agentleFS
RidhuanDEVRidhuanDEV/claude-skills/shadow-grc/SKILL.md

shadow-grc

Skill1 starsChanged yesterdayMITView on GitHub

Evidence-Based IT Governance, Risk & Regulatory Assurance. Use when auditing COBIT 2019 (Capability vs Maturity), ISO/IEC 27001:2022 (Clauses 4-10 + 93 Annex A SoA), SPBE & Indeks KAMI BSSN, or banking IT rules (POJK 11/2022 & PADK OJK 1/2026).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill whenever the Monarch invokes /shadow-grc, executes IT governance/security readiness assessments, designs risk registers, …

    line 8
  2. Distinctive:

    Test Design Effectiveness (does the policy/control address the risk?) separately from Operating Effectiveness (evidence of consistent …

    line 23
  3. Very specific:

    Every finding MUST carry: Criteria, Condition, Cause, Effect/Risk, Recommendation, and Evidence Ref + confidence level.

    line 29
  4. Distinctive:

    Never declare an organization officially "ISO 27001 Certified" or "Regulator Approved" based on internal/advisory self-assessment.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/shadow-grc — Evidence-Based Governance & Regulatory Assurance

Use this skill whenever the Monarch invokes /shadow-grc, executes IT governance/security readiness assessments, designs risk registers, builds a Statement of Applicability (SoA), or prepares audit workpapers for Banking, Government SPBE, BUMN, or Enterprise engagements.

Integrates with shadow-monarch/reference/CONSULTING-INTELLIGENCE-CORE.md and deep methodologies:

  • methodologies/AUDIT-LIFECYCLE-AND-REGULATORY-CROSSWALK.md — Risk-based audit lifecycle, Design vs Operating control testing, COBIT 2019 capability vs maturity rules, ISO/IEC 27001:2022 Clauses 4–10 + 93 Annex A controls, SPBE/Indeks KAMI, and POJK 11/POJK.03/2022 + PADK OJK Nomor 1 Tahun 2026.
  • playbooks/WORKPAPERS-AND-ASSURANCE-TEMPLATES.md — Audit Workpaper, Regulatory Obligations Register, Control Test Sheet, SoA Matrix, Evidence Sufficiency Matrix, Management Action Plan, and Executive Assurance Report.

1. Execution Contract (Evidence & Regulatory Precision)

  1. Context & Regulatory Applicability First: Query consulting_core.py --check-regulations for the client's sector.
    • For Indonesian Banking after 1 March 2026, apply POJK 11/POJK.03/2022 + PADK OJK No. 1 Tahun 2026 (never cite revoked SEOJK 21/SEOJK.03/2017 as active).
    • For SPBE/Government, verify exact Indeks KAMI BSSN workbook version before scoring.
  2. Full Audit Lifecycle & Control Testing:
    • Follow Scoping -> Audit Universe -> Risk-Based Plan -> Evidence Request (PBC) -> Sampling Rationale -> Fieldwork -> 6-Part Finding -> Management Response -> Remediation & Follow-Up.
    • Test Design Effectiveness (does the policy/control address the risk?) separately from Operating Effectiveness (evidence of consistent execution across sampled periods).
  3. Methodological Precision:
    • COBIT 2019: Evaluate Process Capability (0–5 per objective) separately from Focus Area Maturity (0–5 systemic aggregate) — never collapse both into one unverified number.
    • ISO/IEC 27001:2022: Cover Management System Clauses 4–10 alongside the 93 Annex A Controls (37 Organizational, 8 People, 14 Physical, 34 Technological) with explicit SoA justification for inclusions/exclusions.
    • Respect copyright boundaries: map and reference standards legitimately without reproducing proprietary full text.
  4. 6-Part Defensible Findings & Escalation Boundary:
    • Every finding MUST carry: Criteria, Condition, Cause, Effect/Risk, Recommendation, and Evidence Ref + confidence level.
    • Never declare an organization officially "ISO 27001 Certified" or "Regulator Approved" based on internal/advisory self-assessment.

2. Deterministic Assurance Engine

python "shadow-grc/scripts/grc_assurance_engine.py" --self-test
python "shadow-grc/scripts/grc_assurance_engine.py" --assess-cobit path/to/cobit_scores.json
python "shadow-grc/scripts/grc_assurance_engine.py" --validate-soa path/to/iso27001_soa.json
python "shadow-grc/scripts/grc_assurance_engine.py" --validate-findings path/to/findings.json --sector BANKING

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.