Skip to main content
command CX Codex

autopilot — Claude Code command: what it does, how to install

autopilot is a Claude Code command for autonomous vulnerability hunting. It checks scope, ranks targets, validates findings, and drafts reports.

MIT ★ 16,193 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls
Open on GitHub

What autopilot does

The command automates a 7-step vulnerability hunt: checking scope, running recon (or reusing a cache under 7 days old), prioritizing targets via the recon-ranker agent, probing P1 endpoints, validating findings against a 7-question gate, and drafting reports. Reports are never auto-submitted.

Workflow stops depend on the selected flag. By default, --paranoid halts at every signal and partial finding. The --normal mode halts once after the validation phase, while --yolo proceeds through the full attack surface but still pauses before PUT, DELETE, or PATCH requests. A circuit breaker cuts off traffic after five consecutive 403, 429, or timeout responses on a single host. Requests stay constrained to 1 per second during tests and 10 per second during recon.

Run each target in a clean Claude Code session to prevent finding details and payloads from bleeding between domains. If you switch targets inside one session, run /pickup target.com first to reload target-specific context.

What it helps with

  • execute an autonomous hunting loop from recon to report drafting on a domain
  • enforce scope allowlists and safeguard destructive HTTP methods during security scans
  • cut token usage on repeat audits using the findings ledger
  • batch test multiple domains sequentially from a targets file

Example prompts for the agent

  • /autopilot target.com
  • /autopilot target.com --quick
  • /autopilot targets.txt --yolo

How to install autopilot

1Plugin marketplace

/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls

2Manually: put the files in place

.claude/commands/autopilot.md

Call it with /autopilot. For all projects use ~/.claude/commands/

Questions about autopilot

How to install the autopilot command in Claude Code?

Add the repository with /plugin marketplace add elementalsouls/Claude-BugHunter, then run /plugin install claude-bughunter@elementalsouls. Alternatively, place the command definition in .claude/commands/autopilot.md.

What does the autopilot command do?

It runs a structured hunting cycle covering scope verification, reconnaissance, attack surface ranking, endpoint testing, 7-question validation, and report drafting.

Does autopilot send vulnerability reports automatically?

No, report drafts always require manual review and approval before submission. Destructive methods like PUT, DELETE, and PATCH also pause for user confirmation even in --yolo mode.

Source text

autopilot.md · MIT
---
name: autopilot
description: Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]
---

# /autopilot

Autonomous hunt loop with deterministic scope safety and configurable checkpoints.

## Usage

```
/autopilot target.com                    # default: --paranoid mode
/autopilot target.com --normal           # batch checkpoint after validation
/autopilot target.com --yolo             # minimal checkpoints (still requires report approval)
/autopilot target.com --quick            # fast surface scan, fewer checks, lower token use
/autopilot targets.txt                   # multiple targets — one domain per line in the file
```

## Session Isolation (Important)

**Start a fresh Claude Code session per target.** Claude accumulates context across a session —
testing multiple targets in one session causes cross-contamination where findings, payloads,
and tech stack assumptions from target A bleed into target B.

Best practice:
```bash
# Terminal 1: target A
claude  →  /autopilot targetA.com

# Terminal 2: target B (separate process)
claude  →  /autopilot targetB.com
```

If you must test multiple targets in one session, run `/pickup target.com` at the start of
each target switch to reload the correct context.

## Token Optimization

Use `--quick` for faster, lower-cost scans (skips deep fuzzing and extended nuclei templates):
```
/autopilot target.com --quick    # ~40% fewer tokens, covers main attack surface
/hunt target.com --vuln-class idor   # single bug class — lowest token use
```

For long hunts, run `/compact` (Claude Code built-in) periodically to compress context
without losing findings.

## What This Does

Runs the full hunt cycle without stopping for approval at each step:

```
1. SCOPE     Load and confirm program scope
2. RECON     Run recon (or use cached if < 7 days old)
3. RANK      Prioritize attack surface (recon-ranker agent)
4. HUNT      Test P1 endpoints systematically
5. VALIDATE  7-Question Gate on findings
6. REPORT    Draft reports for validated findings
7. CHECKPOINT  Present to human for review
```

## Safety Guarantees

- **Every URL** is checked against the scope allowlist before any request
- **Reports are NEVER auto-submitted** — always requires explicit approval
- **PUT/DELETE/PATCH** require human approval in --yolo mode (safe methods only)
- **Circuit breaker** stops hammering if 5 consecutive 403/429/timeout on same host
- **Rate limited** at 1 req/sec (testing) and 10 req/sec (recon)

## Checkpoint Modes

| Mode | When it stops | Best for |
|---|---|---|
| `--paranoid` | Every finding + partial signal | New targets, learning the surface |
| `--normal` | After validation batch | Systematic coverage |
| `--yolo` | After full surface exhausted | Familiar targets, experienced hunters |

## Ledger memory (token saving)

The autonomous loop can consult the **autopilot ledger** to skip provably-wasteful agent
calls — an item already **confirmed** on a prior run (carried forward, not re-tested) or a
vuln_class with strong **negative** history on this tech stack (`dead-class`).

- **`--paranoid` (default) / `--normal`:** memory is **off** — full coverage, no skips.
- **`--quick` / `--yolo`:** the command passes `--use-memory` to the engine — skips on.
- A vuln_class never hunted on this stack is **never** skipped, and every skip is logged
  (`hunt: skipped via ledger (...)`). Coverage is never silently reduced.
- Capture is automatic; the ledger fills itself as you run. Manage size with `/memory-gc`.

## After Autopilot

- Run `/remember` to log successful patterns to hunt memory
- Run `/pickup target.com` next time to pick up where you left off
- Check the ledger (`~/.claude/bughunter/memory/findings.jsonl`) or run `/memory-gc` for its size

© Sachin Sharma · MIT · elementalsouls/Claude-BugHunter

Similar slash commands

All slash commands for Security →

From the same set92

The whole set →
hunt-exceptional-conditions The hunt-exceptional-conditions skill reveals when an app leaks stack traces, server paths, or library versions through unhandled exceptions triggered by malformed input. Effective for testing APIs and web endpoints. CX Codex +1 ★ 16,193repo stars triage triage evaluates security findings through a 7-question gate before you write a bug report. It helps bug bounty hunters discard invalid submissions immediately. CX Codex +1 ★ 16,193repo stars report Builds a submission-ready bug bounty report. Generates CVSS 3.1 score, proof of concept, impact statement, and fix in HackerOne, Bugcrowd, Intigriti, or Immunefi format. CX Codex +1 ★ 16,193repo stars validate validate — a validation command that culls weak findings before report writing. Runs a 7-Question Gate and 4-gate checklist to prevent submissions that damage your validity ratio. CX Codex +1 ★ 16,193repo stars hunt-clickjacking hunt-clickjacking is a Claude Code skill that checks whether a page can be framed and used to trigger a sensitive action. It investigates clickjacking in web applications. CX Codex +1 ★ 16,193repo stars hunt hunt dispatches vulnerability assessments across Red Team and WAPT workflows with scope boundaries. CX Codex +1 ★ 16,193repo stars token-scan token-scan — a Claude slash command that hunts rug-pull vectors in token and meme coin contracts on Solidity and Solana. Useful before you buy an unknown token or ship your own. CX Codex +1 ★ 16,193repo stars chain Takes a confirmed bug A and finds B and C to combine into a higher-severity chain. For bug hunters stuck with Low or conditionally valid findings. CX Codex +1 ★ 16,193repo stars

Project sponsors

Companies that keep this analytics open