MCP App StoreMCP App Store
from claudecode-research-harness-workflow18
Unified session management for Claude Code: initialize, resume, persist memory, control state, and broadcast messages across agent sessions.
Consolidates session-related functionality into a single skill that handles initialization, memory persistence, resume/fork control, state management, and cross-session communication for Claude Code workflows. Provides commands like /session list, /session inbox, and /session broadcast to inspect and interact with active sessions.
Use this skill when you need to initialize or resume long-running agent sessions, persist learnings across runs, fork or resume work units, or broadcast messages to multiple active sessions. It's intended for developer/research workflows (Claude Code) rather than application user authentication or login flows.
Likely compatible with Claude Code and other Claude-based harnesses; tooling references imply integration with Claude Code resume/restore features and the research harness environment.
This skill has not been reviewed by our automated audit pipeline yet.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Terragrunt Infrastructure
Best-practice patterns and operational guidance for Terragrunt/OpenTofu infrastructure: catalog/live/module layout, state backend setup, and deployment workflow
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Agent Browser — Core
Core usage guide for agent-browser: snapshot-and-ref browser automation to navigate pages, interact with elements, extract data, take screenshots, manage sessio
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.