prep-compact
Claude Code's auto-compact fires late and its generic summary often drops the files, decisions, and blockers you needed. The post-compact session then veers off course…
Plugin bundle · by koenvdheide
About
prep-compact is a plugin bundle for AI coding tools published by koenvdheide. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-13.
Claude Code's auto-compact fires late and its generic summary often drops the files, decisions, and blockers you needed. The post-compact session then veers off course. prep-compact nudges you earlier: a UserPromptSubmit hook watches your transcript's byte delta since the last compact. When it crosses a configurable threshold (default 4 MB ≈ 450K tokens on Opus 4.7), Claude is prompted to invoke the prep-compact skill, which drafts a tailored /compact <mini-schema> covering goal/next/files/decisions/state. You paste, run /compact, and the post-compact session resumes correctly. Invoke /prep-compact:prep-compact manually any time to refresh the draft before compacting.
What it asks for
- Installs as a plugin bundle
- Hooks: 2
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Claude Code: claude-plugins-community declares.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install prep-compact@claude-communityWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Open the source on GitHub) | Listed | 3.0.3 | Forks (GitHub): 0 Stars (GitHub): 1 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What the bundle contains
As published on Claude Code: claude-plugins-community.
Skills: 1
prep-compact
Hooks: 2
StopUserPromptSubmit
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
-
Save structured session context before /clear and auto-restore it next session. Smart Compact captures what was done, why, decisions made, problems solved, and next steps — so you…
-
prompt-squeeze builds prompt-cost discipline into Claude Code via three surfaces: /squeeze skill that compresses a verbose prompt into a token-efficient equivalent and renders a…
-
Automatically monitors MEMORY.md size and warns Claude to compact it when it exceeds a configurable line threshold. Installs a PostToolUse hook on Write/Edit to memory…
-
Prevent task loss during context compaction. Saves recent user instructions and AI progress before compact, then auto-restores them after compaction via SessionStart stdout…
-
Automatic context window monitoring and smart compaction for Claude Code. Zero dependencies. Context Guardian (cg) watches your context window usage in real time via a statusline…
-
Deterministic org-memory for Claude Code: auto-recall on every prompt (fail-open), re-inject after compaction, loss-proof capture to Gather's curated staging inbox. Nothing enters…
-
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
If you have ever had AI hallucinate and make things up (and gaslight you, even): it's because summaries do not preserve nuance. Each /compact cycle summarises and compresses…
-
Session memory for Claude Code automatically saves checkpoints during work, shows what you were doing upon return, and tracks progress across sessions. It includes 7 slash…
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
Save structured session context before /clear and auto-restore it next session. Smart Compact captures what was done, why, decisions made, problems solved, and next steps — so you…
-
prompt-squeeze builds prompt-cost discipline into Claude Code via three surfaces: /squeeze skill that compresses a verbose prompt into a token-efficient equivalent and renders a…
-
Automatically monitors MEMORY.md size and warns Claude to compact it when it exceeds a configurable line threshold. Installs a PostToolUse hook on Write/Edit to memory…
-
Prevent task loss during context compaction. Saves recent user instructions and AI progress before compact, then auto-restores them after compaction via SessionStart stdout…
-
Automatic context window monitoring and smart compaction for Claude Code. Zero dependencies. Context Guardian (cg) watches your context window usage in real time via a statusline…
Has a listing on Claude Code: claude-plugins-official (5)
-
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects…
-
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
-
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
Has a listing on Claude: knowledge-work-plugins (5)
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
MCP server for terminal commands, file operations, and process management
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
The Dropbox plugin for Claude connects your Dropbox files directly to Claude, so you can search, organize, save generated content, and create sharing links without switching…
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Notion workflows for implementation planning, research synthesis, meeting preparation, and knowledge capture.
-
Install, open, and connect the signed ChatCut Desktop app from Codex.
-
Turn Codex into your ClickUp command center.
-
Use MagicPath to find, inspect, install, create, and edit UI components from Codex.
Has a listing on Community GitHub marketplaces (5)
-
Deterministic org-memory for Claude Code: auto-recall on every prompt (fail-open), re-inject after compaction, loss-proof capture to Gather's curated staging inbox. Nothing enters…
-
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
Connects Claude Code to one Hydrant workspace you approve in the browser, and brings the hydrant skill: read first, write with receipts, read back, say what actually happened.
-
Cut your Claude Code bill, measured on your own sessions. Profile and slim any LLM conversation.
-
Automated context collection: mine your past agent sessions for repeated instructions and corrections, and distill them into CLAUDE.md / AGENTS.md with your approval.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
-
Self-configuring status briefing generator. Learns your communication style from examples, discovers your data sources, and produces draft updates for any audience on demand.
-
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
-
Shows live prompt-cache reuse, expiry, token composition, and AIU cost for the current GitHub Copilot session without making model calls.
-
Turn your Copilot sessions into proof of impact — research-grounded HTML reports with effort estimation, skills analysis, and ROI metrics from local session logs.
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Has a listing on Cursor: cursor/plugins (5)
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Search meeting transcripts, summaries, and action items.
-
Search meetings, transcripts, action items, and emails.
-
Capture, search, and organize notes and collections.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
Has a listing on Docker MCP Catalog (5)
-
MCP server for terminal commands, file operations, and process management
-
Production-ready RAG service to search and retrieve data from your documents.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
A Model Context Protocol server for Omi interaction and automation. This server provides tools to read, search, and manipulate Memories and Conversations.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
Has a listing on Official MCP Registry (5)
-
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
-
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
Cut your Claude Code bill, measured on your own sessions. Profile and slim any LLM conversation.
-
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
-
Claude distils its past sessions into linked Markdown notes on disk and searches them later.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.