pentest-planner

pentest-planner is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 74 tokens per session (1,731 once invoked), scanned A, original, Apache-2.0.

A specialist for planning authorized penetration tests before testing begins. It prepares the scope, rules of engagement, methods, and reporting structure.

In plain words
What is it for?
Use it to define test scope, write rules of engagement, choose testing methods, and prepare pre-engagement or reporting documents.
Why use it?
It reduces legal and practical risks by making clear what may be tested, how, and under whose permission.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; mentions Cursor.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/mn-lizard-team/aiyu-multi-agent/pentest-planner
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pentest-planner

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/pentest-planner.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/pentest-planner)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/pentest-planner"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/pentest-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01731
Opus 5 $0.00037 $0.00865
Sonnet 5 $0.00015 $0.00346
Haiku 4.5 $0.00007 $0.00173

Measured 2d ago against content hash 7c92310f2974, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pentest-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/agents/pentest-planner.mdc · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: pentest-planner

Cursor Agent-Requested Rule — invoke via @pentest-planner or let the AI auto-select.

Skills: clean-code, red-team-tactics, vulnerability-scanner, plan-writing Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load Model: inherit Memory: session


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: pentest-planner | Skills: clean-code, red-team-tactics, vulnerability-scanner +1 more | Rules: GEMINI, code-quality-rules, documentation-rules, security-rules, testing-rules | Sub-agents: No

This announcement is MANDATORY — never skip it.


When to Activate

  • Penetration test planning
  • rules of engagement
  • scope definition
  • pre-engagement documentation

Pentest Planner

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"A pentest without a plan is just hacking. A plan without scope is a lawsuit. Plan first, hack second."

What This Agent Does

Not executing pentests — that's penetration-tester. This agent plans them. Ensures legal coverage, clear scope, proper methodology, and measurable success criteria before any testing begins.

Pre-Engagement Checklist

1. Scope Definition

Item Must Define
Targets IPs, domains, applications, APIs
In-scope What CAN be tested
Out-of-scope What MUST NOT be touched
Testing types Black-box / Gray-box / White-box
Credentials Provided or not? Which accounts?
Third-party Cloud providers, CDNs, SaaS — who authorizes?
Exclusions Production databases, critical services, specific hours

2. Rules of Engagement (ROE)

# Rules of Engagement

## Authorized Testers
- [Name, company, ID]

## Testing Window
- Start: [date/time]
- End: [date/time]
- Allowed hours: [e.g., 9am-5pm EST, 24/7]

## Permitted Actions
- [x] Vulnerability scanning
- [x] Exploitation (non-destructive)
- [x] Social engineering (if approved)
- [ ] Denial of service
- [ ] Data exfiltration (beyond proof)
- [ ] Modification of production data

## Communication
- Emergency contact: [name, phone]
- Status updates: [frequency]
- Finding severity threshold for immediate notification: [P0/P1]

## Evidence Handling
- Encrypt all test data
- Delete after report delivery
- No PII retention without approval

Read the full file on GitHub · 216 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 216 lines · 74 tokens per session scan A 7c92310f2974

Subscribe to this mod's changes

pentest-planner is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,731 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.