johnlindquist/claude/cass-memory

Name: cass-memory
Author: johnlindquist

Claude Code and agent skill by johnlindquist/claude

Trust tier 3

community

Source check pending

Checking that the SKILL.md file is still in the repository.

Contextual learning system that remembers patterns and rules from past sessions. Use to get relevant context before tasks, record outcomes, and build a personal playbook of coding patterns.

Install

npx vskill@latest install johnlindquist/claude/cass-memory

SKILL.md

CASS Memory - Contextual Learning System

Build and use a personal playbook of coding patterns learned from your sessions.

Prerequisites

The cm CLI should be available (part of cass-memory system).

Initialize:

bash

cm init
# Or with a starter playbook
cm init --starter typescript
cm init --starter react
cm init --starter python
cm init --starter go

CLI Reference

Get Context for a Task

bash

# THE main command - get relevant rules before starting work
cm context "Description of your task" --json

This returns:

Relevant rules from your playbook
Anti-patterns to avoid
History snippets from similar past work

Reflection (Extract Patterns)

bash

# Run reflection on recent sessions
cm reflect --json
 
# Specify lookback period
cm reflect --days 7 --json
cm reflect --days 30 --json

Playbook Management

bash

# List all rules
cm playbook list --json
 
# Get specific rule details
cm playbook get b-8f3a2c --json
 
# Add a new rule
cm playbook add "Always use optional chaining for nested object access" --json

Feedback on Rules

bash

# Mark rule as helpful
cm mark b-8f3a2c --helpful --json
cm mark b-8f3a2c --helpful --reason "Prevented null error" --json
 
# Mark rule as harmful
cm mark b-8f3a2c --harmful --json
cm mark b-8f3a2c --harmful --reason "Caused false positive" --json

Record Session Outcomes

bash

# Record success
cm outcome --status success --json
cm outcome --status success --rules "b-8f3a2c,b-4d2e1f" --json
 
# Record failure
cm outcome --status failure --text "Build failed due to type error" --json
 
# Mixed results
cm outcome --status mixed --text "Partial completion" --json

Statistics

bash

# Get playbook stats
cm stats --json

Top Rules

bash

# Show most effective rules
cm top --json
cm top 5 --json
cm top 20 --json

Health Check

bash

# Check system health
cm doctor --json
 
# Auto-fix issues
cm doctor --fix --json

Find Stale Rules

bash

# Rules without recent feedback
cm stale --json
cm stale --days 30 --json
cm stale --days 60 --json

Validate Rules

bash

# Validate a proposed rule against history
cm validate "Proposed rule text" --json

Explain Rule Origin

bash

# Show evidence and reasoning for a rule
cm why b-8f3a2c --json

Usage Statistics

bash

cm usage --json

Starter Playbooks

bash

# List available starters
cm starters --json

Workflow Patterns

Session Start

bash

# Get context before starting a task
cm context "Implement user authentication with JWT" --json

During Work

When a rule helps:

bash

cm mark b-8f3a2c --helpful --json

When a rule leads astray:

bash

cm mark b-8f3a2c --harmful --reason "Not applicable to this framework" --json

Session End

bash

# Record outcome
cm outcome --status success --rules "b-8f3a2c,b-4d2e1f" --json

Periodic Maintenance

bash

# Weekly: Run reflection to extract new patterns
cm reflect --days 7 --json
 
# Monthly: Review stale rules
cm stale --days 30 --json
 
# Check system health
cm doctor --json

Building Your Playbook

bash

# Manually add a pattern you've learned
cm playbook add "Use React.memo() for components receiving complex objects as props" --json
 
# After adding, use it in context queries
cm context "Create a list component with filtering" --json

Rule Lifecycle

Creation - Rules emerge from reflection or manual addition
Usage - Rules surface in context queries
Feedback - Mark as helpful/harmful based on experience
Evolution - High-feedback rules rise, low-feedback rules become stale
Retirement - Stale rules get reviewed and pruned

Best Practices

Always get context first - Run cm context "task" before starting work
Provide feedback - Mark rules as helpful/harmful
Record outcomes - Track session success/failure
Run reflection regularly - Weekly reflection extracts new patterns
Review stale rules - Don't let old rules accumulate
Add rules manually - When you learn something important

Integration Tips

Pre-Task Context

Before any significant coding task:

bash

CONTEXT=$(cm context "Your task description" --json)
# Use context to inform your approach

Post-Session Recording

At end of coding session:

bash

cm outcome --status success --text "Completed feature X" --json

Security

Security scanPassed, 95 of 100Pattern checks on the skill's files.
Model reviewPassed

See the full security report

Quality evaluation

Task evaluationNeutral, 77 of 100Ineffective. 1 run. Evaluated 8 months ago.

See evaluation results

Source

SKILL.md in the repositoryCheckingskills/cass-memory/SKILL.md

Popularity

Repository stars: 21
Repository forks: 5
7-day trend score: 15

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 3 Apr 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

Claude Code
Cursor
GitHub Copilot
Windsurf
Codex
Gemini CLI
Cline
Amp
Roo Code
Goose
Continue
Kilo Code
Junie
Trae
OpenHands
Qwen Code
AI Agent
Tabnine Chat
Sourcegraph Cody
Amazon Q
Firebase Genkit
Sweep
Devin
Phind
Mentat
Claude Desktop
Aider
GPT Pilot
Plandex
bolt.new
v0
Replit Agent
Anse
TypingMind
BetterChatGPT
LibreChat
Warp AI
Pieces
Fig AI

Embed badge

[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/johnlindquist/claude/cass-memory/badge)](https://verified-skill.com/skills/johnlindquist/claude/cass-memory)

Something wrong with this skill or its page? Tell us.