harness-orchestration

harness-orchestration is a cursor rule for Cursor from Suzu-Testing/metasploit-cursor-harness. It costs 1,434 tokens per session, scanned A, original, MIT.

A workflow rule set for organizing authorized penetration tests into phases, checkpoints, smaller tasks, and specialized skills. It also defines when work should be delegated to another agent.

In plain words
What is it for?
Use it to route reconnaissance, analysis, exploitation, and post-exploitation work, run checkpoint scripts, and choose the appropriate security-testing skills or agents.
Why use it?
It keeps multi-step testing ordered and requires pending checkpoints to be completed before the workflow advances.

Cursor rule for 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/suzu-testing/metasploit-cursor-harness/harness-orchestration
Clone the repo
git clone --depth 1 https://github.com/Suzu-Testing/metasploit-cursor-harness

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 harness-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/rules/suzu-testing/metasploit-cursor-harness/harness-orchestration.svg)](https://agentmods.dev/rules/suzu-testing/metasploit-cursor-harness/harness-orchestration)
Your own site
<a href="https://agentmods.dev/rules/suzu-testing/metasploit-cursor-harness/harness-orchestration"><img src="https://agentmods.dev/badge/rules/suzu-testing/metasploit-cursor-harness/harness-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,434 This file is loaded in full into every session.
When invoked 1,434 The same file — it is already loaded in full.
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 $0.01434 $0.01434
Opus 5 $0.00717 $0.00717
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00143 $0.00143

Measured 5d ago against content hash d0d684bd8a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-orchestration 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.

.cursor/rules/harness-orchestration.mdc · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pentest Workflow Orchestration

All multi-step pentest work follows phases -> gates -> subgates -> skills.

Start here

  1. Read .cursor/skills/pentest-workflow/SKILL.md
  2. Run gate check: python .cursor/skills/pentest-workflow/scripts/gate-check.py {engagement_id}
  3. Complete pending subgates by loading each subgate's linked skill
  4. Mark done: python .cursor/skills/pentest-workflow/scripts/complete-subgate.py {subgate_id}

Phase routing

Phase Delegate to Primary skills
pre_engage, model, report /harness-orchestrator pentest-workflow, methodology-cheatsheets, msf-harness
recon, analyze /msf-recon-agent msf-recon + domain skill (web, AD, cloud, AI, etc.)
exploit /msf-exploit-agent msf-exploit-chain
post_exploit /msf-post-agent msf-post, internal-ad, windows/linux/macos/cloud/container/pivoting/persistence skills

Delegation thresholds

Trigger Action
Single subgate, single target Execute directly using subgate skill
3+ targets, same subgate type Delegate to specialized subagent
Phase transition or gate advance /harness-orchestrator
Broad instruction ("start testing") /harness-orchestrator
SG4.1 or pre-exploit /msf-reviewer (mandatory)

Subagent reference

Agent Purpose
/harness-orchestrator Phase management, gate advancement, coordination
/msf-recon-agent Recon/analyze subgates
/msf-exploit-agent Exploit subgates
/msf-post-agent Post-exploit subgates
/msf-reviewer G4 hard gate approval

Skill reference (57 skills)

Core (7)

Skill Use
pentest-workflow Phase/gate procedure, advancement
pentest-knowledge-base Skill routing by scenario
methodology-cheatsheets SG2 model, shells, cross-cutting refs
msf-harness Setup, ROE, tool reference
msf-recon MCP recon workflow
msf-exploit-chain SG4.* exploit subgates
msf-post Post-exploitation subgates

Read the full file on GitHub · 130 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. 5d ago First seen · 130 lines · 1,434 tokens per session scan A d0d684bd8a3c

Subscribe to this mod's changes

harness-orchestration is a cursor rule published in the GitHub repository Suzu-Testing/metasploit-cursor-harness (3 stars, last pushed 11d ago), licensed MIT. It adds 1,434 tokens to every session, about $0.0072 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.