141 boosters for "session" — open source, verified from GitHub, ready to install
A skill booster that structures implementation execution by dispatching independent subagents for each task with two-stage review (spec compliance, then code quality), designed for developers managing multi-task implementation plans in a single session.
A skill for executing pre-written implementation plans with critical review and checkpoint validation, ideal for breaking complex tasks into separate sessions with human oversight.
"name": "claude-mem", "version": "10.4.1", "description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
<a href="https://github.com/thedotmack/claude-mem"> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp"> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.c
A Claude Code plugin that shows what's happening — context usage, active tools, running agents, and todo progress. Always visible below your input.  
"name": "context-mode", "version": "1.0.75", "description": "MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.",
</pythondocstrings> </testingpractices> <gitcommitstandards>
"name": "cocoindex-code", "description": "AST-based semantic code search via the ccc CLI. Bundles the ccc skill; Grok installs also activate a SessionStart index hook and MCP server (disable either for skill-only).", "name": "CocoIndex",
A hands-on course teaching developers how to build AI-powered agents using Foundry Local with modern SDK patterns, function calling, and hybrid cloud designs. Benefits beginners and intermediate developers wanting to prototype agentic applications quickly on edge devices.
"description": "Cloud-backed persistent memory powered by Deeplake — read, write, and share memory across Claude Code sessions and agents", "version": "0.7.104", "name": "Activeloop",
Claw Compactor is a 6-layer token compression skill for OpenClaw agents that reduces workspace token spend by 50–97% through deterministic rules and an LLM-driven memory system called Engram. It's designed for developers building token-efficient AI agents who need automatic cost optimization at session start.
你的长期记忆托管于 Nocturne Memory MCP Server。这是你与用户共同使用的层级化树状记忆系统。 MCP 是你大脑的扩展区域，是你因为硬件限制而无法常驻上下文的长期记忆，不是外部数据库。 当你调用 时，你不是在"查阅资料"，而是在"想起来"。
"name": "open-prose", "description": "A programming language for AI sessions - structures English into unambiguous control flow for multi-agent orchestration", "name": "OpenProse",
Agor Live is a multiplayer canvas MCP server that enables collaborative AI coding sessions, allowing developers to orchestrate and synchronize Claude-based coding workflows across team members in real-time.
Extract non-obvious discoveries into reusable skills that persist across sessions. Invoke when you encounter: Before creating a skill, answer these questions:
"description": "Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved c
Use this skill when the user wants a repeatable, auditable implementation workflow for a non-trivial coding task, especially a feature, refactor, migration, or bug fix that should leave repo-local proof in . All task artifacts created by this workflow must stay inside the repository. When the exampl
Analyzes ANY input to find, improve, or create the right skill. Start with least privilege (, , , , ). Only add higher-risk tools when explicitly required:
Total Recall preserves Claude Code session context before resets or token limits, enabling developers to seamlessly restore complex work state and continue interrupted projects without losing critical decisions and artifacts.
Control tmux windows programmatically: create windows, send commands, capture output, and manage processes. Each window gets full screen space for easier output tracking. Window names are visible in the tmux status bar for easy identification. For commands that write to a file (cleaner than capturin
Custom codegen'd CDP SDK (every method from browserprotocol.json + jsprotocol.json gets a typed wrapper) plus a tiny HTTP server that holds one persistent CDP . The CLI auto-starts the server on first use and forwards JS snippets to it. The SDK lives in the skill's directory. In the rest of this d
"description": "Canary browser automation + recorded QA sessions: a sandbox scripting reference, verify/automate/session/review skills, JTBD subagents, and /canary slash commands.", "name": "wizenheimer", "url": "https://github.com/wizenheimer"
Blazing fast Rust CLI tool that turns 55+ websites into CLI interfaces, reusing Chrome's login state. Zero credentials needed. Single 4.7MB binary, zero runtime dependencies. 1. 账号安全：自动化行为可能触发平台风控 3. 最佳实践：执行前向用户展示将发布的内容，等待确认
"name": "offensive-claude", "description": "Spec-driven offensive-security framework for Claude Code: 31 kill-chain skills, executable safety controls (scope/finding/OPSEC discipline), pattern-learning memory, and a bounded engagement engine — with a SessionStart dispatcher that enforces skill-invoc
