# Context Optimize

> Purpose

- Skill: `joonghyun-lee-frieren/context-optimize` (Agent Skill)
- Install (CLI): `npx skillmds@latest add joonghyun-lee-frieren/context-optimize`
- Raw SKILL.md: https://api.skillmd.com/api/skills/joonghyun-lee-frieren/context-optimize/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: Joonghyun-Lee-Frieren (https://skillmd.com/u/joonghyun-lee-frieren)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/joonghyun-lee-frieren/context-optimize

---


## Purpose

Use this skill when context is growing quickly or cache consistency drops.

## Trigger

- Conversation becomes long and repetitive
- The model loses thread coherence
- Frequent prompt restarts or unstable behavior appears

## Workflow

1. Identify repeated, stale, or low-value context.
2. Detect likely cache breakers (instruction churn, unstable prefixes).
3. Propose cache-safe compaction and message hygiene rules.
4. Produce an actionable operating checklist for next turns.

## Output Template

```markdown
## Context Health
- ...

## Cache Risks
- ...

## Optimization Actions
1. ...
2. ...
3. ...

## Session Rules
- ...
```

## Notes

- Keep stable instructions unchanged during a session.
- Prefer summaries over re-sending raw large blocks.