md-composer

Persistent memory across Cowork sessions — automatically recalls past decisions, file changes, insights, and errors so you never lose context between sessions. SQLite + FTS5, token-efficient 3-layer retrieval.

7 skills · hooks

Prospect, enrich leads, and load outreach sequences with Apollo.io — one-click MCP server integration with skills for enrichment, prospecting, and sequence loading

3 skills · 3 agents · 1 MCP server

Long-term memory for Claude across sessions via Notion — plus the 4 official Anthropic Notion skills (knowledge-capture, meeting-intelligence, research-documentation, spec-to-implementation) bundled in

5 skills

Connect Claude to WhatsApp — search messages, read conversations, send texts and media, manage business outreach with persistent conversation memory

2 skills · 2 agents · 1 MCP server

Token-efficient LinkedIn data access — scrape profiles, companies, and jobs via structured MCP, 5-10x cheaper than browser-based approaches

3 skills · 1 agent

MSApps OpsAgents Shopify plugin — full Admin API + Storefront MCP tools (products CRUD, files, orders, customers, themes, metafields), go-to-market guidance, and @opsagents/shopify-sdk typed contracts.

3 skills · 1 MCP server

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server