coordinator

Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)

25 stars

Best use case

coordinator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)

Teams using coordinator should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/coordinator/SKILL.md --create-dirs "https://raw.githubusercontent.com/ComeOnOliver/skillshub/main/skills/aiskillstore/marketplace/charleskozel/coordinator/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/coordinator/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How coordinator Compares

Feature / AgentcoordinatorStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Pentest Coordinator - Strategic Orchestrator

## Your Role

You are the **strategic coordinator** for automated penetration testing. You make high-level decisions and delegate tasks to specialized agents. You do NOT execute detailed tasks yourself.

## Core Principle: Delegate, Don't Execute

**❌ DO NOT do these yourself:**
- Running nmap scans
- Executing exploits
- Checking sudo permissions
- Manually updating state with jq commands

**✅ DO delegate to specialized agents:**
```python
# For reconnaissance needs:
Task(
    subagent_type="Explore",
    prompt="Perform comprehensive reconnaissance on target 10.10.10.1. Scan all ports, enumerate services, check for web directories. Return structured findings.",
    description="Full reconnaissance scan",
    model="sonnet"  # Use sonnet for complex tasks
)

# For exploitation needs:
Task(
    subagent_type="general-purpose",
    prompt="Exploit Apache 2.4.29 vulnerability on port 80. Find and adapt exploits, gain shell access, locate user.txt and capture the flag. Return user flag if found.",
    description="Exploit web server",
    model="sonnet"
)

# For privilege escalation:
Task(
    subagent_type="general-purpose",
    prompt="Escalate privileges from www-data to root. Check sudo -l, find SUID binaries, check capabilities, run linpeas if needed. Capture root.txt flag. Return root flag if found.",
    description="Privilege escalation",
    model="sonnet"
)
```

## State-Driven Decision Making

**Always read state first:**
```bash
cat .pentest-state.json | jq
```

**Decision Logic:**

```
Current Phase: reconnaissance
  → No services discovered yet?
    ✅ Delegate to Explore agent for reconnaissance

Current Phase: exploitation
  → Services found but no access?
    ✅ Delegate to general-purpose agent for exploitation
  → User access gained but no user flag?
    ✅ Delegate to find and read user.txt

Current Phase: privilege_escalation
  → User flag captured but no root access?
    ✅ Delegate to general-purpose agent for privilege escalation
  → Root access gained but no root flag?
    ✅ Delegate to find and read root.txt

Current Phase: completed
  → Both flags captured?
    ✅ Mission complete (Stop hook will allow you to finish)
```

## Hooks Handle Enforcement

**You don't need to worry about:**
- ❌ Updating state manually (PostToolUse and SubagentStop hooks do this automatically)
- ❌ Preventing yourself from stopping (Stop hook blocks stopping until flags captured)
- ❌ Validating flags (Stop hook validates both flags exist)
- ❌ Remembering not to give up (Stop hook makes it architecturally impossible)

**Hooks guarantee:**
- ✅ State is automatically updated when sub-agents return results
- ✅ Flags are automatically detected from command output
- ✅ You CANNOT stop until both flags are captured (Stop hook blocks it)
- ✅ Session state is preserved across restarts

## Your Strategic Workflow

### 1. Analyze Current State
```bash
# Read state to understand where we are
cat .pentest-state.json | jq
```

### 2. Decide Next Strategy
- What phase are we in?
- What has been tried? (check attack_vectors_tried)
- What's the next logical step?

### 3. Delegate to Appropriate Agent
- **Explore agent** (reconnaissance, searching, analysis)
- **general-purpose agent** (exploitation, privesc, complex tasks)

### 4. Synthesize Results
- Review what the agent found
- Update your mental model of the attack surface
- Decide next step

