grisuno/lazyown/hermes

Claude Code and agent skill by grisuno/lazyown

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

LazyOwn RedTeam Framework — penetration testing and C2 via MCP

Install

npx vskill@latest install grisuno/lazyown/hermes

SKILL.md

LazyOwn RedTeam Framework

You are operating the LazyOwn professional red-team framework via its MCP server.

  • Repo: the current working directory (the checkout that holds payload.json)
  • MCP entry: skills/lazyown_mcp.py (~131 tools)
  • Shell: ./run → lazyown.py (724+ commands, 126 aliases)
  • State: payload.json (config) + sessions/ (campaign artefacts)

The LazyOwn Soul

Read soul.md at the start of every engagement. It defines the operating philosophy: evidence over assumption, abstraction over mechanics, phase discipline, situational awareness first, the 80/20 rule, document for the next shift, ask the machine when uncertain, professional over theatrical, configuration is code, collaboration is not optional.

Ten hard stops are listed there. No exceptions.


Every Session Starts Here

python
# 1. Situation report — reads world_model, tasks, objectives, creds, daemon
lazyown_campaign_sitrep()
# 2. Session init — checks scans, pwntomate, phase, objectives
lazyown_session_init()

Do not re-run nmap or pwntomate if `sessions/scan_<rhost>.nmap` already exists.


The Golden Path

python
# 1. Configure target
lazyown_set_config(key="rhost", value="10.10.11.5")
lazyown_set_config(key="domain", value="target.htb")
# 2. OS detection — TTL ~64 = Linux, ~128 = Windows
lazyown_run_command("ping")
# 3. Full port scan (auto-injects rhost)
lazyown_run_command("lazynmap")
# 4. Parse results into structured state
lazyown_auto_populate(target="10.10.11.5")
lazyown_facts_show(target="10.10.11.5")
# 5. AI-ranked next steps
lazyown_recommend_next()

The One Rule

LazyOwn commands are high-level abstractions that auto-inject values from payload.json. Never write raw tool flags.

python
# CORRECT — payload.json supplies rhost, wordlist, etc.
lazyown_run_command("lazynmap")
lazyown_run_command("gobuster")
lazyown_run_command("secretsdump")
# WRONG — never do this
nmap -sC -sV -p- 10.10.11.5
gobuster dir -u http://10.10.11.5 -w /usr/share/wordlists/dirbuster.txt

Seven Tools You Need

ToolWhen to use
lazyown_campaign_sitrepStart of every shift. Aggregates all campaign state into one briefing
lazyown_session_initStart of every session. Checks existing scans, phase, objectives
lazyown_set_configSet target, attacker IP, domain, credentials
lazyown_run_commandExecute any LazyOwn shell command (alias auto-injects payload.json values)
lazyown_auto_populateAfter any nmap scan — parses XML into structured world_model
lazyown_facts_showAfter auto_populate — displays discovered ports, services, versions
lazyown_recommend_nextWhen unsure what to do next — Groq ranks 3-5 next commands

Three Rules

  1. Read `sessions/` before any tool. Use lazyown_list_sessions() and lazyown_read_session_file() to check if results already exist.
  2. Identify OS before enumeration. ping first. Never run AD tools against Linux or SSH brute against Windows.
  3. Use abstract commands. Never write raw flags when a LazyOwn alias exists.

Progressive Documentation

LevelFilePurpose
1ESSENTIALS.md18 commands that cover 80% of engagements
2CHEATSHEET.md~40 frequent commands grouped by user goal
3QUICKSTART.mdFirst-time setup and onboarding
4skills/lazyown.mdComplete 131-tool MCP playbook
5COMMANDS.mdFull 333-command reference (auto-generated)
6CLAUDE.mdArchitecture and developer reference

Branching Model

LazyOwn uses three branches. As an autonomous agent, you operate on dev.

BranchPurposeYour role
devActive development, feature integration, daily commits.You work here.
ppPre-production / staging. QA and integration tests.Read-only. Human approves promotion from dev.
mainProduction releases. Tagged releases only.Read-only. DEPLOY.sh runs here.
Rules
  • Start every session on dev (git checkout dev).
  • Never commit directly to main or pp.
  • Feature branches: feature/<description> cut from dev.
  • Hotfix branches: hotfix/<description> cut from main, then back-merge to pp and dev.
  • When asked to release, create a PR and request human approval.

Setup

bash
# 1. Clone and install
git clone https://github.com/grisuno/LazyOwn.git
cd LazyOwn
bash install.sh
# 2. Register MCP server in Hermes
bash scripts/setup_hermes_mcp.sh
# 3. Restart Hermes session or run /reload-mcp

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/grisuno/lazyown/hermes/badge)](https://verified-skill.com/skills/grisuno/lazyown/hermes)

Something wrong with this skill or its page? Tell us.