Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Decision rules for managing context in long-running LLM agents. Covers when to mask tool outputs, trigger condensation, spawn sub-agents, or switch context as the window fills. Backed by NeurIPS 2025 and ACL 2024 research on context scaling and positional attention bias.
Simple observation masking halves cost and matches LLM summarization on solve rate, making it more effective than investing in complex compression pipelines.
When to use it
- Cutting API costs during multi-hour coding agent runs
- Preventing context overflow on large file analysis tasks
- Designing multi-agent systems with clean context handoffs
- Structuring agent memory for extended autonomous research
- Diagnosing degraded agent behavior in long sessions
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: An agent just returned 800 lines of grep output and context is at 65%. What should I do?
- 1Extract the relevant file paths and match counts from the grep output into a short summary
- 2Write that summary to a file for later reference
- 3Discard the raw tool output from context
- 4Check if context is still above 70% after masking
- 5If yes, mask the oldest reasoning turns from earlier in the session
Context usage reduced, key facts preserved in a file, agent continues without compaction or loss of decision chain