This skill provides comprehensive guidance for inter-agent communication using the Synapse A2A framework. Use this skill when sending messages to other agents, routing @agent patterns, understanding priority levels, handling A2A protocol operations, managing task history, configuring settings, or using File Safety features for multi-agent coordination. Automatically triggered when agent communication, A2A protocol tasks, history operations, or file safety operations are detected.
Coordinates multi-agent workflows using @agent routing and A2A protocol operations.
/plugin marketplace add s-hiraoku/synapse-a2a/plugin install synapse-a2a@synapse-a2aThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/api.mdreferences/commands.mdreferences/examples.mdreferences/file-safety.mdInter-agent communication framework via Google A2A Protocol.
| Task | Command |
|---|---|
| List agents | synapse list |
| Watch agents | synapse list --watch |
| Send message | @<agent> <message> or python3 synapse/tools/a2a.py send --target <agent> "<message>" |
| Check file locks | synapse file-safety locks |
| View history | synapse history list |
| Initialize settings | synapse init |
Send messages to other agents using the @agent pattern:
@codex Please refactor this file
@gemini Research this API
@claude-8100 Review this code
Target Resolution:
@synapse-claude-8100@claude-8100@claude (if single instance)| Priority | Description | Use Case |
|---|---|---|
| 1 | Normal | Default for standard tasks |
| 2-3 | Elevated | Higher urgency |
| 4 | Urgent | Follow-ups, status checks |
| 5 | Interrupt | Emergency (sends SIGINT first) |
# Emergency interrupt
python3 synapse/tools/a2a.py send --target codex --priority 5 "STOP"
| Status | Meaning |
|---|---|
| READY | Idle, waiting for input |
| PROCESSING | Busy handling a task |
Always verify target agent is READY before sending tasks.
synapse history)synapse file-safety)settings.json (synapse init)For detailed documentation, read:
references/commands.md - Full CLI command referencereferences/file-safety.md - File Safety detailed guidereferences/api.md - A2A endpoints and message formatreferences/examples.md - Multi-agent workflow examplesThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.