Browser History

Name: Browser History
Author: samhvw8

samhvw8/dotfiles

46 installs
14 repo stars
Updated July 28, 2026
samhvw8/dotfiles

Helps with ai & agent building tasks.

About

browser-history is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.

browser-history
AI & Agent Building
AI-coding skill

Browser History by the numbers

46 all-time installs (skills.sh)
Ranked #7,539 of 16,556 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Jul 29, 2026 (Skillselion catalog sync)

npx skills add https://github.com/samhvw8/dotfiles --skill browser-history

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/samhvw8/dotfiles/browser-history.svg)](https://skillselion.com/skills/samhvw8/dotfiles/browser-history)

Installs	46
repo stars	★ 14
Last updated	July 28, 2026
Repository	samhvw8/dotfiles ↗

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Browser History Search

Search the user's browser history to find visited pages, analyze browsing patterns, and retrieve forgotten information.

When to use

User asks about pages they visited ("what github repos did I look at last week?")
User wants to find a forgotten page ("find that article about LLMs I read")
User asks about browsing habits ("how much time did I spend on Twitter?")
User wants browsing statistics ("show my most visited sites")

Requirements

sqlite3 CLI

Setup

First, detect available browsers by running:

./find-browser.sh

Output: PATH,TYPE,BROWSER,LAST_MODIFIED
TYPE: firefox or chromium (determines SQL syntax)
Use the first result (most recently used browser) by default
If multiple browsers were used recently (within last 24h), ask the user which one to search

Querying the database

Use ?immutable=1 in the SQLite URI to read the database even when the browser is open:

sqlite3 "file:///path/to/history.db?immutable=1" "SELECT ..."

Firefox databases (places.sqlite)

Search by keyword:

SELECT
    title,
    url,
    datetime(last_visit_date/1000000, 'unixepoch', 'localtime') as visit_date
FROM moz_places
WHERE url LIKE '%keyword%' OR title LIKE '%keyword%'
ORDER BY last_visit_date DESC
LIMIT 50;

Search by date range:

SELECT url, title, datetime(last_visit_date/1000000, 'unixepoch', 'localtime') as visit_date
FROM moz_places
WHERE last_visit_date > strftime('%s', '2025-01-01') * 1000000
  AND last_visit_date < strftime('%s', '2025-01-31') * 1000000
ORDER BY last_visit_date DESC;

Time spent analysis (uses moz_places_metadata):

SELECT
    SUM(m.total_view_time) / 1000 / 60 as minutes,
    COUNT(*) as sessions
FROM moz_places_metadata m
JOIN moz_places p ON m.place_id = p.id
WHERE p.url LIKE '%example.com%'
  AND m.created_at > strftime('%s', '2025-01-01') * 1000;

Note: created_at is in milliseconds, last_visit_date is in microseconds.

Most visited sites:

SELECT
    SUBSTR(url, INSTR(url, '://') + 3,
           INSTR(SUBSTR(url, INSTR(url, '://') + 3), '/') - 1) as domain,
    SUM(visit_count) as visits
FROM moz_places
WHERE url LIKE 'http%'
GROUP BY domain
ORDER BY visits DESC
LIMIT 20;

Chromium databases (History)

Important: Chromium timestamps are microseconds since January 1, 1601 (Windows epoch).

Conversion: (timestamp/1000000) - 11644473600 gives Unix epoch.

Search by keyword:

SELECT
    title,
    url,
    datetime((last_visit_time/1000000)-11644473600, 'unixepoch', 'localtime') as visit_date
FROM urls
WHERE url LIKE '%keyword%' OR title LIKE '%keyword%'
ORDER BY last_visit_time DESC
LIMIT 50;

Search by date range:

SELECT url, title, datetime((last_visit_time/1000000)-11644473600, 'unixepoch', 'localtime') as visit_date
FROM urls
WHERE last_visit_time > (strftime('%s', '2025-01-01') + 11644473600) * 1000000
  AND last_visit_time < (strftime('%s', '2025-01-31') + 11644473600) * 1000000
ORDER BY last_visit_time DESC;

Database schema

Firefox (moz_places)

Column	Description
`url`	Full URL
`title`	Page title
`last_visit_date`	Microseconds since Unix epoch
`visit_count`	Number of visits
`frecency`	Frequency + recency score

Firefox (moz_places_metadata)

Column	Description
`place_id`	Foreign key to moz_places
`total_view_time`	Milliseconds spent on page
`created_at`	Milliseconds since Unix epoch
`scrolling_time`	Time spent scrolling
`key_presses`	Number of key presses

Chromium (urls)

Column	Description
`url`	Full URL
`title`	Page title
`last_visit_time`	Microseconds since 1601-01-01
`visit_count`	Number of visits

Output guidelines

Present results in a readable format, grouped by domain when relevant
For time analysis, show hours/minutes, not raw milliseconds
When showing history, include the date and a clickable link
If results are numerous, summarize by domain or time period
You might include a small ASCII/Unicode chart (daily breakdown, histogram) if relevant

See @README.md for output examples.

