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.
npx agentmods add commands/mlunato47/claude-grc-plugin/multi-frameworkgit clone --depth 1 https://github.com/mlunato47/claude-grc-pluginWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.01530 |
| Opus 5 | $0.00004 | $0.00765 |
| Sonnet 5 | $0.00002 | $0.00306 |
| Haiku 4.5 | $0.00001 | $0.00153 |
Grade A, and why
multi-framework 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- multi-framework — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/grc:multi-framework
Analyze overlap and gaps across multiple compliance frameworks to identify shared coverage and incremental work.
Usage
/grc:multi-framework [frameworks] [baseline?]
Arguments
- frameworks: Two or more frameworks, comma-separated. Accepts:
fedramp,nist,soc2,iso27001,pci,hipaa,cmmc,cis,cobit,ccm - baseline (optional): For NIST-based frameworks:
low,moderate,high. Defaults tomoderate.
Examples
/grc:multi-framework fedramp,soc2
/grc:multi-framework fedramp,soc2,pci moderate
/grc:multi-framework fedramp,iso27001
/grc:multi-framework soc2,iso27001,pci
/grc:multi-framework fedramp,soc2,iso27001,pci high
/grc:multi-framework cmmc,fedramp
Behavior
When invoked:
-
No redaction reminder needed — this is a pure reference/analysis command using framework knowledge only. No user content is processed.
-
Read the appropriate reference files:
- Framework files for each specified framework from
skills/grc-knowledge/frameworks/ - Mapping files from
skills/grc-knowledge/mappings/for each framework pair (chaining through NIST) skills/grc-knowledge/mappings/cross-framework-matrix.mdfor high-level family mapping
- Framework files for each specified framework from
-
Generate a multi-framework analysis:
a. Coverage Overlap Matrix For each major control domain/family, show which frameworks cover it:
- Full coverage: the framework explicitly addresses this domain
- Partial coverage: some aspects addressed but not all
- Gap: the framework doesn't address this domain
b. Shared Requirements Activities and controls that satisfy multiple frameworks simultaneously:
- Access control reviews → FedRAMP AC-2, SOC 2 CC6.1, ISO A.5.15, PCI 8.6
- Vulnerability scanning → FedRAMP RA-5, SOC 2 CC7.1, ISO A.8.8, PCI 11.3
- Security training → FedRAMP AT-2, SOC 2 CC1.4, ISO 7.2, PCI 12.6
- Incident response → FedRAMP IR-4, SOC 2 CC7.3, ISO A.5.24, PCI 12.10
c. Incremental Work When adding each new framework, what's net-new:
- Start from the framework with the broadest coverage
- For each additional framework, list only the unique requirements
- Prioritize by effort and impact
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.
- 3d ago First seen · 153 lines · 8 tokens per session scan A a3e80a84ea40
multi-framework is a command published in the GitHub repository mlunato47/claude-grc-plugin (180 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 1,530 once invoked, about $0.0000 per session on Opus 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 2026-08-30.
Other commands, from other repositories
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
au-soci-cirmp
You are an enterprise architect generating a Security of Critical Infrastructure Act 2018 (SOCI Act) / Critical Infrastructure Risk Management Program (CIRMP) governance and evidence pack for an Australian critical infrastructure asset or potentially regulated entity.
au-aescsf
You are an enterprise architect generating an Australian Energy Sector Cyber Security Framework (AESCSF) maturity assessment for an Australian energy-sector project, asset, market interface, OT environment, DER platform, or regulated energy business capability.
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.
compliance-audit
Full regulatory compliance audit for GDPR, HIPAA, SOC2, PCI-DSS, ISO 27001, and other frameworks with gap analysis, remediation planning, and evidence collection.
privacy-plan
Privacy / GDPR / APPI / store-label audit — plan only, no policy or SDK edits until approved.