Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From brainbrew-devkit
Enables inter-agent communication via Memory Bus using MCP tools like memory_add, memory_list, memory_clear. Targets: global/next/agent:NAME; persistence: session/once/permanent.
npx claudepluginhub brainbrewlabs/brainbrew-devkit --plugin brainbrew-devkitHow this skill is triggered — by the user, by Claude, or both
Slash command
/brainbrew-devkit:memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Use MCP tool `memory_add`:**
Persistent memory for AI agents via hosted MCP. Remember decisions, recall project context, manage TODOs, and govern memory across sessions and tools.
Use when dispatching subagents, composing prompts for teammates, structuring handoff reports, or managing context boundaries between agents. Covers both subagent prompts and team-level messaging.
Guides agents to deliberately search or skip memory using dejavu MCP tools, with query strategies and metadata filters for decisions, user preferences, conventions, and anti-patterns.
Share bugs, ideas, or general feedback.
Use MCP tool memory_add:
mcp__brainbrew__memory_add(
content: "Fix the auth bug in login.ts",
target: "agent:implementer",
persistence: "once"
)
| User says | MCP call |
|---|---|
| "Remember to use TypeScript" | memory_add(content, target: "global", persistence: "permanent") |
| "Tell implementer to fix auth" | memory_add(content, target: "agent:implementer", persistence: "once") |
| "Next agent should check security" | memory_add(content, target: "next", persistence: "once") |
| "For this session, focus on perf" | memory_add(content, target: "global", persistence: "session") |
| "What do you remember?" | memory_list() |
| "Clear memory" | memory_clear() |
| "Forget the TypeScript rule" | memory_clear(...) then re-add without it |
| Target | Who receives |
|---|---|
global | All agents |
next | Next agent only |
agent:NAME | Specific agent (e.g., agent:implementer) |
chain:NAME | All agents in chain |
| Type | Behavior |
|---|---|
session | Default - cleared on exit |
once | Consumed after delivery (queue) |
permanent | Forever (rules, knowledge) |
Use priority: "urgent" for critical messages that should be highlighted.