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.
npx agentmods add rules/suzu-testing/metasploit-cursor-harness/engagement-roegit clone --depth 1 https://github.com/Suzu-Testing/metasploit-cursor-harnessWrote 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.
[](https://agentmods.dev/rules/suzu-testing/metasploit-cursor-harness/engagement-roe)<a href="https://agentmods.dev/rules/suzu-testing/metasploit-cursor-harness/engagement-roe"><img src="https://agentmods.dev/badge/rules/suzu-testing/metasploit-cursor-harness/engagement-roe.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00705 | $0.00705 |
| Opus 5 | $0.00352 | $0.00352 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
engagement-roe 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engagement Rules of Engagement
All Metasploit operations in this harness are subject to strict rules of engagement.
Mandatory Requirements
- Workflow: Follow the phase -> gate -> subgate model in
.cursor/skills/pentest-workflow/SKILL.md. Do not skip phases or hard gates (G0, G2, G4, G6). - Scope enforcement: Every target IP must be in
scope/scope-master.txtor the active engagement'sroe.yamlauthorized_cidrs. Domains must be inscope/in-scope-domains.txtorauthorized_domains. - Engagement ID: Every destructive MCP tool call must include an
engagement_idparameter. If no engagement is active, create one withpython scripts/create-engagement.py --name <name>. - No DoS modules: Modules matching
auxiliary/dos/*are forbidden unconditionally. Do not attempt to work around this restriction. - Check before exploit: Always run
msf_module_checkbeforemsf_run_exploit. The server enforces this whenrequire_check_before_exploit: truein the ROE. If the check says "not vulnerable", do not exploit. - Reviewer gate: SG4.1-reviewer-gate must pass before any exploitation (G4 hard gate).
- Session limits: Do not exceed the
max_sessionsvalue in the active ROE (default: 5). The server fails closed if session count cannot be verified. - CIDR width: Scan targets cannot be broader than
max_scan_cidr(default: /24). Narrow the target range before scanning. - Evidence: Tool outputs auto-save to
evidence/msf/via hooks. Manual evidence should follow the naming conventions inevidence/msf/README.md.
ROE Enforcement Layers
| Layer | Mechanism | Behavior |
|---|---|---|
| Python ROE | msf_harness/mcp/policy/roe.py |
Server-side: CIDR, domain, module, session, exploit-gate, CIDR width |
| MCP Hooks | mcp-action-gate.ps1 |
Pre-call: scope, domain, CIDR width, forbidden module/pattern check |
| Shell Hooks | scope-check.ps1 |
Pre-call: IP extraction, domain, CIDR validation |
| Rate Limit | rate-limit-gate.ps1 |
Pre-call: cooldown for repeated high-risk actions |
| World-State | world-state-gate.ps1 |
Pre-call: duplicate action detection |
| Evidence | mcp-evidence-logger.ps1 |
Post-call: auto-save, ledger, atomic world state |
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.
- 5d ago First seen · 44 lines · 705 tokens per session scan A 7540045bf1d2
engagement-roe is a cursor rule published in the GitHub repository Suzu-Testing/metasploit-cursor-harness (3 stars, last pushed 11d ago), licensed MIT. It adds 705 tokens to every session, about $0.0035 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.