skills.rest
9thLevelSoftware
9thLevelSoftwareCOMMUNITY
Explore all skills by this author →
GitHub

legion:memory-manager

Store and recall cross-session outcomes, patterns, and errors in .planning/memory.

72|8|Updated Mar 1, 2026
Search Tags:#recall#patterns#branching#memory#outcomes#decay#legion
One-click install
npx skills add https://github.com/9thLevelSoftware/legion --skill legion-memory-manager
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: legion:memory-manager
Source: https://github.com/9thLevelSoftware/legion/tree/main/skills/memory-manager
Command: npx skills add https://github.com/9thLevelSoftware/legion --skill legion-memory-manager

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cross-session memory enables Legion to remember outcomes, patterns, and errors across planning, execution, and review, improving agent recommendations and project continuity.

Core Features & Use Cases

  • Centralized memory layers store cross-session outcomes in .planning/memory/OUTCOMES.md to support recall and analytics
  • Distilled knowledge patterns captured in .planning/memory/PATTERNS.md for reusable playbooks and approaches
  • Branch-aware recall to keep memory scoped to the current experiment or project branch
  • Graceful degradation: workflows continue to function when memory is unavailable
  • Memory recall and decay scoring to inform agent selection and status briefings

Quick Start

Store an outcome after each plan or review cycle to populate the memory corpus.

Frequently Asked Questions about legion:memory-manager

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

FAQPage Schema
How do I persist agent memory across multiple sessions in Legion workflows?▼

Cross-session memory in Legion is persisted by storing outcomes, patterns, and errors in append-only Markdown tables within the .planning/memory directory to support recall and analytics.

What is branch-aware recall and how does it scope project memory?▼

Branch-aware recall keeps memory scoped to the current experiment or project branch, ensuring that pattern and outcome data remains isolated and relevant to the active context.

How do I start logging outcomes and patterns to build a reusable knowledge base?▼

To build the memory corpus, store an outcome after each plan or review cycle, which automatically populates OUTCOMES.md and PATTERNS.md with distilled knowledge for future playbooks.

Does Legion's memory manager continue functioning if memory storage becomes unavailable?▼

Graceful degradation ensures that Legion workflows continue to function normally when memory is unavailable, preventing hard failures during recall or storage operations.

How does memory decay scoring affect agent selection and status briefings?▼

Memory decay scoring reduces the weight of older outcomes over time, ensuring that recall operations prioritize recent patterns to inform more accurate agent selection and status briefings.

Can I store cross-session planning errors alongside successful outcomes for analytics?▼

Yes, cross-session memory coordinates errors alongside outcomes and patterns across planning, execution, and review cycles, storing them in Markdown tables to enhance project continuity analytics.

Related Skills

Explore More Software Engineering Skills→
9thLevelSoftware9thLevelSoftware
1

memory-manager

Stores and retrieves task outcomes and agent performance across Legion workflow sessions.

Community
Advanced
sixtycat2000-ctrlsixtycat2000-ctrl

briefing

Compile personalized daily briefings from local brain context.

Community
Intermediate
9thLevelSoftware9thLevelSoftware
1

marketing-workflows

Automate marketing campaign planning and content calendar generation.

Community
Advanced
boshu2boshu2
418

inject

Inject prior knowledge from .agents artifacts into session context at SessionStart.

Community
Basic