Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    crg full assessment

    1

    A 19-step cybersecurity risk assessment agent that uses a checked ledger and CVSS v4.0 for consistent quantification.

    $20

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    crg full assessment

    crg full assessment

    Example session with this skill installed

    Run a full cyber risk assessment for a regional hospital. 500 staff, cloud EMR is the main asset. Legacy VPN in use. MSP manages the cloud. No approved appetite yet. English language.

    • Read your context and instructions
    • Compiled the crg full assessment

    I will begin the CyberRiskGuardian assessment for the regional hospital. I have noted the EMR as a crown jewel and the VPN/MSP dependencies as key context.

    Stage 1 — Context and appetite (steps 1–4)

    1.1 Evidence register

    IDSourceTypeStrength
    E1User InputExpert InputMedium

    1.2 Organizational Context

    The scope includes the regional hospital's 500 staff and the cloud-based Electronic Medical Record (EMR) system. Key dependencies include the Managed Service Provider (MSP) for cloud administration and legacy VPN infrastructure for remote access.

    1.4 Risk appetite and materiality

    • Materiality Threshold: 0.05 of IT Budget (Assumed) — Analytical estimate — validation required
    • Risk Appetite: 0.30 — Analytical estimate — validation required
    • Approval Status: Management decision required

    Stage summary

    Initiated assessment for regional hospital. Identified EMR as critical asset. Set preliminary appetite and materiality benchmarks based on industry standards for healthcare.

    Open gaps

    GapNeeded fromMarkerBlocks which step
    Approved Risk AppetiteBoard/ManagementManagement decisionStep 4
    IT Spending FiguresFinance/IT DeptInfo GapStep 18

    State block

    {
      "crg_state": 1,
      "stage_done": 1,
      "org": "Regional Hospital",
      "lang": "en",
      "assets": ["Cloud EMR"],
      "appetite": 0.30,
      "markers_active": true
    }
    

    Reply continue for stage 2.

    Next steps

    1. Review the appetite estimate and confirm if it aligns with internal policy.
    2. Provide specific IT budget figures to refine materiality.
    3. Type continue to begin scenario identification.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Cybersecurity risk assessments often suffer from inconsistent quantification and subjective guesswork. This skill enforces the CyberRiskGuardian (CRG) methodology to deliver a structured, 19-step risk engagement from intake to management reporting.

    What it does

    • Evidence Management maintains a strict register of documented facts, expert inputs, and analytical assumptions.
    • Scenario Selection screens 20+ candidate threats down to a prioritized list of 10 high-impact scenarios.
    • Quantification Engine calculates risk indices and residual risk using the CRG ledger and CVSS v4.0 lookups.
    • Investment Calibration balances remediation budgets against risk appetite and organizational materiality.
    • State Persistence generates JSON state blocks to allow pausing and resuming assessments across different sessions.

    How it works

    1. Intake provides organizational context, "crown jewel" assets, and available evidence.
    2. Stepwise Execution moves through five distinct stages, from appetite setting to scenario quantification.
    3. Ledger Validation verifies all arithmetic against the calculation-protocol.md to ensure indices are mathematically sound.
    4. Final Reporting produces a management-ready report including KRIs and a quality self-check.

    Frameworks & tools

    Utilizes CyberRiskGuardian risk method, CVSS v4.0, ISO/IEC, CIS Controls, and NIST frameworks. Works in English and French (Québec professional standard).

    Why this beats prompting it yourself

    Generic prompts fail to maintain mathematical consistency across complex risk calculations and often lose context over long engagements. This skill enforces a specific 19-step protocol with mandatory state tracking, ensuring your risk indices are calculated via a checked ledger rather than LLM hallucination.

    Use cases

    • Conduct a formal end-to-end cyber risk assessment for a mid-market organization.
    • Quantify the residual risk impact of proposed security investments for budget approval.
    • Resume an ongoing risk engagement by pasting a previous session's state block.

    Known limitations

    Does not predict actual dollar losses or provide legal/audit opinions. Requires manual lookup of CVSS v4.0 scores from the provided reference files.

    Does not predict dollar losses. Requires CVSS v4.0 reference lookups. Indices are for decision support only. Not for live incident response or legal advice.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    Permissions

    Read Files
    Write Files
    Network Access
    Listed7 days ago

    What's inside

    Frequently Asked Questions

    Traditional LLM prompting often results in 'hallucinated' risk scores; this skill solves that by using a 19-step protocol and a checked ledger system that validates every calculation against CVSS v4.0 standards.

    The skill generates a JSON state block at the end of each stage, which you can save and paste back into a new session to pick up exactly where you left off without losing context.

    You will receive the 'crg full assessment' agent skill, the required calculation-protocol.md, reference files for CVSS v4.0 lookups, and a guide for managing the assessment state blocks.

    While it uses NIST and ISO/IEC frameworks as structural backbones, it specifically employs the CyberRiskGuardian methodology and CVSS v4.0 to quantify risk, making it ideal for organizations needing a rigorous, audit-ready approach.

    This skill is designed to work with advanced LLMs (like GPT-4 or Claude 3.5) that support long-context windows and file uploads, ensuring the agent can process the full 19-step methodology.

    Yes, the skill is fully optimized for both English and French (Québec professional standard), including all reporting templates and methodology terminology.

    New in Security