Rechercher

PythonReactSEOPDF
OpenClaw

context-guardian

Proactive context monitoring with smart 3-level alerts. Know when to restart before quality degrades.

brucey0017-cloud0 installations selon la source☆ 0 Étoiles du dépôtv1.0.1

Installation

Suivez les instructions du dépôt pour votre agent. Consultez les fichiers et dépendances avant l’installation.

SkillHub CLI

skillhub install brucey0017-cloud/context-guardian

Examinez la source et la compatibilité, puis suivez les étapes d’installation.

Donnez le lien à votre agent et demandez-lui d’examiner instructions et dépendances avant d’expliquer les étapes.

Voir la source ↗Guides

Instructions

Context Guardian 🛡️

Your context guardian. Alerts before errors happen.

Proactive context monitoring that warns you at 60%, 70%, and 85% usage — before context pollution causes errors and hallucinations.


Why You Need This

The Problem:

  • Long conversations lead to context pollution
  • Quality degrades silently as context fills up
  • You don't know when to restart until it's too late
  • Errors and hallucinations increase after ~70% usage

The Solution:

  • Continuous monitoring of context usage
  • Smart 3-level alerts (⚠️ 60%, 🟠 70%, 🔴 85%)
  • Actionable suggestions at each level
  • Prevents duplicate alerts

Quick Start

For Agents: Heartbeat Integration

When you receive a heartbeat poll, include this check:

  1. Call session_status tool to get current context usage
  2. Parse the context percentage from the output
  3. Compare against thresholds: 60% (warning), 70% (danger), 85% (critical)
  4. If threshold exceeded and not a duplicate alert, display the appropriate alert message
  5. Update state file to track alert history

Implementation:

During heartbeat:
1. Get context usage from session_status
2. Check if usage >= 60%, 70%, or 85%
3. Load state from memory/context-guardian-state.json
4. Determine if alert should be sent (prevent duplicates)
5. If yes, display alert and update state
For Users: Enable in HEARTBEAT.md

Add to your HEARTBEAT.md:

## Context Monitoring
- Check context usage
- Alert if thresholds exceeded (60%, 70%, 85%)

The agent will automatically handle the rest.


How It Works

Monitoring

The skill calls session_status to check your current context usage percentage.

Alert Levels

⚠️ Warning (60%)

⚠️ Context: 60%
Getting full. Consider wrapping up or starting fresh soon.

🟠 Danger (70%)

🟠 Context: 70%
Pollution risk rising. Recommend:
• Finish current task
• Start new session for next task
• Or compress with context-optimizer

**🔴 Critical...

Informations sur la source

Source
github
Repository
openclaw/skills
Path
skills/brucey0017-cloud/context-guardian
Version
1.0.1
Commit
3186bb371d2e50a84c778e572c1332b312f11768
Source de classification
rules
Statut
active
Visibilité
public

Ces informations proviennent de l’analyse indexée et peuvent être anciennes. Vérifiez les fichiers actuels.

README

Context Guardian 🛡️

Your context guardian. Alerts before errors happen.

Proactive context monitoring with smart 3-level alerts (60%, 70%, 85%). Know when to restart before quality degrades.

Features

  • 🛡️ Proactive protection against context pollution
  • 📊 Real-time monitoring with zero overhead
  • 🚨 Smart 3-level alerts (60%, 70%, 85%)
  • 🔧 Highly configurable thresholds and alert styles
  • 🤝 Integrates with context-optimizer and context-recovery

Quick Start

  1. Install:

    clawhub install context-guardian
    
  2. Add to HEARTBEAT.md:

    ## Context Monitoring
    - Check context usage via context-guardian
    
  3. Done! You'll get alerts when context usage reaches thresholds.

Why You Need This

Long conversations lead to context pollution. Quality degrades silently as context fills up. You don't know when to restart until it's too late.

Context Guardian monitors your context usage and alerts you before errors happen:

  • ⚠️ 60% - Warning: Consider wrapping up
  • 🟠 70% - Danger: Finish current task, start fresh
  • 🔴 85% - Critical: High error risk, restart NOW

Documentation

See SKILL.md for full documentation.

