Claude Code Mods Are Game Changers. This One Saves Me Money.
Claude Code now supports mods that allow customization of the Cloud desktop app. A user demonstrates a cache management mod that tracks usage data, displays costs, monitors session limits, and provides notifications before cache expiration to help optimize spending.
Summary
The speaker introduces a new feature called "mods" for Claude Code that enables users to customize the Cloud desktop app's functionality through simple requests. They showcase a practical cache management mod they created that provides several valuable features. The mod displays real-time usage and cache data, explaining that cached content (everything in the chat history) is not re-read at full cost for new messages. The cache window lasts 60 minutes, after which users must pay full price for all previously cached text again. As context windows grow larger, the financial impact of cache expiration becomes more significant. The mod includes visibility into session limits (5-hour and weekly restrictions) and calculates the total API cost for the current session. Additionally, it features a streaming button that initiates data transfer, followed by a "clear and continue" button that runs the slash clear command automatically—reducing a previously manual five-step process (run skill, copy, clear, paste, Enter) to just two clicks. The mod also provides proactive notifications approximately 5 minutes before cache data becomes inactive, suggesting options to quickly query, compress context, or transfer the session to prevent unnecessary cache charges.
Key Insights
- The speaker claims that cached content in a chat session avoids full-cost re-reading on new messages, but the cache window expires after 60 minutes of inactivity, requiring full payment for all text again if a new request is made after that period.
- The speaker states that as the context window fills up over time, the financial impact of cache expiration becomes increasingly expensive due to larger amounts of cached text losing protection.
- The speaker demonstrates that their mod consolidates a previously manual five-step workflow (run skill, copy, clear, paste, Enter) into a single two-click operation with the "clear and continue" button.
- The speaker explains that the mod sends proactive notifications approximately 5 minutes before cache data becomes inactive, offering users a choice to query, compress context, or transfer the session to avoid cache charges.
- The speaker indicates that the mod displays multiple cost-related metrics including session-level API rates, 5-hour limits, weekly limits, and the projected cost if cache runs out, enabling comprehensive financial visibility.
Topics
Transcript
[0:00] Cloud code just got mods, which means if you want the Cloud desktop app to do something differently, you can just ask it and it will change. I created a bunch of mods here. This one , for example, shows me usage and cache data. So, the cache is actually everything that's in this chat, meaning every new message you send to the agent, for example, if I say "hello," isn't reread at full cost. And you see that the cache time was somewhere around 57 minutes, and now it's back to 60 . So if you don't send a message to the session within 60 minutes, you'll have to pay for all that [0:31] text again. As the…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Nate Herk | AI Automation
Every Codex Concept Explained for Non-Coders
A comprehensive tutorial explaining 18 core Codex concepts for non-technical users, organized into four parts covering basics (projects, agents, agent loops, goals), environments (on-premises vs. cloud, working trees), customization (AI models, effort levels, permissions, skills), and scaling tools (browser, sites, subagents, scheduled tasks, voice mode).
5 Claude Code Mods That Everyone Needs
The video demonstrates five useful Claude Code modifications (mods) that are plugins enabling customization of the Claude desktop application interface. The creator showcases practical mods including Cache Keeper for token management, Recording Mode for privacy, Goal tracking interface, and Collision Guard for file conflict detection, explaining how anyone can create mods using plain language.
How to Actually Build & Sell Software with AI as a Non-Techie
Dave Fabrikant, a 10+ year Python programmer and AI engineer, discusses how AI coding tools have transformed software development from a specialized skill into an accessible field for non-technical founders. He explains the progression from personal tools to scalable products, emphasizing architecture, security best practices, and the shift from specification-driven to intent-based development.
I Tested Codex's NEW $500/mo Ultrafast mode
A reviewer tests Codex's new $500/month Ultrafast mode, which claims to be 8x faster than standard mode. While results vary by task complexity, Ultrafast delivers significant speed improvements but at substantially higher resource consumption, making it suitable primarily for time-sensitive projects.
I Tested Opus 5.5 vs Sonnet 5.5
A comparison test between Claude Opus and Sonnet 3.5 shows that while Opus costs twice as much, it doesn't deliver twice the value across all tasks. Sonnet excels at well-defined requests with faster speed and lower cost, while Opus outperforms on vague, creative tasks requiring deeper reasoning.