Run any Skill in Manus with one click

Get Started

$pwd:

memory-guardian

Name: Memory Guardian
Author: frankxai

// WSL2 memory safety and scaling guardrails for Claude Code sessions and parallel agents.

Run Skill in Manus

$ git log --oneline --stat

stars:0

forks:0

updated:February 20, 2026 at 19:21

File Explorer

2 files

SKILL.md

readonly

name	memory-guardian
description	WSL2 memory safety and scaling guardrails for Claude Code sessions and parallel agents.

Memory Guardian Skill

Purpose

Monitors WSL2 memory usage and enforces safe scaling limits for Claude Code instances and parallel agents.

When This Skill Activates

Before spawning 3+ parallel Task agents
Before running npm run build or other memory-heavy operations
When SessionStart hook reports WARNING or CRITICAL memory status
When user mentions running multiple CC instances

Memory Check Command

free -m | awk '/^Mem:/{printf "RAM: %dMB/%dMB (%d%%)\n", $3, $2, $3*100/$2} /^Swap:/{if($3>0) printf "Swap: %dMB/%dMB\n", $3, $2}'

Scaling Rules

Green Zone (< 75% RAM usage)

Parallel Task agents: up to 4
Background builds: safe
No restrictions

Yellow Zone (75-89% RAM usage)

Parallel Task agents: max 2
Prefer sequential over parallel work
Avoid npm run build alongside agents
Warn user: "Memory pressure is high. Limiting parallel agents to 2."

Red Zone (>= 90% RAM usage)

Parallel Task agents: max 1 (or 0 — work sequentially)
NO background builds
Suggest user close other CC instances
Warn user: "Memory critically low. Working sequentially to prevent WSL crash."

Before Heavy Operations

Always run the memory check before:

Spawning 3+ parallel Task subagents
Running production builds (npm run build)
Starting dev server + agents simultaneously

WSL Configuration Reference

Host: 16GB RAM
WSL limit: 12GB (C:\Users\Frank\.wslconfig)
Swap: 12GB
Per CC instance: ~500MB + ~100-150MB per MCP server
Safe concurrent CC instances: 4-5
autoMemoryReclaim: dropcache (aggressive)

Recovery If Memory Is Critical

# Check what's using memory
ps aux --sort=-%mem | head -20

# Kill any orphaned node processes from old CC sessions
pkill -f "node.*claude" 2>/dev/null

# Force kernel to drop caches (non-destructive)
echo 1 | sudo tee /proc/sys/vm/drop_caches 2>/dev/null

Integration

Hook: .claude/hooks/memory-check.sh runs on SessionStart
Statusline: Memory percentage visible if hook fires warning
Self-enforcing: CC reads this skill and self-limits before scaling

related-skills.json

same repository

brand-voice.md

from "frankxai/acos-intelligence-system"

Apply and enforce brand voice across all content creation. Manages voice attributes, tone adaptation by channel, style rules, and terminology. Use when writing content, reviewing drafts, or defining brand voice for a new project. Loads voice config from CREATOR.md or creator-memory/voice.md.

2026-02-230

creator-productivity.md

from "frankxai/acos-intelligence-system"

Task management and workspace memory for creative work sessions. Manages a TASKS.md file for project tracking, a two-tier memory system (CREATOR.md + creator-memory/), and a daily sprint structure. Use when organizing creative projects, tracking content tasks, or starting a focused work session.

2026-02-230

acos-meta.md

from "frankxai/acos-intelligence-system"

ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.

2026-02-230

ai-architect-newsletter.md

from "frankxai/acos-intelligence-system"

Generate high-quality AI Architect newsletters with latest AI news, research integration, and visual design. Use when creating newsletters, researching AI developments, synthesizing AI news for architects, or distributing intelligence reports. Covers AI model releases, research papers, tool launches, architecture patterns, production systems, and enterprise AI trends. Integrates with FrankX research hub and supports both daily briefs and weekly deep-dives.

2026-02-200

book-publishing.md

from "frankxai/acos-intelligence-system"

ACOS book publishing intelligence for multi-book content, voice, and production workflows.

2026-02-200

game-development.md

from "frankxai/acos-intelligence-system"

ACOS game development intelligence for high-quality browser game design and implementation.

2026-02-200

package.json

"author": "frankxai"

"repository": "frankxai/acos-intelligence-system"

View GitHub Repository View Creator Repositories

$ install --global

$ download --local

Run Skill in Manus

$ useful --forSOC

Network and Computer Systems AdministratorsComputer and Mathematical Occupations15-1244L4

name	memory-guardian
description	WSL2 memory safety and scaling guardrails for Claude Code sessions and parallel agents.

Memory Guardian Skill

Purpose

Monitors WSL2 memory usage and enforces safe scaling limits for Claude Code instances and parallel agents.

When This Skill Activates

Before spawning 3+ parallel Task agents
Before running npm run build or other memory-heavy operations
When SessionStart hook reports WARNING or CRITICAL memory status
When user mentions running multiple CC instances

Memory Check Command

free -m | awk '/^Mem:/{printf "RAM: %dMB/%dMB (%d%%)\n", $3, $2, $3*100/$2} /^Swap:/{if($3>0) printf "Swap: %dMB/%dMB\n", $3, $2}'

Scaling Rules

Green Zone (< 75% RAM usage)

Parallel Task agents: up to 4
Background builds: safe
No restrictions

Yellow Zone (75-89% RAM usage)

Parallel Task agents: max 2
Prefer sequential over parallel work
Avoid npm run build alongside agents
Warn user: "Memory pressure is high. Limiting parallel agents to 2."

Red Zone (>= 90% RAM usage)

Parallel Task agents: max 1 (or 0 — work sequentially)
NO background builds
Suggest user close other CC instances
Warn user: "Memory critically low. Working sequentially to prevent WSL crash."

Before Heavy Operations

Always run the memory check before:

Spawning 3+ parallel Task subagents
Running production builds (npm run build)
Starting dev server + agents simultaneously

WSL Configuration Reference

Host: 16GB RAM
WSL limit: 12GB (C:\Users\Frank\.wslconfig)
Swap: 12GB
Per CC instance: ~500MB + ~100-150MB per MCP server
Safe concurrent CC instances: 4-5
autoMemoryReclaim: dropcache (aggressive)

Recovery If Memory Is Critical

# Check what's using memory
ps aux --sort=-%mem | head -20

# Kill any orphaned node processes from old CC sessions
pkill -f "node.*claude" 2>/dev/null

# Force kernel to drop caches (non-destructive)
echo 1 | sudo tee /proc/sys/vm/drop_caches 2>/dev/null

Integration

Hook: .claude/hooks/memory-check.sh runs on SessionStart
Statusline: Memory percentage visible if hook fires warning
Self-enforcing: CC reads this skill and self-limits before scaling

memory-guardian

Memory Guardian Skill

Purpose

When This Skill Activates

Memory Check Command

Scaling Rules

Green Zone (< 75% RAM usage)

Yellow Zone (75-89% RAM usage)

Red Zone (>= 90% RAM usage)

Before Heavy Operations

WSL Configuration Reference

Recovery If Memory Is Critical

Integration

More from this repository

More from this repository

Memory Guardian Skill

Purpose

When This Skill Activates

Memory Check Command

Scaling Rules

Green Zone (< 75% RAM usage)

Yellow Zone (75-89% RAM usage)

Red Zone (>= 90% RAM usage)

Before Heavy Operations

WSL Configuration Reference

Recovery If Memory Is Critical

Integration