Skill790 repo starsupdated 12d ago
strategic-compact
Strategic-compact is a Claude Code skill that suggests using the `/compact` command at intentional workflow boundaries rather than relying on automatic context compaction. It tracks tool usage and prompts manual compaction after reaching a configurable threshold of tool calls, typically after completing major phases like research or debugging, to preserve relevant context while clearing less useful information before major task shifts.
Install in Claude Code
Copygit clone --depth 1 https://github.com/sangrokjung/claude-forge /tmp/strategic-compact && cp -r /tmp/strategic-compact/skills/strategic-compact ~/.claude/skills/strategic-compactThen start a new Claude Code session; the skill loads automatically.
Definition
SKILL.md
# Strategic Compact Skill
Suggests manual `/compact` at strategic points in your workflow rather than relying on arbitrary auto-compaction.
## 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** - Reminds every 25 calls after threshold
## Hook Setup
Add to your `~/.claude/settings.json`:
```json
{
"hooks": {
"PreToolUse": [{
"matcher": "tool == \"Edit\" || tool == \"Write\"",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/strategic-compact/suggest-compact.sh"
}]
}]
}
}
```
## Configuration
Environment variables:
- `COMPACT_THRESHOLD` - Tool calls before first suggestion (default: 50)
## Best Practices
1. **Compact after planning** - Once plan is finalized, 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*
## Related
- [The Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - Token optimization section
- Memory persistence hooks - For state that survives compactionMore from this repository
architectSubagent
|
build-error-resolverSubagent
|
code-reviewerSubagent
|
database-reviewerSubagent
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
doc-updaterSubagent
|
e2e-runnerSubagent
|
plannerSubagent
|
refactor-cleanerSubagent
|