3 items
Reduce Claude token usage up to 70% with smart optimization and built-in tools. Context Pilot is an AI-conversation efficiency toolkit that works across Claude, ChatGPT, Perplexity, Grok, and Gemini — cutting token usage, speeding up your prompts, and letting you carry context between AI tools without retyping anything. Everything runs locally in your browser. No account, no server, no data collection. CAVEMAN MODE Toggle it on and every message you send gets a compression instruction attached automatically. The AI drops filler, hedging, and pleasantries while keeping every code block, command, error string, and technical detail exact. Shorter replies, same precision — measurably fewer tokens burned per exchange. NATIVE USAGE TRACKING (Claude) On claude.ai, Context Pilot reads Claude's own usage API — the same data Claude's own /usage page shows you, but live and inline next to your chat input. See your exact session (5-hour) and weekly utilization, a real token count computed with the same tokenizer Claude uses internally (not a character-count guess), and a prompt-cache countdown. On other platforms, Context Pilot tracks message counts and estimated tokens locally and flags rate-limit banners automatically. CONTINUE ELSEWHERE Hit a rate limit, or just want a second opinion? Pick a destination — Claude, ChatGPT, Perplexity, Grok, or Gemini — and Context Pilot extracts your conversation (last 8 exchanges or the full thread, your choice), opens the destination in a new tab, and pre-fills the input with full context. You review and hit send yourself; nothing is ever auto-submitted on your behalf. PROMPT POWER-UPS Eleven battle-tested prompt modifiers — BLUNT, BRUTAL, ASSUME, COUNTER, CONTRAST, SCOPE, ZOOM, POST, 2ND_FX, LADDER, STEELMAN — surface automatically as you type, matched to keywords in your draft. One click inserts a precise instruction (e.g. "COUNTER: Generate the strongest counterargument to my point") instead of you writing it out by hand every time. PDF TO MARKDOWN Drop in any PDF and get clean Markdown back — headings inferred from font size, page breaks preserved, ready to paste into a chat or download as a .md file. Runs entirely client-side using a bundled PDF-parsing library. Your file never leaves your device. PRIVACY BY DESIGN Context Pilot has no backend. There is nothing to breach, because there's nothing to send data to. Settings and usage stats live in your browser's local storage only, visible to nobody but you, deleted the moment you clear them or uninstall. No analytics, no ads, no tracking, no data sale — full policy at https://askaboutai.github.io/context-pilot-policy/privacy-policy.html
Jul 20, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.