context-budgeting

✓Verified·Scanned 2/18/2026

This skill provides a framework to manage OpenClaw agent context windows via partitioning, checkpointing, and compaction. It instructs executing scripts/gc_and_checkpoint.sh (which runs openclaw sessions --active 1) and writes HOT_MEMORY.md under /Users/yang/clawd.

from clawhub.ai·v7580259·2.6 KB·0 installs
Scanned from 1.0.0 at 7580259 · Transparency log ↗
$ vett add clawhub.ai/sarielwang93/context-budgeting

Context Budgeting Skill

This skill provides a systematic framework for managing the finite context window (RAM) of an OpenClaw agent.

Core Concepts

1. Information Partitioning

  • Objective/Goal (10%): Core task instructions and active constraints.
  • Short-term History (40%): Recent 5-10 turns of raw dialogue.
  • Decision Logs (20%): Summarized outcomes of past steps ("Tried X, failed because Y").
  • Background/Knowledge (20%): High-relevance snippets from MEMORY.md.

2. Pre-compression Checkpointing (Mandatory)

Before any compaction (manual or automatic), the agent MUST:

  1. Generate Checkpoint: Update memory/hot/HOT_MEMORY.md with:
    • Status: Current task progress.
    • Key Decision: Significant choices made.
    • Next Step: Immediate action required.
  2. Run Automation: Execute scripts/gc_and_checkpoint.sh to trigger the physical cleanup.

Automation Tool: gc_and_checkpoint.sh

Located at: skills/context-budgeting/scripts/gc_and_checkpoint.sh

Usage:

  • Run this script after updating HOT_MEMORY.md to finalize the compaction process without restarting the session.

Integration with Heartbeat

Heartbeat (every 30m) acts as the Garbage Collector (GC):

  1. Check /status. If Context > 80%, trigger the Checkpointing procedure.
  2. Clear raw data (e.g., multi-megabyte JSON outputs) once the summary is extracted.