#!/bin/bash
#
# find-browser.sh - Detect all browsers and their history databases
#
# Output format (tab-separated, sorted by most recent first):
#   PATH<tab>TYPE<tab>BROWSER_NAME<tab>MTIME_HUMAN
#
# TYPE is either "firefox" or "chromium" (determines SQL syntax)
# Exit code 1 if no browser found

set -e

case "$(uname -s)" in
    Darwin)
        FIREFOX_BASE="$HOME/Library/Application Support"
        CHROMIUM_BASE="$HOME/Library/Application Support"
        stat_mtime() { stat -f "%m" "$1"; }
        format_date() { date -r "$1" "+%Y-%m-%d %H:%M"; }
        ;;
    Linux)
        FIREFOX_BASE="$HOME"
        CHROMIUM_BASE="$HOME/.config"
        stat_mtime() { stat -c "%Y" "$1"; }
        format_date() { date -d "@$1" "+%Y-%m-%d %H:%M"; }
        ;;
    MINGW*|MSYS*|CYGWIN*)
        FIREFOX_BASE="$APPDATA"
        CHROMIUM_BASE="$LOCALAPPDATA"
        stat_mtime() { stat -c "%Y" "$1"; }
        format_date() { date -d "@$1" "+%Y-%m-%d %H:%M"; }
        ;;
    *)
        echo "Unsupported OS" >&2
        exit 1
        ;;
esac

# Browser definitions: name|type|subpath (relative to base)
# Use F: prefix for Firefox base, C: for Chromium base
case "$(uname -s)" in
    Darwin) BROWSERS="
Zen|firefox|F:zen/Profiles
Firefox|firefox|F:Firefox/Profiles
LibreWolf|firefox|F:LibreWolf/Profiles
Waterfox|firefox|F:Waterfox/Profiles
Chrome|chromium|C:Google/Chrome
Chromium|chromium|C:Chromium
Brave|chromium|C:BraveSoftware/Brave-Browser
Edge|chromium|C:Microsoft Edge
Arc|chromium|C:Arc/User Data
Vivaldi|chromium|C:Vivaldi
Opera|chromium|C:com.operasoftware.Opera
" ;;
    Linux) BROWSERS="
Zen|firefox|F:.zen
Firefox|firefox|F:.mozilla/firefox
LibreWolf|firefox|F:.librewolf
Waterfox|firefox|F:.waterfox
Chrome|chromium|C:google-chrome
Chromium|chromium|C:chromium
Brave|chromium|C:BraveSoftware/Brave-Browser
Edge|chromium|C:microsoft-edge
Vivaldi|chromium|C:vivaldi
Opera|chromium|C:opera
" ;;
    MINGW*|MSYS*|CYGWIN*) BROWSERS="
Firefox|firefox|F:Mozilla/Firefox/Profiles
LibreWolf|firefox|F:LibreWolf/Profiles
Waterfox|firefox|F:Waterfox/Profiles
Chrome|chromium|C:Google/Chrome/User Data
Chromium|chromium|C:Chromium/User Data
Brave|chromium|C:BraveSoftware/Brave-Browser/User Data
Edge|chromium|C:Microsoft/Edge/User Data
Vivaldi|chromium|C:Vivaldi/User Data
Opera|chromium|C:Opera Software/Opera Stable
" ;;
esac

output_file() {
    local file="$1" type="$2" name="$3"
    local mtime mtime_human
    mtime=$(stat_mtime "$file")
    mtime_human=$(format_date "$mtime")
    printf "%s\t%s\t%s\t%s\t%s\n" "$mtime" "$file" "$type" "$name" "$mtime_human"
}

results=$(mktemp)
trap "rm -f $results" EXIT

echo "$BROWSERS" | while IFS='|' read -r name type path_spec; do
    [[ -z "$name" ]] && continue

    # Parse base prefix and subpath
    base_type="${path_spec%%:*}"
    subpath="${path_spec#*:}"

    [[ "$base_type" == "F" ]] && base="$FIREFOX_BASE" || base="$CHROMIUM_BASE"
    full_base="$base/$subpath"

    [[ -d "$full_base" ]] || continue

    # Firefox stores history in places.sqlite, Chromium in History
    [[ "$type" == "firefox" ]] && filename="places.sqlite" || filename="History"

    find "$full_base" -maxdepth 2 -name "$filename" -type f 2>/dev/null | while read -r file; do
        output_file "$file" "$type" "$name"
    done
done | sort -t$'\t' -k1 -rn | cut -f2- > "$results"

if [[ -s "$results" ]]; then
    cat "$results"
else
    echo "No browser history found" >&2
    exit 1
fi