Cisa Cpg logo

Cisa Cpg

Community
jgsystemsconsulting
cisa-cpg

Knowledge base from CISA Cross-Sector Cybersecurity Performance Goals 2.0. Use for prioritized IT/OT baseline cyber goals aligned to NIST CSF 2.0 (including GOVERN), critical-infrastructure hygiene, MSP/supply-chain expectations, and board-friendly outcome language. Covers CPG 2.0 goals only; does not replace full CSF programs, sector-specific goals (SSGs), or CSET tooling detail.

Overview

Publisherjgsystemsconsulting
Repositoryjgs-se-knowledge-packs
Skill namecisa-cpg
Stars
121
Forks
1
Bundled files
9
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jgsystemsconsulting on GitHub. Read the source before you install it.

Installation

Install the Cisa Cpg AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/cisa-cpg
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs.git /tmp/jgs-se-knowledge-packs
mkdir -p .claude/skills
cp -r /tmp/jgs-se-knowledge-packs/packs/cisa-cpg .claude/skills/cisa-cpg
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cisa Cpg in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cisa Cpg on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cisa Cpg is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CISA Cross-Sector Cybersecurity Performance Goals (CPG) 2.0

Source: CISA CPG 2.0 (US Government work, public domain) | Chapters: 5

When to use

Reach for this pack when selecting or assessing a prioritized baseline of cybersecurity practices for critical infrastructure IT and OT — especially to align investments to CISA’s highest-yield goals, map goals to CSF 2.0 Functions (including GOVERN), brief executives on foundational hygiene, or plan first-mile controls (identity, segmentation, backups, logging, IR readiness) before a full framework build-out.

Prerequisites: none — plain Markdown; no MCP server, API key, or licence tier needed at runtime.

How to Use This Skill

  • Without arguments — load the core frameworks below.
  • With a topic — ask about GOVERN/IDENTIFY/PROTECT/DETECT/RESPOND/RECOVER goals, IT vs OT implementation, prioritization, MFA, segmentation, MSP risk, or 2.0 changes.
  • With a chapter — ask for ch01 through ch05.

Supporting files: glossary.md, patterns.md, cheatsheet.md.

Core Frameworks & Mental Models

What CPGs are

A streamlined, outcome-driven baseline of cybersecurity protections for IT and OT environments across U.S. critical infrastructure. They help organizations pick high-impact practices, prioritize scarce resources, and communicate value to senior leaders.

CSF 2.0 alignment

Goals are grouped under six Functions: GOVERN, IDENTIFY, PROTECT, DETECT, RESPOND, RECOVER. Version 2.0 adds GOVERN and renumbers/consolidates prior goals; former OT-only items fold into universal goals for blended environments.

Goal card pattern

Each goal states an outcome plus recommended actions — usable by practitioners and non-technical stakeholders.

Representative goal map (2.0)

FunctionExample goals
GOVERN1.A responsibilities; 1.C IR plans; 1.D supply-chain reporting; 1.E MSP risk
IDENTIFY2.A/B assets; 2.C/D independent validation; 2.E network topology
PROTECT3.A–3.S identity, MFA, segmentation, training, encryption, backups, logging, edge hardening
DETECT4.A malicious code detection; 4.B adverse events
RESPOND5.A communications; 5.B reporting
RECOVER6.A execute recovery plan

Using CPGs

  • Floor, not ceiling: prioritized subset, not complete assurance.
  • Remap any 1.x trackers before claiming 2.0 coverage.
  • Pair short overview materials with the full report when implementing.
  • Sector-specific goals may extend the cross-sector set.

Chapter Index

#SectionKey content
ch01Purpose and 2.0 ChangesWhy CPGs exist; GOVERN addition; consolidations
ch02GOVERN + IDENTIFYAccountability, IR plans, MSP/supply chain, assets, topology
ch03PROTECTIdentity, MFA, segmentation, backups, logging, edge security
ch04DETECT/RESPOND/RECOVERMalware/events, communications/reporting, recovery execution
ch05IT/OT ImplementationPrioritization, OT constraints, investment framing

Topic Index

  • Adverse event identification → ch04
  • Asset inventory → ch02
  • Backups and restoration → ch03, ch04
  • Board / executive communication → ch01, ch05
  • Change management → ch03
  • CPG 2.0 changes from 1.x → ch01
  • Default passwords / credential hygiene → ch03
  • Encryption → ch03
  • GOVERN function → ch01, ch02
  • Incident communications / reporting → ch04
  • Incident response plans → ch02, ch04
  • Independent control validation → ch02
  • Internet-facing device security → ch03
  • IT vs OT implementation → ch05
  • Logging → ch03
  • Malicious code detection → ch04
  • Managed service provider (MSP) risk → ch02
  • MFA → ch03
  • Network segmentation → ch03, ch05
  • Network topology documentation → ch02
  • Prioritization / where to start → ch01, ch05
  • Privileged vs user accounts → ch03
  • Recovery plan execution → ch04
  • Sector-specific goals (SSGs) → ch05
  • Supply chain incident / vulnerability disclosure → ch02
  • Training → ch03

Supporting Files

  • glossary.md — CPG / CSF terms with chapter references
  • patterns.md — implementation patterns (When/How/Trade-offs)
  • cheatsheet.md — decision rules, goal map, tells & smells

Scope & Limits

This pack covers CISA Cross-Sector Cybersecurity Performance Goals Version 2.0 (report dated December 2025 in the extracted source; aligned to NIST CSF 2.0 including GOVERN) as synthesized reference notes. Combined source_pages = 38 (36-page main report + 2-page slick sheet overview). No separate CPG 2.0 “controls-list” PDF was available at build; the main report holds the full goal inventory. Does not cover: full NIST CSF 2.0 catalog; sector-specific goals in depth; CSET product UI; legal interpretation of NSM-5; or organization-specific compliance scoring. US Government public domain work. No source-material download link is published.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cisa Cpg AI skill do?

Knowledge base from CISA Cross-Sector Cybersecurity Performance Goals 2.0. Use for prioritized IT/OT baseline cyber goals aligned to NIST CSF 2.0 (including GOVERN), critical-infrastructure hygiene, MSP/supply-chain expectations, and board-friendly outcome language. Covers CPG 2.0 goals only; does not replace full CSF programs, sector-specific goals (SSGs), or CSET tooling detail.

Why use Cisa Cpg on TypingMind?

Because you install it once and use it with any model. Cisa Cpg is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cisa Cpg in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/cisa-cpg. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cisa Cpg?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cisa Cpg?

As many as you like. As long as a model supports skills, you can use Cisa Cpg with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cisa Cpg AI skill free?

It is published on GitHub by jgsystemsconsulting. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