The agent

Kotoba runs one agentic loop. It runs in one of two modes, and the mode decides three things: which tools she is offered, how many times she may call them…

One turn is one call into the agentic loop. Inside it the loop iterates: ask the model, run whatever tools it called, feed the results back, ask again. It…

40 tools across 13 toolsets. Enumerated from the live registry.

Seven tools in the core toolset. They are the ones that talk to you rather than to a machine: starting and stopping a job, asking a question, putting a card…

Two tools, and they are not interchangeable. One asks the provider a question; the other fetches one URL you already have.

Five tools in the memory toolset, and three separate stores behind them. All three live on your disk as files or rows you can open, edit and delete.

Four tools in the file toolset: read_file, write_file, patch, search_files.

Two tools, two toolsets, one gate: shell (terminal) and execute_code (code). These are the only two tools routed through the ApprovalGate. (Four others put a…

One tool, cronjob, in the cron toolset. It creates, lists, cancels and skips reminders.

One tool, make_report, in the report toolset.

One tool, delegate, in the subagent toolset. Work mode only.

Three tools in the browser toolset: ask_secret, request_credential, get_credential. Work mode only. The first two block waiting for you to type, which a voice…

A skill is a Markdown file. Not code, not a plugin — a document she reads when the job matches it.

Three tools in the mcp toolset — mcp_install, mcp_find, activate_tools — plus everything a connected server exposes. All work mode only.

Nine tools in the discord toolset. Every one of them answers its availability check with the same question — "is the Discord runtime live" — and that flag is…