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.
git clone --depth 1 https://github.com/DeepBitsTechnology/claude-pluginsWrote 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/commands/deepbitstechnology/claude-plugins/check-browser-hijack)<a href="https://agentmods.dev/commands/deepbitstechnology/claude-plugins/check-browser-hijack"><img src="https://agentmods.dev/badge/commands/deepbitstechnology/claude-plugins/check-browser-hijack/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/commands/deepbitstechnology/claude-plugins/check-browser-hijack"><img src="https://agentmods.dev/badge/commands/deepbitstechnology/claude-plugins/check-browser-hijack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.01034 |
| Opus 5.5 | $0.00008 | $0.00414 |
| Sonnet 5.5 | $0.00004 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
check-browser-hijack 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 1mo 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Hijacking Detection
Scan all installed browsers for signs of hijacking, unauthorized modifications, and malicious extensions.
Browsers to Check
- Google Chrome
- Mozilla Firefox
- Microsoft Edge
- Internet Explorer
- Brave
- Opera
Detection Areas
1. Browser Settings Files
Check for unauthorized modifications in:
Chrome
%LOCALAPPDATA%\Google\Chrome\User Data\Default\Preferences%LOCALAPPDATA%\Google\Chrome\User Data\Default\Secure Preferences- Look for: homepage_url, default_search_provider, homepage
Firefox
%APPDATA%\Mozilla\Firefox\Profiles\*.default*\prefs.js- Look for: browser.startup.homepage, browser.search.defaultenginename
Edge
%LOCALAPPDATA%\Microsoft\Edge\User Data\Default\Preferences- Similar structure to Chrome
2. Browser Extensions
Scan extension directories:
Chrome Extensions
%LOCALAPPDATA%\Google\Chrome\User Data\Default\Extensions\- Check for unknown or suspicious extension IDs
- Review extension manifest.json files for:
- Excessive permissions
- Unknown developers
- Suspicious URLs
Firefox Add-ons
%APPDATA%\Mozilla\Firefox\Profiles\*.default*\extensions\- Review extensions.json
Edge Extensions
%LOCALAPPDATA%\Microsoft\Edge\User Data\Default\Extensions\
3. Browser Shortcuts
Check desktop and taskbar shortcuts for hijacking:
# Check Chrome shortcut target
Get-ItemProperty "C:\Users\*\Desktop\*.lnk" | Select-Object Target
Look for modified targets with:
- Suspicious command line arguments
- URLs appended to shortcuts
- Redirects to unwanted sites
4. Registry Browser Settings
# IE/Edge HomePage
HKCU:\Software\Microsoft\Internet Explorer\Main -> "Start Page"
# Default search providers
HKCU:\Software\Microsoft\Internet Explorer\SearchScopes
# Browser policies
HKCU:\Software\Policies\Microsoft\Edge
HKCU:\Software\Policies\Google\Chrome
5. Proxy Settings
Check for unauthorized proxy configurations:
HKCU:\Software\Microsoft\Windows\CurrentVersion\Internet Settings
Look for:
- ProxyEnable = 1 (when not expected)
- ProxyServer settings
- AutoConfigURL (PAC file hijacking)
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.
- 1mo ago First seen · 174 lines · 21 tokens per session scan A ff04a69f7640
check-browser-hijack is a command published in the GitHub repository DeepBitsTechnology/claude-plugins (49 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,034 once invoked, about $0.0001 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.
Other commands, from other repositories
act
Live agentic desktop + browser control via OAuth (no API key).
ia-test-browser
Run browser tests on pages affected by current PR or branch.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
scrape
Scrape structured data from a single URL using Antigravity (agy). Returns markdown table or JSON. Saves to docs/agy/scrapes/.
restaurant-snipe
Schedule a future reservation to book at the exact release time (e.g. 10am sharp when Resy slots open).
test
Invoke the test-writer subagent to add focused, behavioural tests in the target language's idiom. Pass --mode e2e (or --e2e) to run the browser-driven E2E pipeline instead, or --mode e2e-live for an ephemeral, human-watched browser walkthrough with no spec file written.