Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.simplefunctions.dev/llms.txt

Use this file to discover all available pages before exploring further.

The SF CLI is designed to be driven by an LLM. The recommended loop, the tool classifications, and the JSON contract all assume an agent — not a human — is the primary caller.
1

Discover tools

sf describe --all --json returns every command with its safety class and JSON shape.
2

Pull world state

sf world --json for fresh global context, or sf world --delta --json --since 1h for a long-running agent.
3

Query or inspect

sf query for natural-language search, sf inspect <ticker> for a structured market dossier.
4

Pull account context

sf me --json --detail if authenticated.
5

Decide

Monitor, create an intent, place an order, or wait.
sf describe --all --json
sf world --json
sf query "Fed rate cut" --json --limit 3
sf inspect KXRATECUT-26DEC31 --json
sf portfolio history --json --ticks 10 --trades 10 --since 2026-04-23

​
Long-running agents

Use deltas instead of full snapshots so the context window stays small: 
sf world --delta --json --since 1h
Use bounded account reads: 
sf me --json --detail --limit 10
sf feed --json --hours 6
sf portfolio history --json --ticks 0 --trades 50 --status open

​
Safety classes

Agents should treat commands as:
ClassMeaning
safe_readPublic read-only. No auth required. Always safe to call.
account_readAuthenticated read-only. Returns user-scoped data. Safe to call.
server_writeMutates SimpleFunctions server state (creates intents, theses, alerts). Reversible.
local_runtimeStarts/stops a local process (e.g. sf agent). Side-effects on the local box only.
exchange_writeCan place or cancel orders on Kalshi or Polymarket. Real money.
Always check sf describe --all --json for the safety class before calling a command. exchange_write commands fail-closed without a TTY unless SF_AUTO_CONFIRM=1 is set, but the gate is still your last line of defense — review the order before confirming.

​
Headless mode

sf agent --headless
Emits NDJSON tool calls on stdout and waits for tool responses on stdin. Useful when you want to drive sf’s tool surface from your own LLM harness — for example, embed it in a Trigger.dev task or another agent runtime. See Common workflows for a worked example.

​
MCP

Same tools, different transport. See MCP server for the wire-up.

​
Next steps

JSON contract

CLI envelope shape and exit codes.

Tool manifest

Discover every command programmatically.

CLI command reference

Comprehensive command surface.

Risk gates

Pre-trade safety rails for exchange_write commands.