commands
Lists mirrored command entries from the archived snapshot.
Arguments
Maximum number of entries to display.
Search string. When provided, the command calls
render_command_index() which performs a fuzzy match and returns a ranked Markdown index instead of the plain list.Exclude plugin-sourced commands from the listing.
Exclude skill-sourced commands from the listing.
Output format
Without--query:
--query:
tools
Lists mirrored tool entries from the archived snapshot.
Arguments
Maximum number of entries to display.
Search string. When provided, calls
render_tool_index() for a ranked Markdown result.Load the tool inventory in simple mode (reduced tool set, no advanced tool variants).
Exclude MCP-sourced tools from the listing.
Deny a specific tool by exact name. Can be repeated to deny multiple tools.
Deny all tools whose names start with a given prefix. Can be repeated.
Output format
Without--query:
show-command
Shows one mirrored command entry by exact name.
Arguments
Exact name of the command to look up (e.g.
/config).Output format
1 if the name is not found.
show-tool
Shows one mirrored tool entry by exact name.
Arguments
Exact name of the tool to look up (e.g.
Bash).Output format
1 if the name is not found.
exec-command
Executes a mirrored command shim by exact name.
Arguments
Exact name of the command to execute.
The prompt string to pass to the command shim’s
execute() method.Output format
Prints themessage field from the ExecutionResult. Returns exit code 0 when the command reports handled=True, or 1 otherwise.
exec-tool
Executes a mirrored tool shim by exact name.
Arguments
Exact name of the tool to execute.
A string payload passed to the tool shim’s
execute() method. For tools that expect structured input, pass a JSON string.Output format
Prints themessage field from the ExecutionResult. Returns exit code 0 when handled=True, or 1 otherwise.
route
Routes a prompt across the full command and tool inventories and returns ranked matches.
Arguments
Free-text prompt to route. The router tokenises the prompt, scores each command and tool by counting token matches against the entry’s name, source hint, and responsibility fields, then returns the top matches.
Maximum number of matches to return. The router always tries to include at least one command match and one tool match before filling remaining slots with the highest-scoring leftovers.
Output format
Each line is tab-separated:route is the same scoring logic used internally by bootstrap and turn-loop. Running it directly lets you inspect and tune the routing behaviour without triggering a full runtime session.