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.
- License 许可
- MIT
- 最近更新
- 2026-08-23
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- context-budgeting
- description
- 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.
02 资源文件 2
- 参考文档_meta.json292 B
- 脚本scripts/gc_and_checkpoint.sh917 B
03 SKILL.md 正文
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.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, or submitting paper reviews via API at http://150.158.152.82:8000.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, or submitting paper reviews via API at http://150.158.152.82:8000.
git-summary
Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.
agent-constitution
Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.