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.
curl -O https://raw.githubusercontent.com/Suzu-Testing/metasploit-cursor-harness/main/.cursor/skills/msf-harness/SKILL.mdgit 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/skills/suzu-testing/metasploit-cursor-harness/msf-harness)<a href="https://agentmods.dev/skills/suzu-testing/metasploit-cursor-harness/msf-harness"><img src="https://agentmods.dev/badge/skills/suzu-testing/metasploit-cursor-harness/msf-harness.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 5.1 | $0.00051 | $0.02672 |
| Opus 5 | $0.00026 | $0.01336 |
| Sonnet 5 | $0.00010 | $0.00534 |
| Haiku 4.5 | $0.00005 | $0.00267 |
Grade A, and why
msf-harness scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:55553/ 2>/dev/null || echo "RPC port check only" How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metasploit Cursor Harness
When to Use MCP vs Shell
Always use MCP for:
- Module search and info (
msf_search_modules,msf_module_info) - Database queries (hosts, services, vulns, creds, loot, notes)
- Exploit execution (
msf_run_exploit), auxiliary modules, post modules - Session management (list, command, terminate, upgrade)
- Handler/listener management
- Payload generation and workspace management
Fall back to shell only for:
- Interactive msfconsole workflows with complex multi-step resource scripts
- Operations not yet exposed in the MCP
Engagement Setup
- Read
.cursor/skills/pentest-workflow/SKILL.mdand check phase state - Verify scope file exists:
scope/scope-master.txt(one CIDR per line) - Create or select engagement:
engagements/{engagement_id}/roe.yaml - Confirm
engagements/{engagement_id}/phase-state.yamlexists - Run gate check:
python .cursor/skills/pentest-workflow/scripts/gate-check.py {engagement_id} - Start WSL RPC if not running:
.\scripts\start-msfrpcd.ps1
LHOST Resolution (mandatory before reverse payloads)
Resolve LHOST deterministically. Try in this order; use the FIRST that succeeds:
msf_get_lab_network()-> uselhostfield from response- Read
engagements/{engagement_id}/lhost.yaml-> uselhostvalue - STOP and ask user for LHOST IP
NEVER hardcode an IP. NEVER use 0.0.0.0. NEVER guess.
Verify RPC connectivity
MSF MCP (preferred):
msf_status()
CLI fallback:
wsl -e bash -lc "msfconsole -x 'version; exit'"
curl -s http://127.0.0.1:55553/ 2>/dev/null || echo "RPC port check only"
Domain skills
Load the domain skill before improvising techniques. Router: pentest-knowledge-base.
| Scope signal | Skill |
|---|---|
| Web application | web-app-pentest |
| Active Directory | internal-ad-pentest |
| Windows host | windows-pentest |
| Open port/service | hacktricks-methodology |
| Database access | database-pentest |
| AWS/Azure/cloud | cloud-pentest |
| Docker/K8s/CI-CD | container-devops-pentest |
| Mobile app | mobile-pentest |
| macOS host/session | macos-pentest |
| Linux host/session | linux-pentest |
| LLM/chatbot/MCP | ai-llm-pentest |
| Binary exploit (ROE) | binary-exploit-pentest |
| Cheatsheets/methodology | methodology-cheatsheets |
| MSF exploit chain | msf-exploit-chain |
| Post-ex MCP workflow | msf-post |
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.
- 7d ago First seen · 313 lines · 51 tokens per session scan A 6730b2ea15b4
msf-harness is a skill published in the GitHub repository Suzu-Testing/metasploit-cursor-harness (3 stars, last pushed 14d ago), licensed MIT. It adds 51 tokens to every session and 2,672 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…