How do I install the Context Hygiene skill?

Run npx skillmds@latest add m2ai-portfolio/context-hygiene in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Context Hygiene safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Context Hygiene?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Context Hygiene free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Context Hygiene?

m2ai-portfolio (@m2ai-portfolio) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Context Hygiene by m2ai-portfolio — Agent Skill

Name: Context Hygiene
Author: m2ai-portfolio

Context Hygiene

Reference for Claude Code context management. Use /by-the-way for side questions, /fork for path exploration, and context:fork in skills for isolated execution. Trigger on "context is getting large", "session feels slow", "Claude forgot what we were doing", "how do I manage context".

File contents

Context Hygiene — 3 Shields

Three techniques for keeping Claude Code sessions focused and performant. Use these proactively — context bloat is gradual and invisible until quality degrades.

Shield 1: /by-the-way (Side Questions)

For quick lookups that don't deserve main context space:

"What was that Calendly link?"
"How many slides in the last deck?"
"What's the standard meeting length?"

Usage: Type /by-the-way then your question. Answer returns without polluting the main conversation thread.

Best for: Static data retrieval, FAQ-style questions, quick lookups from CLAUDE.md or project files.

Shield 2: /fork (Path Exploration)

When you want to try a different approach without risking your current progress:

"Let me try a completely different design"
"What if we used a different tech stack?"
"Create version 2 from scratch"

Usage: Type /fork — creates a new conversation branch with full history. Returns a resume command to get back to the original conversation.

Best for: A/B testing approaches, exploring risky changes, version comparison.

Pro tip: Run multiple forks in parallel terminal sessions for simultaneous exploration.

Shield 3: context: fork (Skill Isolation)

Add context: fork to any SKILL.md frontmatter to run heavy skills in an isolated context window. See the context-fork-guide skill for full details.

When Context Gets Large

Signs your context is bloated:

Slower responses
Claude "forgets" earlier decisions
Suggestions become less relevant

Recovery:

/fork to start fresh with history preserved
/compact to summarize and compress context
For future sessions: apply context: fork to heavy skills proactively

Context Budget Rule of Thumb

Light session (single file edits, Q&A): 50K-100K tokens, no shields needed
Medium session (multi-file feature work): 100K-300K tokens, use /by-the-way for side queries
Heavy session (research + build): 300K+, fork skills and /fork for exploration branches

Source

Extracted from: 3 Claude Code Features You'll Wish You Knew Sooner by Mark Kashef (AI Automation Society), March 19, 2026.

---name: context-hygienedescription: Reference for Claude Code context management. Use /by-the-way for side questions, /fork for path exploration, and context:fork in skills for isolated execution. Trigger on "context is getting large", "session feels slow", "Claude forgot what we were doing", "how do I manage context".---# Context Hygiene — 3 ShieldsThree techniques for keeping Claude Code sessions focused and performant.Use these proactively — context bloat is gradual and invisible until quality degrades.## Shield 1: /by-the-way (Side Questions)For quick lookups that don't deserve main context space:- "What was that Calendly link?"- "How many slides in the last deck?"- "What's the standard meeting length?"Usage: Type `/by-the-way` then your question. Answer returns without pollutingthe main conversation thread.Best for: Static data retrieval, FAQ-style questions, quick lookups from CLAUDE.mdor project files.## Shield 2: /fork (Path Exploration)When you want to try a different approach without risking your current progress:- "Let me try a completely different design"- "What if we used a different tech stack?"- "Create version 2 from scratch"Usage: Type `/fork` — creates a new conversation branch with full history.Returns a resume command to get back to the original conversation.Best for: A/B testing approaches, exploring risky changes, version comparison.Pro tip: Run multiple forks in parallel terminal sessions for simultaneous exploration.## Shield 3: context: fork (Skill Isolation)Add `context: fork` to any SKILL.md frontmatter to run heavy skills in anisolated context window. See the context-fork-guide skill for full details.## When Context Gets LargeSigns your context is bloated:- Slower responses- Claude "forgets" earlier decisions- Suggestions become less relevantRecovery:1. `/fork` to start fresh with history preserved2. `/compact` to summarize and compress context3. For future sessions: apply `context: fork` to heavy skills proactively## Context Budget Rule of Thumb- Light session (single file edits, Q&A): 50K-100K tokens, no shields needed- Medium session (multi-file feature work): 100K-300K tokens, use /by-the-way for side queries- Heavy session (research + build): 300K+, fork skills and /fork for exploration branches## SourceExtracted from: [3 Claude Code Features You'll Wish You Knew Sooner](https://www.youtube.com/watch?v=iALzJyvgCoM) by Mark Kashef (AI Automation Society), March 19, 2026.

Frequently asked questions