oscal-guide

oscal-guide is a command for coding agents from mlunato47/claude-grc-plugin. It costs 9 tokens per session (970 once invoked), scanned A, original, MIT.

A guide to OSCAL, a standard format for describing security and compliance information in machine-readable files. It covers models such as system security plans, component definitions, parameters, inheritance, tools, and validation.

In plain words
What is it for?
Use it to learn OSCAL structure, assess readiness for converting a system security plan, understand components and parameters, follow inherited authorisations, and choose validation approaches.
Why use it?
It helps teams understand how existing security documentation can be structured for OSCAL and identify what may need changing before conversion. It also provides topic-specific guidance instead of requiring familiarity with the standard.

Command

Part of the grc plugin — 1 skill, 24 commands, 1 agent shipped together

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 commands/mlunato47/claude-grc-plugin/oscal-guide
Clone the repo
git clone --depth 1 https://github.com/mlunato47/claude-grc-plugin

Or install grc, the plugin that ships this one along with the rest of its 1 skill, 24 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for oscal-guide

README.md
[![agentmods](https://agentmods.dev/badge/commands/mlunato47/claude-grc-plugin/oscal-guide.svg)](https://agentmods.dev/commands/mlunato47/claude-grc-plugin/oscal-guide)
Your own site
<a href="https://agentmods.dev/commands/mlunato47/claude-grc-plugin/oscal-guide"><img src="https://agentmods.dev/badge/commands/mlunato47/claude-grc-plugin/oscal-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 5.1 $0.00009 $0.00970
Opus 5 $0.00005 $0.00485
Sonnet 5 $0.00002 $0.00194
Haiku 4.5 $0.00001 $0.00097

Measured 6d ago against content hash 06487d282cf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

oscal-guide 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

grc/commands/oscal-guide.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/grc:oscal-guide

Provide OSCAL guidance — structure, readiness assessment, and conversion considerations.

Usage

/grc:oscal-guide [topic]

Arguments

  • topic: The OSCAL topic to address. Accepts:
    • overview (default): What OSCAL is, models, and architecture
    • ssp: OSCAL SSP model structure and components
    • readiness: Assess whether your current SSP is ready for OSCAL conversion
    • components: How OSCAL component definitions work
    • parameters: How OSCAL handles ODPs/parameters
    • inheritance: How OSCAL models leveraged authorizations and inheritance
    • tools: OSCAL tooling ecosystem
    • validation: OSCAL validation approaches

Examples

/grc:oscal-guide
/grc:oscal-guide overview
/grc:oscal-guide ssp
/grc:oscal-guide readiness
/grc:oscal-guide components
/grc:oscal-guide tools

Behavior

When invoked:

  1. No redaction reminder needed for most topics — OSCAL guidance is reference material. If the user pastes their SSP content for readiness assessment, display the Data Sensitivity Notice.

  2. Read the appropriate reference files:

    • skills/grc-knowledge/frameworks/oscal-reference.md for OSCAL structure and concepts
    • skills/grc-knowledge/audits/document-section-requirements.md for SSP section requirements (for readiness topic)
    • skills/grc-knowledge/oscal/nist-800-53-rev5/{family}.json and skills/grc-knowledge/oscal/fedramp-moderate-rev5/{family}.json for live OSCAL data examples — when showing structure examples, read a real family file (e.g., at.json for a small example) instead of fabricating sample JSON
  3. For each topic:

    overview: Present OSCAL models, layer architecture, current status, and FedRAMP OSCAL requirements. Explain why OSCAL matters and how it changes the GRC workflow.

    ssp: Deep dive into the OSCAL SSP model — metadata, system characteristics, system implementation, control implementation, back matter. Show the structure with examples.

    readiness: If the user provides SSP details, assess readiness for OSCAL conversion:

    • Are control narratives structured by component?
    • Are ODPs separated from prose?
    • Are roles consistently named?
    • Is inventory itemized?
    • Are diagrams separate, linkable files?
    • Score readiness and list conversion prerequisites.

Read the full file on GitHub · 106 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. 6d ago First seen · 106 lines · 9 tokens per session scan A 06487d282cf4

Subscribe to this mod's changes

oscal-guide is a command published in the GitHub repository mlunato47/claude-grc-plugin (181 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 970 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.