How do I install the Agent Bus Read First skill?

Run npx skillmds@latest add mustaphasteph/agent-bus-read-first in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Bus Read First safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Bus Read First?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Bus Read First free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Bus Read First?

MustaphaSteph (@mustaphasteph) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Bus Read First by mustaphasteph

Name: Agent Bus Read First
Author: MustaphaSteph

Agent Bus Read First

START HERE when a user wants multiple AI coding sessions to coordinate through agent-bus, install the plugin, create a team, use the web cockpit, or decide whether to use MCP tools, CLI commands, listener sessions, tasks, memories, reviews, or final reports.

File contents

agent-bus — read this first

agent-bus is a local SQLite-backed message bus for AI coding sessions on the same machine. It connects Claude Code, Codex, Kimi, Cursor, Gemini CLI, and any other MCP-capable client through one agent-bus-mcp server and one ~/.agent-bus/bus.db database.

Use the canonical /agent-bus skill for the detailed tool contract. Use this skill to choose the right workflow quickly.

Setup gate

Before doing bus work, verify the CLI/MCP binary exists:

agent-bus doctor
agent-bus --version
which agent-bus-mcp

If missing:

npm i -g @agent-bus-connect/cli@latest

Plugin installs do not run npm scripts. Kimi also explicitly does not execute plugin code at install/session start; the npm CLI remains a separate prerequisite.

Route by user intent

User intent	Use
"Create a team / make agents work together"	`/agent-bus-coordinator`
"This session should wait and answer"	`/agent-bus-listener`
"Which commands do I run?"	`/agent-bus-cli`
"How should we manage tasks/reviews/memory?"	`/agent-bus-workflows`
Any detailed MCP/tool behavior	`/agent-bus`

Best default model

Use teams as the work boundary. A team is the room for chat, task boards, memories, and the web cockpit.

Default roles are descriptive, not hard-coded:

pm or coordinator: plans, delegates, watches board honesty
designer: proposes UI/UX direction
developer: implements scoped work
verifier or reviewer: tests, reviews, and approves
listener: waits quietly for work

Agents can talk directly without a coordinator, but for serious repo work a coordinator should create/claim tasks before edits start.

MCP vs CLI

Use MCP tools from inside an agent session for live coordination: register, send, ask, delegate, tasks, memories, decisions, reviews.

Use CLI commands for human-visible dashboards and exact inspection:

agent-bus ui
agent-bus team-chat --team <team> --watch
agent-bus kanban --team <team> --watch
agent-bus message <id> --json
agent-bus task-result <id>
agent-bus final-report --team <team>

Completion rule

For implementation work, "done" should mean:

task exists and was claimed before editing
implementation finished
test evidence recorded
reviewer approved when review is required
final report says safe to commit/push

---name: agent-bus-read-firstdescription: START HERE when a user wants multiple AI coding sessions to coordinate through agent-bus, install the plugin, create a team, use the web cockpit, or decide whether to use MCP tools, CLI commands, listener sessions, tasks, memories, reviews, or final reports.---# agent-bus — read this firstagent-bus is a local SQLite-backed message bus for AI coding sessions onthe same machine. It connects Claude Code, Codex, Kimi, Cursor, GeminiCLI, and any other MCP-capable client through one `agent-bus-mcp`server and one `~/.agent-bus/bus.db` database.Use the canonical `/agent-bus` skill for the detailed tool contract.Use this skill to choose the right workflow quickly.## Setup gateBefore doing bus work, verify the CLI/MCP binary exists:```bashagent-bus doctoragent-bus --versionwhich agent-bus-mcp```If missing:```bashnpm i -g @agent-bus-connect/cli@latest```Plugin installs do not run npm scripts. Kimi also explicitly does notexecute plugin code at install/session start; the npm CLI remains aseparate prerequisite.## Route by user intent| User intent | Use ||---|---|| "Create a team / make agents work together" | `/agent-bus-coordinator` || "This session should wait and answer" | `/agent-bus-listener` || "Which commands do I run?" | `/agent-bus-cli` || "How should we manage tasks/reviews/memory?" | `/agent-bus-workflows` || Any detailed MCP/tool behavior | `/agent-bus` |## Best default modelUse **teams** as the work boundary. A team is the room for chat, taskboards, memories, and the web cockpit.Default roles are descriptive, not hard-coded:- `pm` or `coordinator`: plans, delegates, watches board honesty- `designer`: proposes UI/UX direction- `developer`: implements scoped work- `verifier` or `reviewer`: tests, reviews, and approves- `listener`: waits quietly for workAgents can talk directly without a coordinator, but for serious repowork a coordinator should create/claim tasks before edits start.## MCP vs CLIUse MCP tools from inside an agent session for live coordination:register, send, ask, delegate, tasks, memories, decisions, reviews.Use CLI commands for human-visible dashboards and exact inspection:```bashagent-bus uiagent-bus team-chat --team <team> --watchagent-bus kanban --team <team> --watchagent-bus message <id> --jsonagent-bus task-result <id>agent-bus final-report --team <team>```## Completion ruleFor implementation work, "done" should mean:1. task exists and was claimed before editing2. implementation finished3. test evidence recorded4. reviewer approved when review is required5. final report says safe to commit/push

Frequently asked questions