Skip to content
Security
Command

/engage.init

Initialize a new security engagement following the Kill Chain workflow

From plugin
offensive-claude
33818 skills8 agents18 commands1 hook
Install
> /plugin marketplace add hypnguyen1209/offensive-claude
> /plugin install offensive-claude@offensive-claude-marketplace

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/engage.init

Context preview

What this command does when you run it.

Initialize a new security engagement following the Kill Chain workflow

Command definition

engage.init.md
description: Initialize a new security engagement following the Kill Chain workflow

/engage.init

Initializes a new engagement project with the selected workflow preset.

Usage

`/engage.init <workflow-type> --client <client-name> [--date YYYY-MM-DD]`

Workflow Types

  • `web-app` — Web application pentest (OWASP-focused)
  • `network` — Internal network pentest
  • `red-team` — Full red team engagement (all 9 phases)
  • `cloud` — Cloud security audit (AWS/Azure/GCP)
  • `mobile` — Mobile application pentest (Android/iOS)
  • `ad-domain` — Active Directory domain assessment
  • `bug-bounty` — Bug bounty hunting

Process

1. Load the selected workflow YAML from `workflows/<type>.yml` 2. Create engagement directory: `engagement-<client>-<date>/` 3. Create `.engage/state.json` with engagement metadata 4. Copy phase templates from `templates/<phase>/` based on workflow 5. Create `evidence/` subdirectories (screenshots, pcaps, logs) 6. Print status and suggest `/engage.scope` as next step

State File Structure

The `.engage/state.json` tracks:

  • Engagement metadata (client, date, workflow type)
  • Current phase (0-8)
  • Phase completion status
  • Gate validation results
  • Findings count per phase

Next Steps

After initialization, run `/engage.scope` to begin Phase 0 (Scope Definition).

Ships withoffensive-claude

A spec-driven offensive security framework for Claude Code — structured engagement workflows based on the Cyber Kill Chain, 31 kill-chain skills (multi-file progressive-disclosure) plus a discipline layer (a SessionStart dispatcher + 6 process/discipline

Get the whole plugin