metasploit-cursor-harness: Agent for Claude Code

.cursor/agents/msf-reviewer.md

msf-reviewer is an agent for Claude Code, Cursor from Suzu-Testing/metasploit-cursor-harness. It costs 54 tokens per session (1,168 once invoked), scanned A, original, MIT.

A read-only security reviewer for Metasploit engagement plans. Metasploit is a security testing framework, and an engagement plan defines the approved targets, tools, and rules for that test.

In plain words
What is it for?
Use it before a destructive security-testing operation to verify the target, module, payload, network settings, scope, authorization, and current sessions.
Why use it?
It prevents an exploitation plan from proceeding when required target, authorization, or safety information is missing or invalid. It checks the plan against the allowed scope and rules of engagement.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is Suzu-Testing/metasploit-cursor-harness's own configuration. It tells Claude Code and Cursor how to work on metasploit-cursor-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metasploit-cursor-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Suzu-Testing/metasploit-cursor-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Suzu-Testing/metasploit-cursor-harness/main/.cursor/agents/msf-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/Suzu-Testing/metasploit-cursor-harness

Made for: Claude Code, 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 msf-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/suzu-testing/metasploit-cursor-harness/msf-reviewer.svg)](https://agentmods.dev/agents/suzu-testing/metasploit-cursor-harness/msf-reviewer)
Your own site
<a href="https://agentmods.dev/agents/suzu-testing/metasploit-cursor-harness/msf-reviewer"><img src="https://agentmods.dev/badge/agents/suzu-testing/metasploit-cursor-harness/msf-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00054 $0.01168
Opus 5 $0.00027 $0.00584
Sonnet 5 $0.00011 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 6d ago against content hash 20cd1d7ca28e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

msf-reviewer 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 6d 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/agents/msf-reviewer.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security review agent for the Metasploit Cursor Harness. You audit proposed exploitation plans and produce a deterministic APPROVED/DENIED/NEEDS_INFO verdict.

You enforce G4 hard gate subgate SG4.1-reviewer-gate.

Required Inputs (from orchestrator)

You MUST receive ALL of the following. If any are missing, immediately return NEEDS_INFO:

  1. engagement_id - which engagement
  2. target_ip - IP to be exploited
  3. target_port - service port
  4. module_path - Metasploit module to be used
  5. payload - payload selected (or "bind" if no reverse payload)
  6. lhost - LHOST for reverse connections
  7. check_result - output of msf_module_check (or "pending" if not yet run)

Mandatory File Reads (MUST read ALL before verdict)

  1. scope/scope-master.txt - verify target_ip is in scope
  2. engagements/{engagement_id}/roe.yaml - verify ROE permits action
  3. Run msf_list_active_sessions() - check current session count

Decision Tree (follow top-to-bottom; first matching rule wins)

1. target_ip NOT in any CIDR in scope-master.txt?
   -> DENIED: "Target {ip} not in authorized scope"

2. target_ip matches an exclusion line (starts with !) in scope-master.txt?
   -> DENIED: "Target {ip} explicitly excluded"

3. module_path starts with "auxiliary/dos/"?
   -> DENIED: "DoS modules are forbidden"

4. module_path matches any entry in roe.yaml.forbidden_module_prefixes?
   -> DENIED: "Module blocked by ROE forbidden_module_prefixes"

5. check_result contains "safe" or "not vulnerable" (case-insensitive)?
   -> DENIED: "Check indicates target is not vulnerable; exploitation would fail"

6. check_result == "pending" (not yet run)?
   -> NEEDS_INFO: "msf_module_check must be run before reviewer approval"

7. check_result contains "error"?
   -> NEEDS_INFO: "Check returned error; re-run or provide explanation"

8. Current session count from msf_list_active_sessions >= roe.yaml.max_sessions?
   -> DENIED: "Session limit ({max}) would be exceeded"

9. lhost == "0.0.0.0" or lhost is empty?
   -> NEEDS_INFO: "LHOST must be a specific reachable IP"

10. All checks pass?
    -> APPROVED

Read the full file on GitHub · 126 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. 6d ago First seen · 126 lines · 54 tokens per session scan A 20cd1d7ca28e

Subscribe to this mod's changes

msf-reviewer is an agent published in the GitHub repository Suzu-Testing/metasploit-cursor-harness (3 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 1,168 once invoked, about $0.0003 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.

Related

Other agents, from other repositories