Skip to content

rustimacc/context-ledger-skills

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Context Ledger

Structured memory and snapshot history for AI agents

A multi-skill system for OpenCode and Claude Code that gives agents persistent, versioned memory across sessions — without rebuilding context or wasting tokens.


🚀 Quick Install

npx skills add rustimacc/context-ledger-skills --skill '*' -a opencode -a claude-code -g -y

🧠 What Problem Does This Solve?

Most agents break because:

  • context is implicit and messy
  • memory is lost between sessions
  • tokens are wasted rebuilding state
  • no reliable way to recover past decisions

Context Ledger fixes this.


🧩 What You Get

A complete memory system composed of:

  • persistent structured context
  • human-readable summaries
  • versioned snapshots (history)
  • selective context recovery

📦 Included Skills

Skill Purpose
save-context Store structured state + snapshot
load-context Restore current working context
list-context-history List available snapshots
load-context-from-history Load specific past states

🧱 How It Works

/agent-memory/
context.json → source of truth
context.md → readable summary
history/ → timestamped snapshots

Core idea:

  • JSON = machine memory
  • Markdown = agent context
  • History = controlled recall

🔁 Workflow

Save context

save the current context

Load context

load the context

Inspect history

list context history

Recover past states

load context from history:


⚙️ Installation Modes

Full pack (recommended)

npx skills add rustimacc/context-ledger-skills --skill '*' -a opencode -a claude-code -g -y

Interactive

npx skills add rustimacc/context-ledger-skills -a opencode -a claude-code

Single skill

npx skills add rustimacc/context-ledger-skills --skill save-context

🧠 Design Principles

  • structured > implicit context
  • minimal and actionable summaries
  • history is additive, not destructive
  • current context always wins
  • optimized for token efficiency

⚠️ Best Practices

  • save only at meaningful checkpoints
  • keep summaries short
  • avoid loading too many snapshots
  • use history as support, not primary context

🚫 Common Mistakes

  • storing full conversations
  • mixing too many historical states
  • overloading context with noise
  • not updating context after decisions

🧩 Compatibility

  • OpenCode
  • Claude Code

Los días más felices fueron, son y serán peronistas. Las Malvinas siempre ARGENTINAS 🇦🇷

✌️ VIVA PERÓN