context-engineering

name	context-engineering
description	Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).

Context Engineering Skill

Optimizes Claude Code context for better performance and accuracy.

Tracked files in repo: !git ls-files 2>/dev/null | wc -l || true

Auto-Invoke Triggers

• Every 50 messages in conversation
• After major refactoring
• When context feels stale
• Task switching
• User requests /context command

Context Principles

Active Curation

• Keep only relevant information
• Remove completed task details
• Archive outdated patterns
• Focus on current work

Signal-to-Noise Ratio

High Signal	Low Signal
Current APIs	Old experiments
Active patterns	Completed tasks
Recent decisions	Historical context
Project structure	Implementation details

Token Budget

File	Limit	Purpose
CLAUDE.md	< 2000 tokens	Quick reference
Agent docs	< 500 per agent	Role definition
Skills	< 300 per skill	Methodology

Context Analysis Process

Step 1: Measure Current State

## Context Analysis

### Token Counts
- CLAUDE.md: XXX tokens
- Agent docs: XXX tokens total
- Skills: XXX tokens total
- Total: XXXX tokens

### Staleness Check
- [ ] Last updated: [date]
- [ ] References current project state
- [ ] No deprecated APIs/patterns

Step 2: Identify Issues

### Issues Found

#### Stale Content
- Section X: Outdated [reason]
- Section Y: No longer relevant

#### Redundant Content
- Duplicated in files A and B
- Can consolidate X and Y

#### Missing Content
- Current API not documented
- New pattern not captured

Step 3: Optimization Actions

### Optimization Plan

1. **Archive**: Move section X to knowledge-core.md
2. **Remove**: Delete duplicate Y
3. **Update**: Refresh API documentation
4. **Add**: Document new pattern Z

CLAUDE.md Structure

Optimal structure for quick reference:

# Project Name

[One-line description]

## Quick Reference
| Action | Command |
|--------|---------|
| Run | command |
| Test | command |
| Build | command |

## Agent System
[Link to detailed docs]

## Tech Stack
- Frontend: [stack]
- Backend: [stack]

## Project Structure
[Key directories only]

## Key Rules
1. [Critical rule]
2. [Critical rule]

Always-loaded vs lazy path-scoped rules

CLAUDE.md content splits into two tiers by when it must be available:

Tier	Lives in	Loads	Examples
Always-loaded	project-root CLAUDE.md	every message, before any file is touched	routing Protocol + Decision Tree + Agents table
Lazy / path-scoped	nested CLAUDE.md in a subdir	only while editing under that directory tree	per-area code conventions, stack notes, types location

Hard rule: the routing sections NEVER move into a nested CLAUDE.md — routing must fire on the first message, but a nested file only loads on Edit/Write under its tree (too late to route). Only path-specific code conventions are candidates to relocate, and only via the opt-in /init-rules scaffolder. This trims always-loaded tokens (modest for the plugin CLAUDE.md, larger for heavy project repos) without weakening routing. /doctor asserts the routing section is still present in the root CLAUDE.md.

Optimization Strategies

Token Reduction

• Use tables instead of prose
• Link to details instead of inline
• Remove examples from main docs
• Keep explanations brief

Information Hierarchy

1. Immediate: In CLAUDE.md
2. Reference: In linked docs
3. Archive: In knowledge-core.md
4. Delete: Truly obsolete

Import Chain Management

• Max 5 levels of imports
• No circular references
• Clear dependency direction

Context Health Metrics

Metric	Healthy	Warning	Critical
CLAUDE.md tokens	< 1500	1500-2500	> 2500
Stale sections	0	1-2	3+
Redundancy	0%	< 10%	> 10%
Missing critical	0	1	2+

Maintenance Schedule

Trigger	Action
Every 50 messages	Quick analysis
After major change	Update relevant sections
Weekly	Full review
Task switch	Clear task-specific context

Output: Context Report

## Context Report

**Date**: [date]
**Health**: Healthy | Warning | Critical

### Metrics
- Total tokens: XXXX
- Stale sections: X
- Redundancy: X%

### Findings
1. [Finding]
2. [Finding]

### Recommendations
1. [Action to take]
2. [Action to take]

### Potential Savings
- Current: XXXX tokens
- After optimization: XXXX tokens
- Savings: XX%