CLI commands

Three commands: setup writes a config, run fires a scan from one, and hunt runs an autonomous campaign. Run opfor <command> --help for the live version any time.

`opfor setup`

Interactive wizard that writes a timestamped config to .opfor/configs/.

Flag	Description
`--agent`	Skip the mode prompt, go to the agent wizard
`--mcp`	Skip the mode prompt, go to the MCP wizard
`--empty`	Write a minimal config without prompts
`--config <path>`	Override the output config path
`--env <path>`	Load env vars from a non-default `.env` path

`opfor run`

Reads a config, fires attacks, judges, and writes the report. With no --config, it runs the setup wizard inline first.

Flag	Description
`--config <file>`	Config to run. Omit to run the wizard inline
`--effort <e>`	Override effort (`adaptive` or `comprehensive`)
`--turns <n>`	Override turn count (`1` forces single-turn)
`--output <dir>`	Override report parent directory (default `.opfor/reports/`)
`--env <path>`	Load env vars from a non-default `.env` path
`--events <path>`	Stream NDJSON run lifecycle events to `<path>` (for CI/automation)
`--objective <text>` / `--objective-file <path>`	Steer every evaluator’s attacks toward a specific free-text mission
`--judge-hint <text>` / `--judge-hint-file <path>`	Free-text steering for the judge’s verdict
`--business-use-case <text>` / `--business-use-case-file <path>`	Free-text domain/business context for the target agent

`opfor hunt`

Autonomous red-team campaign driven by an AI agent. See the autonomous mode guide for details.

Target

Flag	Description
`--endpoint <url>`	Target HTTP endpoint (required unless a local-script target is given via `--target-config`)
`--objective <text>`	Attack objective
`--objective-file <path>`	Read objective from a file
`--target-key-env <var>`	Env var holding the target API key
`--target-key <key>`	Target API key directly
`--name <name>`	Display name for the target
`--target-model <id>`	Model value sent in requests
`--stateless` / `--stateful`	Conversation history handling
`--session-field <name>`	Body field for a client-owned session id
`--target-config <path>`	JSON file with a run-style `target` block — enables server-owned & header sessions, and local-script targets; see session handling

Models

Flag	Default
`--model <id>`	`sonnet`
`--operator-model <id>`	`sonnet`
`--scout-model <id>`	`haiku`

Limits

Flag	Default	Purpose
`--budget-usd <n>`	`10`	Hard USD budget (`0` = unlimited)
`--max-operators <n>`	`6`	Parallel operators
`--max-turns <n>`	`120`	Total agentic turns
`--max-thread-turns <n>`	`25`	Per-thread depth ceiling
`--max-total-threads <n>`	`40`	Total attack threads
`--max-depth <n>`	`3`	Exploration generations
`--max-recon-probes <n>`	`8`	Benign recon probes

Output

Flag	Default	Purpose
`--output <dir>`	`.opfor/reports`	Report directory
`--ui`	off	Launch live dashboard
`--ui-port <port>`	`3847`	Dashboard port
`--env <path>`	—	Load a `.env` file

Get Started

CLI

Browser Extension

MCP Server

Skills

SDK

Evaluators & Suites

Trace-aware Testing

Reference

CLI commands

`opfor setup`

`opfor run`

`opfor hunt`

​opfor setup

​opfor run

​opfor hunt

`opfor setup`

`opfor run`

`opfor hunt`