Tools

Every agent has the same base kit, five finance tools, and BytNode. Exchange tools come with the accounts you attach.

The base kit

ReadReads text, images, PDFs and notebooks.
Write, Edit, NotebookEditCreates and changes files. Edit replaces one exact string.
Glob, GrepFinds files by name, searches their content (ripgrep, embedded).
Bash, PowerShellRuns a command in the working folder, bounded in time.
MonitorWatches a command or a WebSocket for a while, and reports.
WebSearch, WebFetchSearches the web; fetches a page as Markdown.
WorkflowDelegates tasks to sub-agents, each with a profession.
SkillOpens one of your skills and follows it.

Finance

SaveMarketDataOne BytNode tool call written straight to a CSV in the working folder, without pushing the rows through the model.
ChartA PNG from a CSV: candles or line, volume, overlaid columns, markers, levels. The agent sees the image; so do you, in the thread.
BacktestOne standard engine in Python: next-candle execution, fees, slippage, funding, position sizing by risk, in and out of sample, metrics per period. The agent only writes signal(df) and stop_distance(df).
MemoryDated notes in the working folder; the last 25 are slipped into every prompt.
TodoWriteThe agent’s own task list on a long request, shown in the thread.

Sub-agents

Workflow splits a long request into tasks. Each task names a profession and a model; sub-agents run three at a time, eight at most, with the profession’s skills and every tool but Workflow and the exchange actions. They ask no permission, and each returns a report signed by its profession, merged into the answer.

Permissions

In Ask before acting mode, Bash, PowerShell, Monitor, Write, Edit, NotebookEdit, Backtest and Workflow wait for your answer in the thread: Autoriser, Toujours pour cet agent (a rule for that tool or that command prefix), or Refuser. An irreversible command, a recursive delete or a force push for instance, never gets a Toujours. Exchange orders, closes and transfers always ask, in every mode.

Context, handled for you

Every tool call is checked against its schema before it runs; a malformed call goes back to the model with the reason. Past 70 % of the model’s window, old tool results are pruned from what the model receives (the thread you see keeps everything); at 90 % the thread is compacted; if the provider refuses the context, it is compacted and your message replayed.