Web Monitor

Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, mon...

Security Scan

The skill and included script are coherent: a local web-page monitor that fetches URLs, stores snapshots under ~/.web-monitor, computes diffs, and optionally uses BeautifulSoup; it does not request unrelated credentials or external services.

Purpose & Capability

Name/description, SKILL.md usage examples, README, and scripts/monitor.py all align: the code implements URL fetching, snapshotting, diffs, and keyword alerts which match the stated purpose.

Instruction Scope

Runtime instructions tell the agent to run scripts/monitor.py which performs HTTP(S) requests to arbitrary URLs and writes data to ~/.web-monitor (overridable via WEB_MONITOR_DIR). This is expected for a monitor, but it means the skill will fetch whatever URL it is asked to watch (including internal/localhost addresses if supplied). The instructions do not read other unrelated system files or exfiltrate data to third-party endpoints.

Install Mechanism

No install spec is included; this is instruction + source-code only. The script is pure Python with an optional dependency (beautifulsoup4) referenced by the SKILL.md; nothing is downloaded from untrusted URLs or installed automatically.

Credentials

The skill requests no credentials or sensitive env vars. It optionally respects WEB_MONITOR_DIR to change storage location; no unrelated secrets or config paths are required.

Persistence & Privilege

always is false and the skill does not request elevated/system-wide privileges or modify other skills. It stores data only under the user's configured data directory.

Assessment

This skill appears to do exactly what it claims: fetch pages, save snapshots in ~/.web-monitor, and compute diffs. Before installing or allowing autonomous use, consider: (1) the agent will fetch any URL you or the agent adds — avoid adding internal/localhost endpoints if you don't want those probed, (2) stored snapshots live under your home directory (overridable with WEB_MONITOR_DIR), and (3) if you need CSS-selector support install beautifulsoup4 in the environment. No credentials are requested and there are no hidden network callbacks in the code, but be cautious about which URLs the agent is permitted to monitor.

Track web pages for changes. Stores snapshots, computes diffs, supports CSS selectors.

Quick Start

# Add a URL to watch
uv run --with beautifulsoup4 python scripts/monitor.py add "https://example.com" --name "Example"

# Add with CSS selector (monitor specific section)
uv run --with beautifulsoup4 python scripts/monitor.py add "https://example.com/pricing" -n "Pricing" -s ".pricing-table"

# Check all watched URLs for changes
uv run --with beautifulsoup4 python scripts/monitor.py check

# Check one specific URL
uv run --with beautifulsoup4 python scripts/monitor.py check "Example"

# List watched URLs
uv run --with beautifulsoup4 python scripts/monitor.py list

# View last diff
uv run --with beautifulsoup4 python scripts/monitor.py diff "Example"

# View current snapshot
uv run --with beautifulsoup4 python scripts/monitor.py snapshot "Example" --lines 50

# Remove
uv run --with beautifulsoup4 python scripts/monitor.py remove "Example"

Commands

Command	Args	Description
add	<url> [-n name] [-s selector]	Add URL to watch, take initial snapshot
remove	<url-or-name>	Stop watching a URL
list	[-f json]	List all watched URLs with stats
check	[url-or-name] [-f json]	Check for changes (all or one)
diff	<url-or-name>	Show last recorded diff
snapshot	<url-or-name> [-l lines]	Show current snapshot

Output Symbols

• 🔔 CHANGED — page content changed (shows diff preview)
• ✅ No changes
• 📸 Initial snapshot taken
• ❌ Error fetching

Data

Stored in ~/.web-monitor/ (override with WEB_MONITOR_DIR env var):

• watches.json — watch list config
• snapshots/ — stored page content + diffs

Tips

• Use --selector to monitor specific elements (prices, article lists, etc.)
• Use --format json for programmatic checking (heartbeat integration)
• CSS selectors require beautifulsoup4 (included via --with flag)
• Text is normalized to reduce noise from timestamps, whitespace, ads