Context Budgeting OpenClaw Plugin & Skill | ClawHub
Looking to integrate Context Budgeting into your AI workflows? This free OpenClaw plugin from ClawHub helps you automate coding agents & ides tasks instantly, without having to write custom tools from scratch.
What this skill does
Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce token costs and latency for long-running tasks.
Install
openclaw skills install @sarielwang93/context-budgetingnpx clawhub@latest install context-budgetingFull SKILL.md
Open original| name | description |
|---|---|
| context-budgeting | Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce token costs and latency for long-running tasks. |
SKILL.md content below is scrollable.
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:
- Generate Checkpoint: Update
memory/hot/HOT_MEMORY.mdwith:- Status: Current task progress.
- Key Decision: Significant choices made.
- Next Step: Immediate action required.
- Run Automation: Execute
scripts/gc_and_checkpoint.shto 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.mdto finalize the compaction process without restarting the session.
Integration with Heartbeat
Heartbeat (every 30m) acts as the Garbage Collector (GC):
- Check
/status. If Context > 80%, trigger the Checkpointing procedure. - Clear raw data (e.g., multi-megabyte JSON outputs) once the summary is extracted.