---

name: memory-optimizer description: Refactors CLAUDE.md into minimal startup context by extracting path-specific rules, skills, commands, and agents. Use when CLAUDE.md exceeds 50 lines, startup feels slow, memory needs restructuring, or splitting monolithic project instructions.

Memory Optimizer

Restructures .claude/CLAUDE.md using progressive disclosure to minimize startup tokens.

Decision Table

Workflow

1. Analyze: Read CLAUDE.md, count lines
2. Categorize: Apply decision table to each section
3. Plan: Present extraction table for approval
4. Extract: Create files with proper frontmatter
5. Refactor: Reduce CLAUDE.md to <50 lines
6. Report: Show before/after line counts

Extraction Plan Format

Present before creating files:

Copy| Content        | Extract To                     | Type    | Trigger/Path        |
| -------------- | ------------------------------ | ------- | ------------------- |
| TS conventions | .claude/rules/typescript.md    | Rule    | `**/*.ts`           |
| Deploy process | .claude/skills/deploy/SKILL.md | Skill   | "deploy", "release" |
| PR template    | .claude/commands/review.md     | Command | `/review`           |
| Security check | .claude/agents/security.md     | Agent   | security tasks      |

File Templates

Rule

Copy---
paths: src/**/*.ts
---
# {Topic}
{ Instructions }

Skill

Copy---
name: {kebab-case}
description: {What it does}. Use when {triggers}.
---
# {Name}
{Instructions}

Command

Copy---
description: { Brief description }
---
{ Prompt template with $ARGUMENTS }

Agent

Copy---
name: {name}
description: {When to delegate}. Use proactively for {triggers}.
tools: Read, Grep, Glob
---
# {Name}
{Instructions}

Refactored CLAUDE.md Target

Copy# {Project}

{1-2 sentence overview}

## Commands

- Build: `{cmd}`
- Test: `{cmd}`

## References

- @README.md
- @docs/architecture.md

Goal: <50 lines, ideally 20-30

Validation

After extraction, verify:

• CLAUDE.md line count reduced
• Each file has valid YAML frontmatter
• Rules have paths:, skills have description: with "Use when"

Description Formula

{Verb} {what}. Use when {trigger1}, {trigger2}, or {trigger3}.

Bad: Helps with code review Good: Reviews code for security and performance issues. Use when reviewing PRs, checking code quality, or after major changes.