autosearch:context-retention-policy
CommunityMaintain runtime context across long research sessions.
Education & Research#context-management#token-budget#context-compaction#session-policy#offload-evidence#long-session
Author0xmariowu
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Session-long research often drives context windows beyond practical limits. This policy defines what evidence to keep, what to offload, and when to compact to preserve retrieval quality and performance.
Core Features & Use Cases
- Keeps the last n tool results inline while offloading older evidence to disk.
- Preserves essential session artifacts like the citation index, rubrics, and the graph-search plan.
- Use Case: During long research sessions across multiple channels, it maintains a coherent context while respecting token budgets.
Quick Start
Enable this policy for an active Autosearch session to automatically manage context retention.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: autosearch:context-retention-policy Download link: https://github.com/0xmariowu/Autosearch/archive/main.zip#autosearch-context-retention-policy 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.