skills.rest
tuantiensiu
tuantiensiuCOMMUNITY
Explore all skills by this author →
GitHub

session-management

Manage session context with thresholds and tools for memory pruning and transfer.

1|Updated Jan 10, 2026
Search Tags:#workflow#context#memory#session-management#ai-agent#pruning#task-switching
One-click install
npx skills add https://github.com/tuantiensiu/todo-app --skill session-management-tuantiensiu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: session-management
Source: https://github.com/tuantiensiu/todo-app/tree/main/.opencode/skill/session-management
Command: npx skills add https://github.com/tuantiensiu/todo-app --skill session-management-tuantiensiu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Context management becomes challenging when working on long sessions or switching tasks; this Skill helps by defining thresholds and providing tools to prune, summarize, and transfer memory so you can resume work efficiently.

Core Features & Use Cases

  • Context thresholds at 70%, 85%, and 95% with recommended actions such as consolidation, summarization, and session restart.
  • Session Tools: list_sessions, read_session, search_session, summarize_session to discover, retrieve, search, and summarize past work.
  • Memory and workflow patterns: recommended best practices for pruning, memory extraction, and starting new sessions to maintain performance and cost efficiency.

Use cases include starting new tasks within the same project, resuming work after interruptions, and cross-project memory retrieval.

Quick Start

Start a new session and pull the most recent context to continue work.

Frequently Asked Questions about session-management

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

FAQPage Schema
How do I manage AI agent context when switching between tasks?▼

You can manage AI agent context during task-switching by using session tools to summarize and transfer memory. This Skill implements thresholds and workflow patterns to prune context efficiently so you can resume work without losing track.

What is context pruning and when should I do it in a long-running project?▼

Context pruning is summarizing and consolidating memory to reduce session length. In long-running projects, prune context when thresholds hit 70%, 85%, or 95%, triggering actions like consolidation, summarization, or session restart to maintain efficiency.

How do I resume work after an interruption in a multi-task workflow?▼

To resume work after an interruption in a multi-task workflow, start a new session and pull the most recent summarized context. Use search_session and read_session tools to retrieve past memory and continue where you left off.

Does this session management approach work for cross-project memory retrieval?▼

Yes, this approach supports cross-project memory retrieval by providing search and read session tools. You can discover, retrieve, and summarize past work across different projects, enabling efficient memory transfer and context recovery.

Why does my AI agent lose track of context in long sessions?▼

AI agents lose track in long sessions because unmanaged memory accumulates, degrading performance and increasing costs. Applying context thresholds and pruning workflows to summarize and consolidate memory prevents overload and maintains session focus.

Related Skills

Explore More Software Engineering Skills→
kimasplundkimasplund

memory-consolidation

Consolidate cross-session memories by detecting patterns, resolving conflicts, and applying temporal decay.

Community
Intermediate
einargudnigeinargudnig

continue-work

Reads MEMORY.md and git state to summarize pending work.

Community
Intermediate
anthony-chaudharyanthony-chaudhary
30

ctx-overlay

Compact the active context window and prune the memory store.

Community
Basic
tarrragontarrragon
1

strategic-compact

Prompt manual context compaction at strategic workflow milestones via a PreToolUse hook.

Community
Intermediate