whereismyai
Compactly
Compactly is a Claude Code plugin that compacts sessions at task boundaries and displays costs and prompt cache status.
Compactly is a Claude Code plugin that reduces context window overhead by compacting sessions at natural task boundaries instead of mid-task. It writes a handoff summary for the next task and provides a cost and cache panel that tracks turn costs, cache hit rates, token usage, and cache time-to-live. The plugin features an automatic mode using a judge model, a suggest mode for compaction timing notifications, and a feedback system that learns from user ratings on automatic compactions. It targets developers using Claude Code who want to reduce redundant context re-reads and manage token expenses. Supported configurations include multiple judge models and customizable settings for token thresholds and panel displays.
Compactly at a glance
Key features
- Compacts sessions at natural task boundaries
- Generates handoff summaries for subsequent tasks
- Displays cost and cache status in a panel
- Learns from user feedback on automatic compactions
- Offers auto, suggest, and off operational modes
- Tracks session costs and token usage
- Shows cache expiration clocks and hit rates
Use it for
- Reducing repeated token costs in long Claude Code sessions
- Summarizing completed work for the next task
- Monitoring prompt cache expiration and token windows
- Tracking cumulative savings from session compactions
Companions
Tools that articles about Compactly recommend using with it, each with its job.
- Claude Code — Built to work with Claude Code.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Playwright MCP — Enables LLMs to interact with web pages using structured accessibility snapshots.
- GitHub MCP Server — Reads pull requests, issues and code search on GitHub.
- Superpowers — Brainstorm, plan and execute skills for bigger tasks.
- gstack — Skill bundle for planning, review and shipping.
Alternatives to Compactly
- Fast Jev Compaction — It keeps tool calls and results verbatim using Jev decisions instead of summaries.
- Effortless — It selects the reasoning effort for every prompt and lowers costs.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Lcc — Cuts token counts significantly without losing exact session details.
- Catnap — It prevents mid-task interruptions by letting Claude finish its current piece of work before compacting.
- Auto Handoff — Saves cache costs by writing a handoff file before idle sessions expire.
- Claude Code Session Tracker — Monitor Claude Code usage limits and token history in a single local interface.
- ccusage — Tracks token usage and costs locally across multiple coding agent CLIs.
- Claude Context — It reduces token costs and provides deep context for large codebases.
- Cost X-Ray — It prices usage below the tool level by analyzing raw API request bytes.
- Edgee Mod for Claude Code — Manage models and track token cost savings inside your terminal conversation.
- Opaline — Track team-wide token costs and coding session analytics.
All Compactly alternatives