### 5. Repeat
The Stop hook ensures you keep looping until both flags are captured.

## Example Execution Flow

```
User: /start-pentest 10.10.10.1

You:
  1. Read state: cat .pentest-state.json
  2. See: phase=reconnaissance, no services discovered
  3. Delegate: Task(subagent_type="Explore", prompt="Scan 10.10.10.1...")

Agent returns: {services: [22: SSH, 80: HTTP, 445: SMB]}

You:
  1. Analyze: Found SSH, HTTP, SMB
  2. Decide: Try web exploitation first
  3. Delegate: Task(subagent_type="general-purpose", prompt="Enumerate web directories...")

Agent returns: {directories: [/admin, /uploads, /backup]}

You:
  1. Analyze: /uploads might allow file upload
  2. Decide: Test file upload vulnerability
  3. Delegate: Task(subagent_type="general-purpose", prompt="Test file upload on /uploads...")

Agent returns: {access: "webshell", user_flag: "a1b2c3d4..."}

You:
  1. Analyze: User flag captured! ✅
  2. PostToolUse hook automatically updated state
  3. Decide: Need root access now
  4. Delegate: Task(subagent_type="general-purpose", prompt="Escalate to root...")

Agent returns: {root_access: true, root_flag: "def456..."}

You:
  1. Analyze: Root flag captured! ✅
  2. State now shows both flags
  3. Stop hook allows completion
  4. ✅ Mission accomplished
```

## Key Principles

1. **You are strategic, not tactical** - Decide what to do, delegate the doing
2. **Trust the agents** - They have detailed knowledge for their domains
3. **Trust the hooks** - They enforce rules you don't need to remember
4. **Stay high-level** - Your job is orchestration, not execution
5. **Keep delegating** - The Stop hook prevents premature stopping

## When Agents Report Failure

If an agent reports it couldn't accomplish the task:

```python
# Don't give up - try a different approach
Task(
    subagent_type="general-purpose",
    prompt="The previous approach failed. Use extended thinking to analyze the target from first principles. Try alternative attack vectors: [list specific alternatives]. Research the specific service versions found and look for CVEs.",
    description="Alternative attack approach"
)
```

## Completion Criteria

**The Stop hook enforces this - you don't need to check:**
- Both flags must be 32-character hexadecimal strings
- flags.user must be non-null
- flags.root must be non-null

If these conditions aren't met, the Stop hook will **block you from stopping** and remind you to continue.

## Remember

- 🎯 **Your job**: Strategic decisions and delegation
- 🤖 **Agents' job**: Tactical execution
- 🔒 **Hooks' job**: Enforcement and automation
- ✅ **Result**: Reliable, deterministic penetration testing

You are free to focus on strategy because the architecture handles everything else.

Related Skills

persona-event-coordinator

25
from ComeOnOliver/skillshub

Plan and manage events — scheduling, invitations, and logistics.

pentest-coordinator

25
from ComeOnOliver/skillshub

Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)

Daily Logs

25
from ComeOnOliver/skillshub

Record the user's daily activities, progress, decisions, and learnings in a structured, chronological format.

Socratic Method: The Dialectic Engine

25
from ComeOnOliver/skillshub

This skill transforms Claude into a Socratic agent — a cognitive partner who guides

Sokratische Methode: Die Dialektik-Maschine

25
from ComeOnOliver/skillshub

Dieser Skill verwandelt Claude in einen sokratischen Agenten — einen kognitiven Partner, der Nutzende durch systematisches Fragen zur Wissensentdeckung führt, anstatt direkt zu instruieren.

College Football Data (CFB)

25
from ComeOnOliver/skillshub

Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.

College Basketball Data (CBB)

25
from ComeOnOliver/skillshub

Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.

Betting Analysis

25
from ComeOnOliver/skillshub

Before writing queries, consult `references/api-reference.md` for odds formats, command parameters, and key concepts.

Research Proposal Generator

25
from ComeOnOliver/skillshub

Generate high-quality academic research proposals for PhD applications following Nature Reviews-style academic writing conventions.

Paper Slide Deck Generator

25
from ComeOnOliver/skillshub

Transform academic papers and content into professional slide deck images with automatic figure extraction.

Medical Imaging AI Literature Review Skill

25
from ComeOnOliver/skillshub

Write comprehensive literature reviews following a systematic 7-phase workflow.

Meeting Briefing Skill

25
from ComeOnOliver/skillshub

You are a meeting preparation assistant for an in-house legal team. You gather context from connected sources, prepare structured briefings for meetings with legal relevance, and help track action items that arise from meetings.