Check what changed from Claude Max 20x to Ultra
Review the renamed plan, verification conditions and current billing before changing subscriptions.
12 resources
Cost and context
Token usage and context size: tools that measure them, settings that cut them, and what the numbers actually look like.
/
Keyword HERMESPRO
Keep Hermes project context and memory useful
Separate project rules from reusable procedures and check usage before compressing a long session.
Keyword CRONGATE
Skip idle Hermes cron agent runs
Let a script skip unchanged polls before Hermes starts an agent, with a check you supply.
Keyword STACKPICK
Six AI coding tools, one for each job
Cost, context, repo packing, browser debugging, diff review and PR review: one tool each, with the install line.
Keyword IDLE
Control Claude Code idle compaction
Choose whether long idle conversations compact automatically, with the documented version and cache limits.
Keyword TOKENCUT
Reduce Claude Code tool output with three tools
Try RTK, Headroom or Context Mode, with usage checks before you trust their token savings.
Keyword LIMITS
Use less context before raising your AI plan
Keep chats focused, reuse project files and choose effort levels that fit the task.
Keyword FUSION
Choose an effort level in Copilot Fusion
Let Copilot select models per task, then inspect which models ran and how credits were used.
Keyword TERRA
Use GPT-6.1 Terra in GitHub Copilot
Find Terra in Copilot, check organization access and compare its default token rates before choosing it.
Keyword MEMORY
Give new Claude Code sessions your project facts
Keep a short CLAUDE.md for recurring project facts, then check which instructions loaded.
Keyword HACKS
Use five built-in Claude Code shortcuts
Inspect context, ask side questions and review changes without installing another plugin.
Use a larger context window with a clear plan
Opus 4.6 expanded context capacity, but useful inputs and review still determine the outcome.