License

MIT

Contenu extrait

SKILL.md
# Context Guardian 🛡️

**Your context guardian. Alerts before errors happen.**

Proactive context monitoring that warns you at 60%, 70%, and 85% usage — before context pollution causes errors and hallucinations.

---

## Why You Need This

**The Problem:**
- Long conversations lead to context pollution
- Quality degrades silently as context fills up
- You don't know when to restart until it's too late
- Errors and hallucinations increase after ~70% usage

**The Solution:**
- Continuous monitoring of context usage
- Smart 3-level alerts (⚠️ 60%, 🟠 70%, 🔴 85%)
- Actionable suggestions at each level
- Prevents duplicate alerts

---

## Quick Start

### For Agents: Heartbeat Integration

When you receive a heartbeat poll, include this check:

1. Call `session_status` tool to get current context usage
2. Parse the context percentage from the output
3. Compare against thresholds: 60% (warning), 70% (danger), 85% (critical)
4. If threshold exceeded and not a duplicate alert, display the appropriate alert message
5. Update state file to track alert history

**Implementation:**

```
During heartbeat:
1. Get context usage from session_status
2. Check if usage >= 60%, 70%, or 85%
3. Load state from memory/context-guardian-state.json
4. Determine if alert should be sent (prevent duplicates)
5. If yes, display alert and update state
```

### For Users: Enable in HEARTBEAT.md

Add to your `HEARTBEAT.md`:

```markdown
## Context Monitoring
- Check context usage
- Alert if thresholds exceeded (60%, 70%, 85%)
```

The agent will automatically handle the rest.

---

## How It Works

### Monitoring

The skill calls `session_status` to check your current context usage percentage.

### Alert Levels

**⚠️ Warning (60%)**
```
⚠️ Context: 60%
Getting full. Consider wrapping up or starting fresh soon.
```

**🟠 Danger (70%)**
```
🟠 Context: 70%
Pollution risk rising. Recommend:
• Finish current task
• Start new session for next task
• Or compress with context-optimizer
```

**🔴 Critical...
README
# Context Guardian 🛡️

**Your context guardian. Alerts before errors happen.**

Proactive context monitoring with smart 3-level alerts (60%, 70%, 85%). Know when to restart before quality degrades.

## Features

- 🛡️ **Proactive protection** against context pollution
- 📊 **Real-time monitoring** with zero overhead
- 🚨 **Smart 3-level alerts** (60%, 70%, 85%)
- 🔧 **Highly configurable** thresholds and alert styles
- 🤝 **Integrates** with context-optimizer and context-recovery

## Quick Start

1. Install:
   ```bash
   clawhub install context-guardian
   ```

2. Add to `HEARTBEAT.md`:
   ```markdown
   ## Context Monitoring
   - Check context usage via context-guardian
   ```

3. Done! You'll get alerts when context usage reaches thresholds.

## Why You Need This

Long conversations lead to context pollution. Quality degrades silently as context fills up. You don't know when to restart until it's too late.

Context Guardian monitors your context usage and alerts you **before** errors happen:

- ⚠️ **60%** - Warning: Consider wrapping up
- 🟠 **70%** - Danger: Finish current task, start fresh
- 🔴 **85%** - Critical: High error risk, restart NOW

## Documentation

See [SKILL.md](SKILL.md) for full documentation.

## License

MIT

Skills associés

OpenClaw

xint

0xnyk

X Intelligence CLI — search, monitor, analyze, and engage on X/Twitter. TypeScript + Bun. AI agent skill.

OpenClaw

bambu-studio-ai

heyixuan2

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...

OpenClaw

flightclaw

jackculpan

Track flight prices from Google Flights with this OpenClaw skill. Search routes, monitor prices, and get alerts when prices drop.

OpenClaw

openclaw-trading-assistant

openclaw-trade

openclaw trading assistant| openclaw trading skill | nof1.ai & openclaw [moltbot] collaboration | We get the best practices from alpha arena trading seasons and bring it to clawdbot All top AI agents, realtime...