common-context-optimization
OfficialBoost context efficiency and reduce latency.
Software Engineering#latency#context-management#token-budget#ai-systems#output-masking#state-compaction#logs-processing
Authorwildbitca
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Techniques to maximize context window efficiency, reduce latency, and prevent 'lost in middle' issues through strategic masking and compaction. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)
Core Features & Use Cases
- Observation Masking (Noise Reduction): Replace raw output with semantic summaries after consumption to keep context concise.
- Context Compaction (State Preservation): Recursive summarization that preserves User Goal, Active Task, Current Errors, and Key Decisions.
- KV-Cache Awareness (Latency): Enforce a strict System -> Tools -> RAG -> User order and an append-only history to maximize pre-fill cache hits.
See references/ masking.md and references/compaction.md for patterns and algorithms.
Quick Start
Configure the agent to automatically mask large outputs and perform recursive state compaction at defined intervals.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: common-context-optimization Download link: https://github.com/wildbitca/ai-resources/archive/main.zip#common-context-optimization Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.