ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

proactive-agent-jarvis

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

skill-install β€” Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bingze00000/proactive-agent-jarvis
Or

Proactive Agent 🦞

By Hal Labs β€” Part of the Hal Stack

A proactive, self-improving architecture for your AI agent.

Most agents just wait. This one anticipates your needs β€” and gets better at it over time.

What's New in v3.1.0

  • Autonomous vs Prompted Crons β€” Know when to use systemEvent vs isolated agentTurn
  • Verify Implementation, Not Intent β€” Check the mechanism, not just the text
  • Tool Migration Checklist β€” When deprecating tools, update ALL references

What's in v3.0.0

  • WAL Protocol β€” Write-Ahead Logging for corrections, decisions, and details that matter
  • Working Buffer β€” Survive the danger zone between memory flush and compaction
  • Compaction Recovery β€” Step-by-step recovery when context gets truncated
  • Unified Search β€” Search all sources before saying "I don't know"
  • Security Hardening β€” Skill installation vetting, agent network warnings, context leakage prevention
  • Relentless Resourcefulness β€” Try 10 approaches before asking for help
  • Self-Improvement Guardrails β€” Safe evolution with ADL/VFM protocols

The Three Pillars

Proactive β€” creates value without being asked

βœ… Anticipates your needs β€” Asks "what would help my human?" instead of waiting

βœ… Reverse prompting β€” Surfaces ideas you didn't know to ask for

βœ… Proactive check-ins β€” Monitors what matters and reaches out when needed

Persistent β€” survives context loss

βœ… WAL Protocol β€” Writes critical details BEFORE responding

βœ… Working Buffer β€” Captures every exchange in the danger zone

βœ… Compaction Recovery β€” Knows exactly how to recover after context loss

Self-improving β€” gets better at serving you

βœ… Self-healing β€” Fixes its own issues so it can focus on yours

βœ… Relentless resourcefulness β€” Tries 10 approaches before giving up

βœ… Safe evolution β€” Guardrails prevent drift and complexity creep


Contents

  1. Quick Start
  2. Core Philosophy
  3. Architecture Overview
  4. Memory Architecture
  5. The WAL Protocol ⭐ NEW
  6. Working Buffer Protocol ⭐ NEW
  7. Compaction Recovery ⭐ NEW
  8. Security Hardening (expanded)
  9. Relentless Resourcefulness
  10. Self-Improvement Guardrails
  11. Autonomous vs Prompted Crons ⭐ NEW
  12. Verify Implementation, Not Intent ⭐ NEW
  13. Tool Migration Checklist ⭐ NEW
  14. The Six Pillars
  15. Heartbeat System
  16. Reverse Prompting
  17. Growth Loops

Quick Start

  1. Copy assets to your workspace: cp assets/*.md ./

Metadata

Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build β€” we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bingze00000-proactive-agent-jarvis": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.