Context Engineering

Four operations control everything about how context flows through an AI coding session. Master them and you control the quality of every response.

The Four Operations

1. Write — Persist Info Outside Context

Move information out of the context window into durable storage so it survives compaction and session boundaries.

Where to write:

.claude/memory/

[LEARN]

Pattern — Scratchpad workflow:

1. Start complex task → create NOTES.md with goals and constraints
2. After research → write findings to NOTES.md
3. After compaction → NOTES.md survives, context does not
4. Resume → read NOTES.md to recover full state

2. Select — Retrieve Relevant Info

Pull the right information into context at the right time. Precision matters more than volume.

Methods ranked by precision:

1. @file

   references — exact file injection

2. grep

   /

   Glob

   — targeted pattern search
3. Subagent exploration — delegated deep search
4. RAG / embeddings — semantic retrieval for large codebases

Key principle: Focused 300 tokens > unfocused 113K tokens.

A surgical grep result that returns the exact function signature beats dumping an entire module into context. Every irrelevant token dilutes attention.

Pattern — Progressive retrieval:

1. Start with file names (Glob)
2. Narrow to specific functions (Grep)
3. Read only the relevant lines (Read with offset+limit)
4. Never read entire large files when you need one function

3. Compress — Reduce Tokens, Preserve Signal

Shrink context without losing the information that matters.

Compaction strategies:

/compact

/compact focus: auth module changes

Compaction triggers:

• After planning, before implementation
• After completing a feature or milestone
• When context exceeds 50% (set

  CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=50

  )
• Before switching task domains
• After heavy search/read operations

PostCompact hook — Re-inject critical context:

{
  "type": "PostCompact",
  "command": "cat .claude/critical-context.md"
}

Use this to ensure project rules, current task state, or architecture constraints survive every compaction.

4. Isolate — Partition Across Execution Spaces

Don't load everything into one context. Split work across independent execution spaces.

claude -w

/btw

/resume

Pattern — Subagent delegation:

Main session: planning, coordination, commits
Subagent 1: explore auth module, report findings
Subagent 2: run test suite, report failures
Subagent 3: generate migration script

Main context stays clean. Subagents handle the volume.

Context Budget Planning

Example baseline (calibrate with

/context

Put static context first. CLAUDE.md and tool definitions load before conversation. Keeping them stable maximizes prompt cache hits — saves cost and latency.

When to /clear vs /compact vs Subagent

/compact

/compact

/resume

/clear

/btw

Anti-Patterns

• Loading entire files when you need one function
• Keeping MCP tool results in context after extracting what you need
• Running 15+ MCPs (each adds tool schema overhead to every request)
• Vague prompts that force Claude to search broadly ("fix the code")
• Never compacting until auto-compact triggers at 95%

Add to CLAUDE.md

## Context Engineering

Write to NOTES.md for working state that must survive compaction.
Select with precision — grep first, read specific lines, never dump whole files.
Compact at 50% or task boundaries. Set CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=50.
Isolate heavy work to subagents. Main session stays for coordination and commits.