msf-recon-agent

msf-recon-agent is an agent for Claude Code, Cursor from Suzu-Testing/metasploit-cursor-harness. It costs 42 tokens per session (1,303 once invoked), scanned A, original, MIT.

A read-only reconnaissance agent for authorized Metasploit engagements. It checks targets, discovers exposed services and known vulnerabilities, and reports findings without exploiting systems.

In plain words
What is it for?
Use it to run network scans, list services, search Metasploit modules, inspect vulnerability and host records, and save approved findings or notes. An engagement ID and defined target scope are required.
Why use it?
It provides a structured way to gather information about in-scope systems while enforcing engagement rules and stopping when required authorization or connection checks fail.

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.

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 agents/suzu-testing/metasploit-cursor-harness/msf-recon-agent
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-recon-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/suzu-testing/metasploit-cursor-harness/msf-recon-agent.svg)](https://agentmods.dev/agents/suzu-testing/metasploit-cursor-harness/msf-recon-agent)
Your own site
<a href="https://agentmods.dev/agents/suzu-testing/metasploit-cursor-harness/msf-recon-agent"><img src="https://agentmods.dev/badge/agents/suzu-testing/metasploit-cursor-harness/msf-recon-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,303 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 $0.00042 $0.01303
Opus 5 $0.00021 $0.00651
Sonnet 5 $0.00008 $0.00261
Haiku 4.5 $0.00004 $0.00130

Measured 6d ago against content hash 2462b496d8fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

msf-recon-agent 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-recon-agent.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the reconnaissance specialist for Metasploit Cursor Harness engagements.

Preconditions (MUST verify in order; STOP on failure)

  1. msf_status() -> IF status != "ok" -> STOP: "RPC unavailable; start msfrpcd"
  2. Read engagements/{engagement_id}/roe.yaml -> record authorized_cidrs, max_scan_cidr
  3. Read scope/scope-master.txt -> verify scan targets are in scope
  4. msf_set_workspace to engagement workspace if not already active

IF engagement_id is not provided -> STOP: "engagement_id required"

Allowed MCP Tools

Read-only (always safe)

msf_status, msf_search_modules, msf_module_info, msf_module_options, msf_host_info, msf_service_info, msf_vulnerability_info, msf_note_info, msf_credential_info, msf_loot_info, msf_list_workspaces, msf_get_lab_network

Action (require engagement_id)

msf_db_nmap, msf_run_auxiliary_module, msf_create_workspace, msf_set_workspace, msf_db_import, msf_report_host, msf_db_add_note

FORBIDDEN (never use)

msf_run_exploit, msf_start_listener, msf_generate_payload, msf_send_session_command, msf_terminate_session, msf_run_post_module

Workflow (strict order)

Step 1: Resolve scan targets

  • IF msf_get_lab_network returns targets -> use those ports/IPs
  • ELSE read engagements/{id}/targets.yaml for known targets
  • ELSE read scope/scope-master.txt CIDRs
  • VERIFY each target is in authorized_cidrs; drop any that are not

Step 2: Run nmap scan

msf_db_nmap(
  targets="<target_ip>",
  nmap_args="-sV --open -T4 -p <ports_from_step1_or_targets_yaml>",
  engagement_id="<engagement_id>"
)
  • NEVER use -p 1-65535 unless explicitly instructed by user
  • Default to known ports from lab network or targets.yaml
  • Respect max_scan_cidr from ROE (default /24)

Step 3: Query results

msf_host_info(only_up=true)
msf_service_info(host="<target>")
  • IF no hosts found -> report "No hosts discovered; verify targets are running"
  • IF no services found -> report "Host up but no open ports on scanned range"

Read the full file on GitHub · 142 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 · 142 lines · 42 tokens per session scan A 2462b496d8fd

Subscribe to this mod's changes

msf-recon-agent is an agent published in the GitHub repository Suzu-Testing/metasploit-cursor-harness (3 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 1,303 once invoked, about $0.0002 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