strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Skill by vibeeval
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vibeeval-strategic-compact
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
strategic-compact- Description
- Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
- License
- MIT
- Instructions
- 60 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- suggest-compact.sh
SKILL.md (first lines)
---
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 compactionFrom vibeeval/vibecosystem, MIT.
More from vibeeval/vibecosystem
- 0.565score
codex-orchestration
vibeeval
OpenAI Codex CLI + Claude Code (Hizir) birlikte kullanim rehberi.
SkillBFreshness: B★ 540Claude Code +9 - 0.562score
plan-agent
vibeeval
Planning agent that creates implementation plans and handoffs from conversation context
SkillBFreshness: B★ 540Claude Code +9 - 0.559score
help
vibeeval
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
SkillBFreshness: B★ 540Claude Code +9 - 0.559score
explore
vibeeval
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
SkillBFreshness: B★ 540Claude Code +9 - 0.559score
cli-reference
vibeeval
Claude Code CLI commands, flags, headless mode, and automation patterns
SkillBFreshness: B★ 540Claude Code +9 - 0.524score
tdd-workflow
vibeeval
Use this skill when writing new features, fixing bugs, or refactoring code.
SkillCFreshness: C★ 540Claude Code +9 - 0.522score
kotlin-patterns
vibeeval
Coroutine patterns, Flow operators, Jetpack Compose state management, Ktor routing, and Kotlin Multiplatform shared code.
SkillCFreshness: C★ 540Claude Code +9 - 0.522score
compliance-patterns
vibeeval
GDPR data handling, audit logging, data classification, retention policies, and consent management for regulatory compliance.
SkillCFreshness: C★ 540Claude Code +9 - 0.522score
feature-flag-patterns
vibeeval
Gradual rollout strategies, kill switches, A/B testing integration, flag lifecycle management, and technical debt prevention.
SkillCFreshness: C★ 540Claude Code +9 - 0.522score
aws-patterns
vibeeval
Lambda best practices, S3 event patterns, SQS/SNS fanout, and DynamoDB access patterns for serverless AWS architectures.
SkillCFreshness: C★ 540Claude Code +9 - 0.522score
experiment-engine
vibeeval
Otonom deney dongusu.
SkillCFreshness: C★ 540Claude Code +9 - 0.522score
grpc-patterns
vibeeval
Protobuf schema design, streaming patterns, interceptor chains, deadline propagation, and error handling for gRPC services.
SkillCFreshness: C★ 540Claude Code +9
Signals
- Stars
- 540
- Forks
- 44
- Open issues
- 5
- Last commit (this folder)
- Mar 23, 2026 (7 months ago)
- Last release
- Apr 12, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/vibeeval/vibecosystem
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.767score
strategic-compact
sangrokjung
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillBFreshness: B★ 863Claude Code +9 - 0.400score
strategic-compact
GGGODLIN
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillAFreshness: A★ 72Claude Code +9 - 0.399score
strategic-compact
Fmarzochi
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillAFreshness: A★ 67Claude Code +9 - 0.347score
strategic-compact
mturac
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillCFreshness: C★ 83Claude Code +9 - 0.344score
strategic-compact
ysyecust
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillCFreshness: C★ 59Claude Code +9 - 0.299score
strategic-compact
marshall0524
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 41Claude Code +9 - 0.294score
strategic-compact
Luohaothu
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 26Claude Code +9 - 0.281score
strategic-compact
Infopibe
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 8Claude Code +9 - 0.257score
strategic-compact
ashutoshrathi0909-oss
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 1Claude Code +9 - 0.244score
strategic-compact
sumitkashyape2
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: DClaude Code +9 - 0.241score
strategic-compact
bh679
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: DClaude Code +9
More from vibeeval
- 0.565score
codex-orchestration
vibeeval
OpenAI Codex CLI + Claude Code (Hizir) birlikte kullanim rehberi.
SkillBFreshness: B★ 540Claude Code +9 - 0.562score
plan-agent
vibeeval
Planning agent that creates implementation plans and handoffs from conversation context
SkillBFreshness: B★ 540Claude Code +9 - 0.559score
help
vibeeval
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
SkillBFreshness: B★ 540Claude Code +9 - 0.559score
cli-reference
vibeeval
Claude Code CLI commands, flags, headless mode, and automation patterns
SkillBFreshness: B★ 540Claude Code +9 - 0.559score
explore
vibeeval
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
SkillBFreshness: B★ 540Claude Code +9 - 0.524score
tdd-workflow
vibeeval
Use this skill when writing new features, fixing bugs, or refactoring code.
SkillCFreshness: C★ 540Claude Code +9
Cite this page
strategic-compact skill. Agent Mart. https://agentmart.dev/skills/vibeeval-strategic-compact (last updated 2026-10-24)