# Doncheli Context Health

> Report the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".

- **Type:** Skill
- **Install:** `agentstack add skill-doncheli-don-cheli-sdd-doncheli-context-health`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [doncheli](https://agentstack.voostack.com/s/doncheli)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [doncheli](https://github.com/doncheli)
- **Source:** https://github.com/doncheli/don-cheli-sdd/tree/main/.opencode/skills/doncheli-context-health
- **Website:** https://doncheli.tv

## Install

```sh
agentstack add skill-doncheli-don-cheli-sdd-doncheli-context-health
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Don Cheli: Context Health Monitor

## Instructions

1. Estimate the current context window usage based on:
   - Files loaded in the current session
   - Conversation length (turns × average tokens)
   - Any large outputs already in context
2. Report usage as a percentage of the model's context limit
3. Apply thresholds from the global rules:
   - > 50K tokens in a result → recommend isolating in subagent
   - > 200K session tokens → recommend summarizing and compressing context
4. Identify the highest-cost items in the current context:
   - Large file reads
   - Repeated content
   - Verbose tool outputs that could be summarized
5. Recommend specific actions:
   - Which files can be evicted (already processed)
   - Which outputs should be summarized
   - Whether a subagent should handle the next task
6. If context is healthy (< 40% used), confirm and suggest no action
7. Never truncate or discard context without explicit user confirmation

## Output Format

```
## Context Health — 2026-03-28T16:00Z

### Usage Estimate
- Current session: ~85K tokens
- Model limit: 200K tokens
- Usage: 42% ✅ (healthy)

### Largest Items
1. src/payments/processor.ts full read — ~8K tokens (can evict — already analyzed)
2. Test run output from 14:32 — ~12K tokens (can summarize — report saved)
3. Conversation history — ~18K tokens (normal)

### Recommendations
- No immediate action required
- If you add 3+ more large files, consider /dc:destilar to compress session notes
- Next heavy task: use a subagent to isolate output

### Warning Threshold
Will warn again at 70% usage (~140K tokens)
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [doncheli](https://github.com/doncheli)
- **Source:** [doncheli/don-cheli-sdd](https://github.com/doncheli/don-cheli-sdd)
- **License:** Apache-2.0
- **Homepage:** https://doncheli.tv

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-doncheli-don-cheli-sdd-doncheli-context-health
- Seller: https://agentstack.voostack.com/s/doncheli
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.