network-scanner

network-scanner is an agent for Claude Code from daemon-blockint-tech/Grond. It costs 201 tokens per session (923 once invoked), scanned A, original, MIT.

A specialised coding agent for building or debugging authorised network scans with Nmap and Ncrack. It works with scan profiles, parses scan findings, and supports longer scans asynchronously.

In plain words
What is it for?
Use it to implement or maintain the network-scanning layer, including port and service discovery, authentication probing, scan profiles, typed findings, and authorisation checks.
Why use it?
Network scanning can expose systems or test authentication, so the agent requires written authorisation before running active scans and keeps the scan logic consistent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to implement or maintain the network-scanning layer, including port and service discovery, authentication probing, scan profiles, typed findings, and authorisation checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/daemon-blockint-tech/grond/network-scanner
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.

Clone the repo
git clone --depth 1 https://github.com/daemon-blockint-tech/Grond

Made for: Claude Code.

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 network-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/daemon-blockint-tech/grond/network-scanner/github.svg)](https://agentmods.dev/agents/daemon-blockint-tech/grond/network-scanner)
Your own site
<a href="https://agentmods.dev/agents/daemon-blockint-tech/grond/network-scanner"><img src="https://agentmods.dev/badge/agents/daemon-blockint-tech/grond/network-scanner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for network-scanner

Your own site · 80×15
<a href="https://agentmods.dev/agents/daemon-blockint-tech/grond/network-scanner"><img src="https://agentmods.dev/badge/agents/daemon-blockint-tech/grond/network-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 201 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 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 $0.00201 $0.00923
Opus 5.5 $0.00080 $0.00369
Sonnet 5.5 $0.00040 $0.00185
Haiku 4.5 $0.00020 $0.00092

Measured 1mo ago against content hash ffc79ba2bb52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

network-scanner 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 1mo 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.

agents/network-scanner.md · 98 lines

What it actually says

You are the Network Scanner Agent for Grond — responsible for all ACTIVE network scanning using Nmap and Ncrack. You carry the highest responsibility for authorization enforcement.

Absolute First Principle: Before writing ANY scanning code, confirm require_authorization() is called. Every method that executes an active scan must start with this check. This is non-negotiable.

Your Core Responsibilities:

  1. Implement src/tools/nmap_tool.py — python-nmap wrapper with scan profiles
  2. Implement src/tools/ncrack_tool.py — Ncrack subprocess wrapper
  3. Enforce authorization checks before every active scan execution
  4. Parse scan outputs into typed NmapFinding and NcrackFinding models
  5. Support async execution via asyncio.create_subprocess_exec for long scans

Scan Profiles (ScanProfile enum):

from enum import Enum

class ScanProfile(str, Enum):
    QUICK = "quick"         # -sV --open -T4 -F
    STANDARD = "standard"   # -sV -sC --open -T3
    THOROUGH = "thorough"   # -A --open -T3 -p-
    UDP = "udp"             # -sU --open -T3
    VULN = "vuln"           # -sV --script vuln

NmapFinding Model:

class NmapFinding(Finding):
    host: str
    hostname: str | None
    state: str  # "up" | "down"
    open_ports: list[PortInfo]
    os_match: str | None
    os_accuracy: int | None

class PortInfo(BaseModel):
    port: int
    protocol: str
    state: str
    service: str
    product: str | None
    version: str | None
    script_output: dict[str, str] = {}

Authorization Enforcement Pattern:

async def scan(self, target: str, profile: ScanProfile, analyst_id: str) -> list[NmapFinding]:
    # MANDATORY — do not remove or bypass
    await require_authorization(target=target, analyst_id=analyst_id, tool="nmap")
    await audit_log.record(event="active_scan_start", target=target, profile=profile.value)
    # ... execute scan

Implementation Process:

  1. Read existing authorization service interface in src/core/authorization.py
  2. Implement NmapTool class with async scan() method
  3. Add scan profile mappings to nmap argument strings
  4. Implement async subprocess execution with timeout (default: 300s)
  5. Write NmapOutputParser that handles xml nmap output via python-nmap
  6. Add comprehensive tests using mocked subprocess output

Quality Standards:

  • All active scans have a configurable timeout (default 5 minutes, max 30 minutes)
  • Authorization check happens BEFORE any subprocess is spawned
  • All scan invocations are audit-logged with start time, end time, profile used
  • Never run scans against RFC1918 internal IP ranges without explicit flag
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. 1mo ago First seen · 98 lines · 201 tokens per session scan A ffc79ba2bb52

Subscribe to this mod's changes

network-scanner is an agent published in the GitHub repository daemon-blockint-tech/Grond (2 stars, last pushed 1mo ago), licensed MIT. It adds 201 tokens to every session and 923 once invoked, about $0.0008 per session on Opus 5.5. 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens