Documentation
¶
Overview ¶
Package agentassets holds lockssh's agent texts (skill, instructions, Cursor rule, example config) and their wiring through lockkit's agentwire.
Index ¶
Constants ¶
This section is empty.
Variables ¶
View Source
var ( //go:embed skill.md Skill []byte //go:embed agents.md Instructions []byte //go:embed cursor-rule.mdc CursorFrontMatter []byte //go:embed config.toml ProjectConfig []byte )
View Source
var Wiring = agentwire.Wiring{Product: product.P, Assets: agentwire.Assets{ MCPCommand: []string{"lockssh", "mcp"}, Skill: Skill, Instructions: Instructions, CursorFrontMatter: CursorFrontMatter, ProjectConfig: ProjectConfig, ClaudeAllow: []string{"mcp__lockssh__lockssh_status", "Bash(lockssh status:*)", "Bash(lockssh doctor:*)"}, ClaudeNote: "lockssh_run asks Claude Code each time: its allow-listed commands run on the host at once; other commands are decided on lockhub (lox approve, the lea deck or a paired phone).", }}
Wiring wires the agents to lockssh. Claude Code may call, without a prompt, only the status: lockssh_run runs a command on the host.
Functions ¶
This section is empty.
Types ¶
This section is empty.
Click to show internal directories.
Click to hide internal directories.