strategic-compact

Files (2)

• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

# Strategic Compact Skill

Suggests manual `/compact` at strategic points in your workflow rather than relying on arbitrary auto-compaction.

## When to Activate

- Running long sessions that approach context limits (200K+ tokens)
- Working on multi-phase tasks (research → plan → implement → test)
- Switching between unrelated tasks within the same session
- After completing a major milestone and starting new work
- When responses slow down or become less coherent (context pressure)

## Why Strategic Compaction?

Auto-compaction triggers at arbitrary points:
- Often mid-task, losing important context
- No awareness of logical task boundaries
- Can interrupt complex multi-step operations

Strategic compaction at logical boundaries:
- **After exploration, before execution**: Compact research context, keep implementation plan
- **After completing a milestone**: Fresh start for next phase
- **Before major context shifts**: Clear exploration context before different task

## How It Works

The `suggest-compact.sh` script runs on PreToolUse (Edit/Write) and:

1. **Tracks tool calls**: Counts tool invocations in session
2. **Threshold detection**: Suggests at configurable threshold (default: 50 calls)
3. **Periodic reminders**: Once past threshold, reminds again on every absolute multiple of 25 (with the default threshold of 50: 75, 100, 125...; a custom `COMPACT_THRESHOLD=40` still reminds at 50, 75, 100, not at 65, 90)

## Hook Setup

Add to the hook settings of your tool, with the path the skill was installed under (example for Claude Code, `~/.claude/settings.json`):

```json
{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit",
        "hooks": [{ "type": "command", "command": "~/.claude/skills/strategic-compact/suggest-compact.sh" }]
      },
      {
        "matcher": "Write",
        "hooks": [{ "type": "command", "command": "~/.claude/skills/strategic-compact/suggest-compact.sh" }]
      }
    ]
  }
}
```

## Configuration

Environment variables:
- `COMPACT_THRESHOLD`: Tool calls before first suggestion (default: 50)

## Compaction Decision Guide

Use this table to decide when to compact:

| Phase Transition | Compact? | Why |
|-----------------|----------|-----|
| Research → Planning | Yes | Research context is bulky; plan is the distilled output |
| Planning → Implementation | Yes | Plan is in TodoWrite or a file; free up context for code |
| Implementation → Testing | Maybe | Keep if tests reference recent code; compact if switching focus |
| Debugging → Next feature | Yes | Debug traces pollute context for unrelated work |
| Mid-implementation | No | Losing variable names, file paths, and partial state is costly |
| After a failed approach | Yes | Clear the dead-end reasoning before trying a new approach |

## What Survives Compaction

Understanding what persists helps you compact with confidence:

| Persists | Lost |
|----------|------|
| GEMINI.md instructions | Intermediate reasoning and analysis |
| TodoWrite task list | File contents you previously read |
| Memory files (the memory folder of the tool, and the EGC session state) | Multi-step conversation context |
| Git state (commits, branches) | Tool call history and counts |
| Files on disk | Nuanced user preferences stated verbally |

## Best Practices

1. **Compact after planning**: Once plan is finalized in TodoWrite, compact to start fresh
2. **Compact after debugging**: Clear error-resolution context before continuing
3. **Don't compact mid-implementation**: Preserve context for related changes
4. **Read the suggestion**: The hook tells you *when*, you decide *if*
5. **Write before compacting**: Save important context to files or memory before compacting
6. **Use `/compact` with a summary**: Add a custom message: `/compact Focus on implementing auth middleware next`

## Token Optimization Patterns

### Trigger-Table Lazy Loading
Instead of loading full skill content at session start, use a trigger table that maps keywords to skill paths. Skills load only when triggered, reducing baseline context by 50%+:

| Trigger | Skill | Load When |
|---------|-------|-----------|
| "test", "tdd", "coverage" | tdd-workflow | User mentions testing |
| "security", "auth", "xss" | security-review | Security-related work |
| "deploy", "ci/cd" | deployment-patterns | Deployment context |

### Context Composition Awareness
Monitor what's consuming your context window:
- **GEMINI.md files**: Always loaded, keep lean
- **Loaded skills**: Each skill adds 1-5K tokens
- **Conversation history**: Grows with each exchange
- **Tool results**: File reads, search results add bulk

### Duplicate Instruction Detection
Common sources of duplicate context:
- Same rules in both the global `rules/` folder of the tool and the project one
- Skills that repeat GEMINI.md instructions
- Multiple skills covering overlapping domains

### Context Optimization Tools
- `token-optimizer` MCP: Automated 95%+ token reduction via content deduplication
- `context-mode`: Context virtualization (315KB to 5.4KB demonstrated)

From Fmarzochi/EGC, Apache-2.0.

More from Fmarzochi/EGC