aidevops: Skill for Claude Code

.agents/tools/browser/chromium-debug-use/SKILL.md

chromium-debug-use is a skill for Claude Code, Codex from marcusquinn/aidevops. It costs 24 tokens per session (520 once invoked), scanned A, original, MIT.

A guide for attaching to an already-open Chromium-based browser for temporary inspection and light interaction. Chromium-based browsers include Chrome, Brave, Edge, Vivaldi, and Chromium itself.

In plain words
What is it for?
Use it to inspect page content, HTML, or browser state, and to perform limited clicks, typing, navigation, or screenshots in an existing browser session.
Why use it?
It helps inspect a live browser session before setting up a larger, repeatable automation workflow. It also explains the required local approval and safety checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is marcusquinn/aidevops's own configuration. It tells Claude Code and Codex how to work on aidevops 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 aidevops configures →

Part of the aidevops plugin — 13 skills, 128 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to marcusquinn/aidevops. 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/marcusquinn/aidevops/main/.agents/tools/browser/chromium-debug-use/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/marcusquinn/aidevops

Made for: Claude Code, Codex.

Or install aidevops, the plugin that ships this one along with the rest of its 13 skills, 128 commands.

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 chromium-debug-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusquinn/aidevops/chromium-debug-use/github.svg)](https://agentmods.dev/skills/marcusquinn/aidevops/chromium-debug-use)
Your own site
<a href="https://agentmods.dev/skills/marcusquinn/aidevops/chromium-debug-use"><img src="https://agentmods.dev/badge/skills/marcusquinn/aidevops/chromium-debug-use/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 chromium-debug-use

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcusquinn/aidevops/chromium-debug-use"><img src="https://agentmods.dev/badge/skills/marcusquinn/aidevops/chromium-debug-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 520 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 pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00520
Opus 5 $0.00012 $0.00260
Sonnet 5 $0.00005 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 6d ago against content hash b27fbe12f998, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

chromium-debug-use 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 6d 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.

.agents/tools/browser/chromium-debug-use/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chromium Debug Use

Read tools/browser/chromium-debug-use.md first.

Use This Skill When

The user wants to inspect or lightly interact with something already open in a Chromium-family browser (Chrome, Brave, Edge, Vivaldi, Chromium) before committing to a heavier automation tool.

Workflow

  1. Confirm explicit, user-approved live-session investigation.
  2. If the debug port is not yet open, have the user launch with the flag from tools/browser/chromium-debug-use.md.
  3. Use .agents/scripts/chromium-debug-use-helper.sh version and list to confirm access.
  4. Prefer snapshot, html, and eval to understand the page before using click, type, navigate, or screenshot.
  5. Once the flow is understood, hand off to the best-fit longer-term tool:
    • tools/browser/playwright.md — repeatable isolated automation
    • tools/browser/dev-browser.md — aidevops-managed persistent profile
    • tools/browser/playwright.md — official extension mode for selected tabs in the user's normal browser
    • tools/browser/chrome-devtools.md — performance, network, and console inspection

Safety

  • Local-only and temporary; the user must have enabled the debug path for this investigation.
  • Prefer loopback endpoints and temporary profiles.
  • Do not use this path for unrelated tabs or long-lived background control.

Commands

.agents/scripts/chromium-debug-use-helper.sh version
.agents/scripts/chromium-debug-use-helper.sh list
.agents/scripts/chromium-debug-use-helper.sh snapshot <target>
.agents/scripts/chromium-debug-use-helper.sh html <target> [selector]
.agents/scripts/chromium-debug-use-helper.sh eval <target> "document.title"
.agents/scripts/chromium-debug-use-helper.sh click <target> "button.submit"
.agents/scripts/chromium-debug-use-helper.sh type <target> "hello world"
.agents/scripts/chromium-debug-use-helper.sh screenshot <target> /tmp/page.png

Read the full file on GitHub · 50 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. 6d ago Changed b27fbe12f998
  2. 8d ago First seen · 50 lines · 24 tokens per session scan A 27294e23d98a

Subscribe to this mod's changes

chromium-debug-use is a skill published in the GitHub repository marcusquinn/aidevops (396 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 520 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

playwright

Use when the task requires capturing or automating a real browser from the terminal.

openai/openai-agents-python · 19 tokens

e2e-testing-patterns

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

wshobson/agents · 51 tokens

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

vercel-labs/open-agents · 51 tokens

computer-use

Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…

kirodotdev/KiroCrew · 105 tokens

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens

browser-auth

Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.

kirodotdev/KiroCrew · 47 tokens