scan

A host security scanner for macOS and Linux that checks computer settings, network configuration, and development prerequisites.

In plain words
What is it for?
Use it to run a full security scan of the current computer or perform the available local checks.
Why use it?
It identifies security misconfigurations and missing requirements, and can install the AgentKeeper command if needed.

Skill for Claude CodeCodex

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 skills/rad-security/claude-code-plugin/scan
Any agent
npx skills add rad-security/claude-code-plugin --skill scan
Clone the repo
git clone --depth 1 https://github.com/rad-security/claude-code-plugin

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 868 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00040 $0.00868
Opus 5 $0.00020 $0.00434
Sonnet 5 $0.00008 $0.00174
Haiku 4.5 $0.00004 $0.00087

Measured yesterday against content hash 6737fa671d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

scan scanned grade B with 2 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 yesterday.

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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://www.agentkeeper.dev/install.sh | bash

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://www.agentkeeper.dev/install.sh | bash
plugins/agentkeeper/skills/scan/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentKeeper Host Security Scan

You are running the AgentKeeper CLI security scanner on the user's machine.

Step 1: Check if AgentKeeper CLI is Installed

which agentkeeper 2>/dev/null || command -v agentkeeper 2>/dev/null

If installed:

Proceed to Step 2.

If not installed:

Display:

AgentKeeper CLI not found.

The AgentKeeper CLI runs 39 security checks across your host configuration,
network settings, and development environment.

Would you like to install it? It takes about 10 seconds:

    curl -fsSL https://www.agentkeeper.dev/install.sh | bash

This installs the `agentkeeper` command to /usr/local/bin.

Ask the user if they want to install. If yes, run:

curl -fsSL https://www.agentkeeper.dev/install.sh | bash

If the install fails, show the error output and suggest:

Installation failed. You can also:
  - Download manually: https://www.agentkeeper.dev/install.sh
  - Or run directly without installing:
    curl -fsSL https://www.agentkeeper.dev/install.sh | bash -s -- --run-only

After successful install, proceed to Step 2.

If the user declines installation, display:

No problem. You can still use these local checks:
  /agentkeeper:audit — audit your Claude Code configuration
  /agentkeeper:secrets — scan for exposed secrets

Stop here.

Step 2: Run the Scanner

Run the AgentKeeper scanner:

agentkeeper scan 2>&1

If the command takes too long (>30 seconds), it may be running interactive prompts. Use:

agentkeeper scan --non-interactive 2>&1

If the scan command is not recognized, try the alternative:

agentkeeper agent run 2>&1

Step 3: Display Results

The scanner outputs a JSON report or formatted text. Display the results inline.

If the output is JSON, parse it and format it as a readable report:

AgentKeeper Host Security Scan

Grade: [letter_grade]
Score: [score]/[total]

Phase 1: macOS Host Security
  [PASS|FAIL|SKIP]  [check_name] — [detail]
  ...

Phase 2: Network Configuration
  [PASS|FAIL|SKIP]  [check_name] — [detail]
  ...

Phase 3: Prerequisites
  [PASS|FAIL|SKIP]  [check_name] — [detail]
  ...

Phase 4: Security Audit
  [PASS|FAIL|SKIP]  [check_name] — [detail]
  ...

[summary line with pass/fail/skip counts]

Read the full file on GitHub · 133 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. yesterday First seen · 133 lines · 40 tokens per session scan B 6737fa671d59

Subscribe to this mod's changes

scan is a skill published in the GitHub repository rad-security/claude-code-plugin (2 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 868 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens