context-health

Name: context-health
Availability: InStock
Author: kgan01

Detect context degradation and apply recovery strategies in long-running tasks.

6|Updated Apr 7, 2026

Search Tags:#checkpoint #drift-detection #token-budget #long-running-tasks #context-health #re-anchoring #recovery-strategies

Ready to run

npx skills add https://github.com/Kgan01/ghengis-skills --skill context-health-kgan01

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-health
Source: https://github.com/Kgan01/ghengis-skills/tree/main/plugins/ghengis-skills/skills/context-health
Command: npx skills add https://github.com/Kgan01/ghengis-skills --skill context-health-kgan01

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Detects when a long conversation or multi-step task degrades due to context window pressure, task drift, or tool failures, and offers recovery options to maintain progress.

Core Features & Use Cases

Drift detection across multi-turn interactions to preserve intent.
Recovery strategies: truncate, checkpoint restart, re-anchoring, or warnings.
Context-awareness tooling: threshold-based checks, cooldowns, and safe reset mechanisms.

Quick Start

Monitor a running task and apply a recovery strategy when drift or context pressure is detected to keep the task on track.

Frequently Asked Questions about context-health

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect context drift in long-running multi-step tasks?▼

Context drift in long-running tasks is detected using heuristic checks that measure divergence between user intent and assistant output across multiple turns. Threshold-based monitoring flags degradation so recovery strategies can be applied.

What's the best way to handle context window pressure during long conversations?▼

Context window pressure is handled by monitoring token budget thresholds and applying recovery strategies like truncation or checkpoint restart. These mechanisms prevent context degradation from breaking long conversation progress.

How do I recover a multi-step task after tool failures cause context degradation?▼

Recover from tool failure context degradation by applying re-anchoring or checkpoint restart strategies. The system detects high tool failure rates and triggers safe reset mechanisms with cooldowns to restore task progress.

When do I need to apply re-anchoring or truncation to preserve user intent?▼

Re-anchoring or truncation is needed when heuristic drift detection identifies a significant gap between the original user intent and current assistant output. Applying these recovery strategies realigns the conversation safely.

Can I monitor token budget thresholds to prevent context degradation in long horizons?▼

Yes, you can monitor token budget thresholds to prevent context degradation in long horizons. The system tracks token usage and triggers user warnings or truncation when thresholds are exceeded during multi-step tasks.

What are the limitations of using checkpoint restarts for long-running conversation recovery?▼

Checkpoint restarts for long-running conversation recovery require re-establishing context from the saved state, which may lose intermediate tool call results. Cooldowns and safe reset mechanisms mitigate but do not eliminate data loss risks.