raiz/a-gusman-claude --skill ag-10-benchmark-softwaregit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-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/andregusman-raiz/a-gusman-claude/ag-10-benchmark-software)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-10-benchmark-software"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-10-benchmark-software/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/andregusman-raiz/a-gusman-claude/ag-10-benchmark-software"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-10-benchmark-software.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 5 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.
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 | $0.00033 | $0.01796 |
| Opus 5 | $0.00016 | $0.00898 |
| Sonnet 5 | $0.00007 | $0.00359 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
ag-10-benchmark-software 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-10-benchmark-software — BENCHMARK Machine
Maquina replicavel para navegar, documentar e especificar qualquer plataforma SaaS.
Uso
/crawl-platform <nome> <url> [--max-pages N] [--depth N]
Exemplos:
/crawl-platform gupy https://app.gupy.io
/crawl-platform reportei https://app.reportei.com --max-pages 30
/crawl-platform qrcodefacil https://qrcodefacil.com --depth 2
Algoritmo
Ao receber este comando, execute o seguinte processo EXATAMENTE:
FASE 0: Setup
- Parsear argumentos:
name(1o arg),url(2o arg), flags opcionais - Defaults:
maxPages=50,depth=3 - Criar diretorio de output:
~/Claude/projetos/vibecoding-roadmap/docs/specs/{name}/ ~/Claude/projetos/vibecoding-roadmap/docs/specs/{name}/screenshots/ ~/Claude/projetos/vibecoding-roadmap/docs/specs/{name}/screens/ - Ler config se existir:
~/Claude/projetos/vibecoding-roadmap/src/lib/crawler/configs/{name}.json - Inicializar contadores:
visited=0,queue=[],pages=[]
FASE 1: Login
- Navegar para a URL fornecida:
mcp__plugin_playwright_playwright__browser_navigate({ url: "<url>" }) - Tirar screenshot da tela de login:
mcp__plugin_playwright_playwright__browser_take_screenshot({ type: "png", filename: "docs/specs/{name}/screenshots/000-login.png" }) - Pedir ao usuario: "Faca login na plataforma. Quando estiver logado, me avise."
- Aguardar resposta do usuario
- Apos confirmacao, tirar screenshot da pagina pos-login:
mcp__plugin_playwright_playwright__browser_take_screenshot({ type: "png", filename: "docs/specs/{name}/screenshots/001-home.png" })
FASE 2: Crawl (BFS)
Para cada pagina na fila (comecando pela pagina pos-login):
-
Capturar estado da pagina:
mcp__plugin_playwright_playwright__browser_snapshot()→ Salvar snapshot (accessibility tree com refs)
-
Screenshot:
mcp__plugin_playwright_playwright__browser_take_screenshot({ type: "png", filename: "docs/specs/{name}/screenshots/{NNN}-{slug}.png" })
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.
- 12d ago First seen · 182 lines · 33 tokens per session scan A cadcd612aa24
ag-10-benchmark-software is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,796 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
screenshot-intake
Use when a user provides a URL or screenshot files and wants to build an app from them, or when starting /build-from-screenshot. Captures pages via Chrome DevTools or Playwright MCP, analyzes structure with Claude vision, and produces build-spec.json. Keywords: screenshot intake, URL capture, build spec, screenshot…
ui-test
Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Covers end-to-end flows (clicks, forms, assertions), visual checks (screenshot + optional baseline diff), accessibility (axe-core), performance (Web Vitals + light Lighthouse-style metrics), and an interactive --debug…
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
audit-ui-e2e
Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Drives Chrome through every interactive element on the target surface, collects structured findings (severity, category, where, symptom, impact, repro, triage), and hands the result off to…
capture-screens
Automatically navigates a web app using Playwright MCP and captures context-aware named screenshots at each product feature state. Names each file semantically based on context (e.g., checkout-payment-form-filled.png). Outputs a manifest.json mapping filenames to descriptions and a summary report. Use when documenting…
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. 100ms per command. Use when you need to test a…