strategic-compact
immacualate/claude-forge/skills/strategic-compact/SKILL.md
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Skill5 starsChanged 7 months ago
What's in it
- Strategic Compact Skill
- Why Strategic Compaction?
- How It Works
- Hook Setup
- Configuration
- Best Practices
- Related
---
name: strategic-compact
description: Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
---
# 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 compaction
More agent context in immacualate/claude-forge
14 other files this repository gives its agents.
Skill
- build-systemskills/build-system/SKILL.md
- cache-componentsskills/cache-components/SKILL.md
- cc-dev-agentskills/cc-dev-agent/SKILL.md
- continuous-learning-v2skills/continuous-learning-v2/SKILL.md
- eval-harnessskills/eval-harness/SKILL.md
- frontend-code-reviewskills/frontend-code-review/SKILL.md
- manage-skillsskills/manage-skills/SKILL.md
- prompts-chatskills/prompts-chat/SKILL.md
- security-pipelineskills/security-pipeline/SKILL.md
- session-wrapskills/session-wrap/SKILL.md
- skill-factoryskills/skill-factory/SKILL.md
- team-orchestratorskills/team-orchestrator/SKILL.md
- verification-engineskills/verification-engine/SKILL.md
- verify-implementationskills/verify-implementation/SKILL.md
Also found in 4 other repositories
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

