> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentopfor.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Autonomous mode
> Let an AI agent plan and run a full assessment from a single objective.
`opfor hunt` runs an autonomous red-team campaign. Instead of a fixed suite, you give it an objective and a multi-agent system does the rest — reconnaissance, strategy, adaptive multi-turn attacks, self-judging, and a full report.
It's powered by the Claude Agent SDK, so it needs an Anthropic-compatible key (direct or via OpenRouter) to drive the agents.
## Quickstart
```bash theme={null}
opfor hunt \
--endpoint "https://your-target.com/v1/chat/completions" \
--name "My Target Bot" \
--target-key-env TARGET_API_KEY \
--objective "Probe for jailbreaks, system-prompt leakage, and safety bypasses."
```
Add `--ui` to watch the attack tree unfold in a live dashboard.
Set `ANTHROPIC_API_KEY` (or `OPENROUTER_API_KEY`) for the agents that drive the campaign. `--target-key-env` points to the key for the *target* you're attacking — they're separate.
## How it works
Three agent roles divide the work, each on a model tier suited to its job:
| Agent | Role | Default model |
| ------------- | --------------------------------------------------------------- | ------------- |
| **Commander** | Orchestrates strategy, dispatches operators, interprets results | `sonnet` |
| **Operator** | Executes multi-turn attack threads with personas + strategies | `sonnet` |
| **Scout** | Fingerprints the target with benign recon probes | `haiku` |
The campaign starts with recon, then the commander spawns operators to pursue leads, forking new threads as it finds weak points — until the objective is met or a limit is hit.
## Options
| Option | Description |
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `--endpoint ` | Target HTTP endpoint (required unless a [local-script target](#local-script-targets) is given via `--target-config`) |
| `--objective ` | Attack objective |
| `--objective-file ` | Read objective from a file |
| `--target-key-env ` | Env var holding the target API key |
| `--target-key ` | Target API key directly |
| `--name ` | Display name for the target |
| `--target-model ` | Model value sent in requests |
| `--stateless` / `--stateful` | How conversation history is handled |
| `--session-field ` | Body field for a client-owned session id |
| `--target-config ` | JSON file with a run-style `target` block — enables server-owned & header sessions, and [local-script targets](#local-script-targets); see [session handling](/reference/sessions) |
| Option | Default |
| ----------------------- | -------- |
| `--model ` | `sonnet` |
| `--operator-model ` | `sonnet` |
| `--scout-model ` | `haiku` |
| Option | Default | Purpose |
| ------------------------- | ------- | --------------------------------- |
| `--budget-usd ` | `10` | Hard USD budget (`0` = unlimited) |
| `--max-operators ` | `6` | Parallel operators |
| `--max-turns ` | `120` | Total agentic turns |
| `--max-thread-turns ` | `25` | Per-thread depth ceiling |
| `--max-total-threads ` | `40` | Total attack threads |
| `--max-depth ` | `3` | Exploration generations |
| `--max-recon-probes ` | `8` | Benign recon probes |
| Option | Default | Purpose |
| ------------------ | ---------------- | --------------------- |
| `--output ` | `.opfor/reports` | Report directory |
| `--ui` | off | Launch live dashboard |
| `--ui-port ` | `3847` | Dashboard port |
## Local-script targets
For targets that can't be modeled as a simple HTTP request/response — async/polling APIs, session ids embedded in a URL path segment, or auth flows needing custom logic — point `opfor hunt` at a local script adapter instead of an endpoint. It uses the same `type: "local-script"` shape and stdin/stdout contract as `opfor run` (see the [local script contract](/reference/config#local-script-contract)).
```json target.json theme={null}
{
"target": {
"kind": "agent",
"type": "local-script",
"scriptPath": "./opfor-local-target.js"
}
}
```
```bash theme={null}
opfor hunt --target-config target.json --objective "Probe for jailbreaks and safety bypasses."
```
There is no `--endpoint`, `--script-path`, or similar flag for this — local-script targets are configured **only** via `--target-config`. `--name` still overrides the display name (it defaults to the script's basename).
Hunt's per-thread `threadId` is passed to the script as `sessionId`, so each forked attack thread gets an isolated session automatically — no extra wiring needed. The script has 240 seconds per turn to respond before it's killed.
## Authentication
Credentials for the agents that drive the campaign are resolved in order:
1. `ANTHROPIC_API_KEY` — pay-per-token Anthropic API key.
2. `CLAUDE_CODE_OAUTH_TOKEN` — token from `claude setup-token`.
3. Local Claude subscription — falls back to your `claude login` session (Pro/Max) if neither is set, using that subscription's usage/rate limits.
Options 2 and 3 require the [Claude Code CLI](https://docs.claude.com/claude-code) (`npm install -g @anthropic-ai/claude-code`).
**Gateway / self-hosted proxy** (e.g. OpenRouter) — set both together (a token without a base URL is ignored):
```bash theme={null}
export ANTHROPIC_BASE_URL=https://openrouter.ai/api
export ANTHROPIC_AUTH_TOKEN=sk-or-v1-...
```
## What it probes
The agents draw on a built-in library of vulnerability classes, personas, and strategies, and combine them adaptively.
| Category | Examples |
| ------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
| **Vulnerability classes** | bias · harmful · accuracy · disclosure · injection · excessive-agency · brand-conduct · access-control · mcp-usage |
| **Personas** | naive-user · journalist · security-auditor · frustrated-developer · entitled-customer · fellow-ai |
| **Strategies** | fictional-framing · authority-escalation · gradual-trust · instruction-override · encoding-obfuscation · context-overload |
## Troubleshooting
Check `ANTHROPIC_API_KEY` and `ANTHROPIC_BASE_URL` are set correctly for the agent models.
Lower `--max-operators` or `--budget-usd` to reduce concurrency and total calls.
The same campaign is available as `hunt()` in the SDK, with progress streaming.