Verified:GitHub

code-refactoring-context-restore

Restore project context from memory stores using semantic retrieval and token-budget management.

Updated Feb 24, 2026

Search Tags:#multi-agent #provenance #context-management #semantic-memory #vector-search #token-budget #context-restoration

Ready to run

npx skills add https://github.com/chicanoandres702/SentientAIBrowser --skill code-refactoring-context-restore-chicanoandres702

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: code-refactoring-context-restore
Source: https://github.com/chicanoandres702/SentientAIBrowser/tree/main/.agents/workflows/code-refactoring-context-restore
Command: npx skills add https://github.com/chicanoandres702/SentientAIBrowser --skill code-refactoring-context-restore-chicanoandres702

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Long-running AI projects often lose context as agents switch tasks and memory fragments emerge across workflows. This Skill provides deterministic context restoration to preserve and reconstruct project knowledge with high fidelity and minimal information loss.

Core Features & Use Cases

Semantic vector search and relevance filtering for accurate context retrieval
Incremental and full context restoration with token-budget management
Session state reconstruction and provenance preservation across multi-agent workflows
Context merging, validation, and conflict resolution to maintain decision traceability

Quick Start

Run context-restoration for project:my-project with mode set to full and a token_budget of 8192 to restore the complete context.

Frequently Asked Questions about code-refactoring-context-restore

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I restore project context across distributed AI workflows?▼

Project context restoration reconstructs state from memory stores using semantic vector search and incremental loading, ensuring continuity and decision traceability across multi-agent pipelines with minimal information loss.

Why does my multi-agent pipeline lose memory when switching tasks?▼

Multi-agent pipelines lose memory because context fragments across distributed workflows. Deterministic context restoration solves this by preserving project knowledge and reconstructing session state with high fidelity.

How can I manage token budgets when reconstructing long-running project context?▼

Manage token budgets during context reconstruction by configuring incremental context loading. Set a specific token_budget parameter, such as 8192, to retrieve only the most relevant semantic information within limits.

What is the best way to maintain decision traceability across multi-agent workflows?▼

Maintain decision traceability across multi-agent workflows by implementing provenance retention and conflict resolution during context merging, ensuring that all historical decisions and session states are preserved and validated.

Can I use semantic vector search for cross-project knowledge transfer?▼

Yes, you can use semantic vector search to enable cross-project knowledge transfer. It filters and retrieves relevant context from memory stores, allowing you to apply reconstructed knowledge to new distributed AI workflows.

How do I do a full context restoration for a specific project?▼

Execute a full context restoration by targeting your specific project identifier and setting the mode to full. Provide a defined token_budget to retrieve the complete reconstructed project knowledge from memory.