compact-guardian
Prevent task loss during context compaction. Saves recent user instructions and AI progress before compact, then auto-restores them after compaction via SessionStart stdout…
Пакет плагинов · от ibarapascal
Коротко
compact-guardian: пакет плагинов для ИИ-инструментов разработки, издатель ibarapascal. Витрин, которые мы читаем и где он опубликован: 1 (Claude Code: claude-plugins-community). Мы впервые увидели его 2026-10-11 и с тех пор изменений не фиксировали. Данные нашего прохода по витринам на 2026-10-14.
Prevent task loss during context compaction. Saves recent user instructions and AI progress before compact, then auto-restores them after compaction via SessionStart stdout injection.
Что просит
- Ставится как пакет плагинов
- Хуков: 2
Что объявляет, просит и запускает, полностью
Устанавливайте плагины только от разработчиков, которым доверяете. Мы показываем то, что публикуют витрины, и не проверяем плагины.
Работает с
- Claude Code
По маркетплейсам, где он опубликован, и объявленному транспорту MCP, как их документирует каждый клиент. Плагины мы не тестируем.
Подключить
Команды и конфигурации собраны только из того, что объявляют витрины. Мы не запускаем их за вас и не проверяем плагины.
Как плагин Claude Code
Собрано из того, что объявляет Claude Code: claude-plugins-community.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install compact-guardian@claude-communityГде опубликован
| Витрина | Статус | Версия | Числа | Проверен | Впервые замечен |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Открыть исходники на GitHub) | Опубликован | 0.1.3 | Форки (GitHub): 0 Звёзды (GitHub): 0 |
Не помечен |
Каждое число принадлежит своей витрине и никогда не складывается с числами других витрин. Если витрина число не публикует, мы его не показываем: нет числа не значит ноль.
Что входит в пакет
Так опубликовано на витрине Claude Code: claude-plugins-community.
Хуки: 2
PreCompactSessionStart
Что менялось
С тех пор как мы следим за плагином, ничего не менялось.
Похожие плагины
Продукты, чьи собственные названия, описания, инструменты и скиллы ближе всего по смыслу к этому, на всех витринах, которые мы читаем. Близость упорядочена только внутри этого списка.
-
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…
-
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…
-
Prevent context window exhaustion. Real-time token tracking, semantic compact scoring, and carry-forward memory that fixes cumulative amnesia across `/compact` cycles.
-
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…
-
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
Eliminate context rot in Claude Code with intelligent memory hierarchy, auto-learning hooks, and specialized subagents. Uses an 8-layer memory architecture with SessionStart/End…
-
Preserves important architectural decisions and user requests that get lost during compaction and long sessions. Automatically extracts structured session memory (goals…
-
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
-
Persistent memory with session tracking, compaction recovery, and a save protocol. Gives the agent a memory that survives across sessions.
-
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…
Похожие плагины по витринам
Тот же вопрос к каждой витрине по отдельности: есть ли там аналог этого плагина?
Есть на витрине 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…
-
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…
-
Prevent context window exhaustion. Real-time token tracking, semantic compact scoring, and carry-forward memory that fixes cumulative amnesia across `/compact` cycles.
-
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…
-
Eliminate context rot in Claude Code with intelligent memory hierarchy, auto-learning hooks, and specialized subagents. Uses an 8-layer memory architecture with SessionStart/End…
Есть на витрине Claude Code: claude-plugins-official (5)
-
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Official Convex plugin for Claude Code with bundled Convex skills, the convex-expert subagent for code-writing, a runtime-error monitor, and MCP access for backend development…
-
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin…
Есть на витрине Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to…
-
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.
-
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…
Есть на витрине Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Install, open, and connect the signed ChatCut Desktop app from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
Есть на витрине Community GitHub marketplaces (5)
-
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
Persistent memory with session tracking, compaction recovery, and a save protocol. Gives the agent a memory that survives across sessions.
-
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…
-
Persistent memory for ZCode: session tracking, compaction recovery, and a save protocol. Registers the three lifecycle events this client fires.
-
UltraMemory Agent Kit (Tier 3) — Turbo Token Saver (recall-first hook + client cache) + the harness (grounding / checklist-bound execution skills, subagents, Stop gate) + optional…
Есть на витрине Copilot CLI: github/awesome-copilot (5)
-
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…
-
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…
-
Maps branching Copilot conversations so parallel follow-up questions and exploration paths from complex tasks or learning can be navigated without losing context. Its visual…
-
Premium planning, thrifty implementation
-
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
Есть на витрине Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Есть на витрине Cursor: cursor/plugins (5)
-
Capture, search, and organize notes and collections.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Scaffold and validate new agent plugins.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
Есть на витрине Docker MCP Catalog (5)
-
MCP server for terminal commands, file operations, and process management
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
-
Production-ready RAG service to search and retrieve data from your documents.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
Есть на витрине Official MCP Registry (5)
-
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
-
memharness io.github.las7/memharness
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
-
ctxl ai.autoblocks/ctxl
Personal context management for AI assistants
-
Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.
Найдено по смыслу, а не по общему коду или репозиторию: похожие плагины остаются разными продуктами, и это не обзор и не рекомендация.
Это ваш плагин?
Добавьте плагин в свои проекты и докажите, что поддерживаете его: файлом в репозитории, файлом на вашем домене или DNS-записью. Вы будете получать уведомления, когда витрина добавит плагин, снимет его, изменит отметку verified или список того, что он просит, а его удалённый endpoint встанет на мониторинг как веб-сервис.
Данные витрины Claude Code: claude-plugins-community. Числа взяты из наших регулярных обходов витрин, последняя проверка . Контакты издателей плагинов мы не публикуем.