Install
$ agentstack add skill-mustaphasteph-agent-bus-plugins-agent-bus-read-first ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
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:
pmorcoordinator: plans, delegates, watches board honestydesigner: proposes UI/UX directiondeveloper: implements scoped workverifierorreviewer: tests, reviews, and approveslistener: 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 --watch
agent-bus kanban --team --watch
agent-bus message --json
agent-bus task-result
agent-bus final-report --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
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: MustaphaSteph
- Source: MustaphaSteph/agent-bus-plugins
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.