DQIII8: Skill for Claude Code

.claude/skills/cdp-investigate/SKILL.md

cdp-investigate is a skill for Claude Code from senda-labs/DQIII8. It costs 55 tokens per session (1,335 once invoked), scanned A, original, MIT.

A web-investigation workflow that extracts text, HTML, or screenshots from a web page through an authenticated Chrome browser connection.

In plain words
What is it for?
Use it to research a URL, read its contents, inspect its HTML, or capture a screenshot. It does not cover clicking, filling forms, or sending data.
Why use it?
It lets an agent inspect pages that may require the user's logged-in browser session, without giving it unrestricted browser scripting or permission to submit changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 bin/tools/cdp_investigate.py --url <URL> --extract text|html|screenshot|all \.

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/cdp-investigate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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.

agentmods badge for cdp-investigate

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/cdp-investigate/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/cdp-investigate)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/cdp-investigate"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/cdp-investigate/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.

agentmods 80×15 button for cdp-investigate

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/cdp-investigate"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/cdp-investigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01335
Opus 5 $0.00028 $0.00668
Sonnet 5 $0.00011 $0.00267
Haiku 4.5 $0.00006 $0.00134

Measured 12d ago against content hash 05082b03c934, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cdp-investigate scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

diagnóstico manual vía `curl` directo, fuera de esta tool) y permita
.claude/skills/cdp-investigate/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CDP Investigate — Investigación web bajo demanda sobre el túnel CDP

Cuándo usar este skill

Cuando el usuario pide investigar, extraer información, o "visualizar" una web o plataforma bajo demanda:

  • "Investiga X" / "entra en <url> y sácame..." / "haz captura de..."
  • Necesitas texto, HTML o un screenshot de una página que requiere estar autenticado (la sesión del navegador del PC del usuario, vía 9333) o de cualquier página pública.
  • No uses este skill para clicar, rellenar formularios, enviar datos o cualquier acción con efectos secundarios sobre la página — está fuera del alcance por diseño (ver "Fuera de alcance" abajo).

Herramienta

cd /root/dqiii8
python3 bin/tools/cdp_investigate.py --url <URL> --extract text|html|screenshot|all \
  [--port 9333] [--settle 4.0] [--full-page] [--max-total-s 60]
  • --url debe ser http(s) — cualquier otro esquema se rechaza.
  • --extract es un enum cerrado: no hay passthrough de JS arbitrario ni modo de red libre.
  • Puerto por defecto 9333 (túnel SSH al Chrome del PC Windows del usuario, intermitente). Usa --port 9222 para el Chrome local del VPS si aplica.

Interpretar el JSON de salida

{"ok": true, "text_path": "...", "html_path": "...", "screenshot_path": "...", "inline": {"text": "...", "html": "..."}}
  • inline.text/inline.html están truncados a ~4000 chars — para el contenido completo, lee text_path/html_path con el tool Read.
  • screenshot_path es un PNG — inspecciónalo con el tool Read.

Outcomes de fallo — normales, NO reintentar en bucle

  • {"ok": false, "error": "tunnel_down"} — el túnel 9333 no responde. Es un resultado normal: comunica al usuario que abra el túnel/PC, no reintentes en bucle.
  • {"ok": false, "error": "cdp_busy"} — ya hay otra investigación en curso sobre el mismo puerto (invariante de un solo cliente CDP a la vez). Espera y reintenta más tarde si hace falta, no en bucle inmediato.
  • {"ok": false, "error": "invalid_url_scheme"} — corrige la URL.
  • {"ok": false, "error": "blocked_host"} — la URL apunta a localhost/red privada (bloqueado: evita SSRF hacia el propio plano de control de DevTools, p.ej. cerrar tabs ajenas vía /json/close/<id>). No es un bug, es la guardarraíl de S1 funcionando.
  • {"ok": false, "error": "watchdog_timeout"} — la investigación excedió --max-total-s; la tab y el lock quedan liberados igualmente (el watchdog intenta cerrar la tab por HTTP antes de forzar la salida).

Read the full file on GitHub · 103 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.

  1. 12d ago First seen · 103 lines · 55 tokens per session scan A 05082b03c934

Subscribe to this mod's changes

cdp-investigate is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 1,335 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.