~/agent-config
Learn AI
FundamentalsJul 13, 20261 min read

Tokens, Context Windows, and Why Prompts Matter

Every model has a finite short-term memory measured in tokens. Understanding it explains why prompts get "forgotten," why long chats drift, and how to keep answers sharp.

A token is the unit an LLM reads and writes. It's usually a word fragment — "learning" might be one token, "tokenization" a few. As a rough guide, 100 tokens is about 75 English words.

The context window

The context window is the maximum number of tokens the model can consider at once — your prompt, the conversation so far, and its own reply all count against it. It is the model's entire short-term memory. Nothing outside the window exists to the model.

  • Too much filler pushes important instructions out of the window.
  • In long chats, early messages get truncated or summarized away.
  • Retrieval and tools let you pull in only the relevant context on demand.

Practical prompting

Because attention is spread across everything in the window, signal-to- noise matters. Put the most important instructions where the model will weigh them, be specific about the output you want, and give concrete examples rather than long abstract descriptions.

Weak:   "Summarize this."
Strong: "Summarize this in 3 bullet points for a non-technical
         reader. Each bullet under 15 words."

Get started with these

Drop-in configs from the catalog to put this into practice.

Skill

Brainstorming

Explores user intent, requirements, and design before implementation. Required before any creative work — features, components, or behavior changes.

#planning #design #spec +1

Cursor, Claude Code, Windsurf +3

MCP

Memory MCP

Gives your agent a persistent knowledge graph so it remembers entities and relationships across sessions. Great for long-running projects and context…

#mcp #memory #knowledge-graph +1

Cursor, Claude Code, Windsurf +2

Details