Chrome Devtools Browser

Community

Encod3d-Sec

chrome-devtools-browser

Bring up a REAL, visible, interactive chromium on the Kali VM that the operator logs into (Smart-ID / Mobile-ID / any manual auth or MFA/CAPTCHA), while the agent drives and observes it live through the chrome-devtools MCP (navigate, DOM snapshot, network capture, screenshots, console, evaluate). Use whenever a target needs a MANUAL login the agent cannot complete headlessly, when you need to capture an authenticated session / the real API calls a page makes, or to confirm/screenshot a DOM-XSS. Triggers - "open a browser", "log in manually", "smart-id / mobile-id / national id login", "mfa / 2fa login", "solve the captcha", "drive the browser", "capture the authenticated session / network".

Overview

Publisher	Encod3d-Sec
Repository	`TORCH`
Skill name	`chrome-devtools-browser`
Stars	334
Forks	48
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by Encod3d-Sec on GitHub. Read the source before you install it.

Installation

Install the Chrome Devtools Browser AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/chrome-devtools-browser
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git /tmp/TORCH
mkdir -p .claude/skills
cp -r /tmp/TORCH/skills/workflow/chrome-devtools-browser .claude/skills/chrome-devtools-browser

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chrome Devtools Browser in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Chrome Devtools Browser on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Chrome Devtools Browser is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

chrome-devtools-browser

Headless browser.sh cannot solve a human login. This skill brings up a visible chromium on the Kali desktop (:0) the operator can click and type into, with its DevTools port tunnelled back so the chrome-devtools MCP drives and watches it. Two roles at once: the human authenticates; the agent observes + acts. The VM holds the VPN/egress path, so it reaches both internet and in-scope targets.

1. Bring it up (one command)

bash
bash scripts/browser-visible.sh <login-url> --profile bbtest-<eng>
# e.g. bash scripts/browser-visible.sh https://target.example/ib --profile bbtest-<eng>

It resolves the VM's seat session, unlocks/wakes :0, frees the CDP port, launches chromium as the seat user on :0 in a named tmux session (a dedicated per-engagement profile, so the operator's own profile/cookies stay clean), then reuses scripts/browser.sh to forward CDP to http://127.0.0.1:9222. It prints VISIBLE on :0 when a real on-screen window exists (not merely a listening port). If it prints a no (:N) desktop session message, the VM has no desktop - fall back to scripts/browser.sh (headless).

2. Attach + hand off for login

The chrome-devtools MCP attaches to http://127.0.0.1:9222. Confirm with list_pages; navigate_page to the login URL if needed.
Stay off the browser while the operator enters credentials. Take a take_screenshot so they can confirm the page, then wait for their "logged in" before you drive again. The operator owns credential entry and the phone approval; the agent never types a personal code / PIN.

3. Drive + observe (chrome-devtools MCP capability map)

Need	MCP tool
List/select tabs	`list_pages` (select the target tab; ignore the operator's other tabs)
Go to a page / back / reload	`navigate_page`
Rendered DOM (elements + uids)	`take_snapshot`
Visual PoC / confirm state	`take_screenshot` -> a `web` evidence image (hand to `Skill(screenshot)`/`Skill(evidence)`)
The real API calls the app makes	`list_network_requests` (add `includePreservedRequests:true` to span the login redirects); this is the authenticated API map a curl crawl never sees
One request's headers/body/cookies	`get_network_request <reqid>`
Console / JS errors	`list_console_messages`
Read client config / globals, confirm DOM-XSS	`evaluate_script` (e.g. `__NEXT_DATA__`, `window.*`, fire a payload in the real DOM)

Once authenticated, the captured /… API calls feed the hunt skills: Skill(hunt-idor) / Skill(hunt-api) (BOLA on id-keyed endpoints), Skill(hunt-xss) (DOM-XSS via evaluate_script), business-logic on the authed flows. Load-bearing requests still go to Burp Repeater when reachable (Skill(hunt-burp)).

4. Field notes

A 200 {"message":"Unable to login"} with NO Set-Cookie = the server rejected at an account/state check and issued no session -> nothing to pivot (not a bug). A Set-Cookie/JWT issued before such a check is a real authz-bypass lead - test the gated endpoints with that cookie.
dbus/GPU errors in the tmux pane are non-fatal VM noise; judge success by VISIBLE on + list_pages.
Data minimisation on the authed surface: prove IDOR/BOLA with your own account + stop at the first adjacent-id differential; never pull another customer's real PII.

Safety

The CDP port is unauthenticated = total control of the browser (read any tab, lift session cookies). It stays loopback-only + ssh -L; never bind 0.0.0.0 / expose it to the LAN.
Named tmux session only (cdpbrowser); never tmux kill-server (the VPN/other work may live in tmux).
Dedicated --profile per engagement; the port-free step warns it drops any tabs on that port.

Teardown

bash
bash scripts/browser.sh stop                                   # drop the CDP tunnel
bash /root/vm.sh 'tmux kill-session -t cdpbrowser'             # close the VM browser

Setup / recipe rationale + the dead-ends that shaped this: scripts/browser.sh, scripts/shot.py (seat-session resolution), and the engagement failures.md note.

Frequently asked questions

What does the Chrome Devtools Browser AI skill do?

Why use Chrome Devtools Browser on TypingMind?

Because you install it once and use it with any model. Chrome Devtools Browser is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Chrome Devtools Browser in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/chrome-devtools-browser. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Chrome Devtools Browser?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Chrome Devtools Browser?

As many as you like. As long as a model supports skills, you can use Chrome Devtools Browser with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Chrome Devtools Browser AI skill free?

Yes. It is published on GitHub by Encod3d-Sec under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Add Uint Support

pytorch

OrganizationPopular

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions…

Cuda Index Width

Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or…

Plan Change

Turn a feature request into a minimal, file-level implementation plan before any code.

Simplified English

Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

chrome-devtools-browser

1. Bring it up (one command)

2. Attach + hand off for login

3. Drive + observe (chrome-devtools MCP capability map)

4. Field notes

Safety

Teardown

Frequently asked questions

Related AI Skills

Set up your own AI workspace now