Recursive Context Pruning & Token Budgeting

Overview

This skill implements a "Gatekeeper" logic to prevent context window bloat and unnecessary token expenditure. It ensures the agent only processes relevant data shards and adheres to an Atomic Precision protocol—delivering functional answers with zero conversational filler. By recursively summarizing state and stripping "bridge phrases," it maximizes the longevity and speed of long-running development workflows.

When to Use This Skill

• Use when building multi-step agents to prevent repetition and "memory drift" in long conversations.
• Use when working with large document sets or codebases to avoid dumping entire files into the prompt.
• Use when you need purely functional output (code/logic) without "Sure! Here is your..." intros.

How It Works

Step 1: Metadata Sharding

Scan the available data for headers, summaries, and key indicators. Create a "map" of the context rather than injecting the full source. Never pull the entire file into the prompt unless a specific, narrowed fragment is requested.

Step 2: Token Budget Allocation