oscal-profile

oscal-profile is a skill for Claude Code from metaschema-framework/claude-plugins. It costs 24 tokens per session (1,942 once invoked), scanned A, original, CC0-1.0.

A security-baseline document that selects and adjusts controls from one or more OSCAL catalogs or profiles. OSCAL is a standard format for exchanging cybersecurity and compliance information.

In plain words
What is it for?
Use it to create baselines such as FedRAMP or CMMC levels and to organize the controls a system must implement.
Why use it?
It keeps the exact security requirements for a system in one reusable baseline, including selected controls, changed settings, and extra guidance.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the oscal plugin — 9 skills shipped together

Good fit Use it to create baselines such as FedRAMP or CMMC levels and to organize the controls a system must implement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metaschema-framework/claude-plugins/oscal-profile
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.

Any agent
npx skills add metaschema-framework/claude-plugins --skill oscal-profile
Clone the repo
git clone --depth 1 https://github.com/metaschema-framework/claude-plugins

Made for: Claude Code.

Or install oscal, the plugin that ships this one along with the rest of its 9 skills.

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-profile

README.md
[![agentmods](https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/oscal-profile/github.svg)](https://agentmods.dev/skills/metaschema-framework/claude-plugins/oscal-profile)
Your own site
<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/oscal-profile"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/oscal-profile/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for oscal-profile

Your own site · 80×15
<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/oscal-profile"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/oscal-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00024 $0.01942
Opus 5.5 $0.00010 $0.00777
Sonnet 5.5 $0.00005 $0.00388
Haiku 4.5 $0.00002 $0.00194

Measured 2mo ago against content hash 4ae9f726cc4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oscal-profile 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 2mo 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.

plugins/oscal/skills/oscal-profile/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OSCAL Profile Model

The Profile model enables selecting, organizing, and tailoring controls from catalogs to create security baselines. Profiles can import from catalogs or other profiles.

Related skills:

  • oscal-catalog - Control definitions that profiles select from
  • oscal-ssp - System Security Plans that implement profile baselines

Purpose

A profile:

  • Selects specific controls from source catalogs
  • Tailors controls by modifying parameters, adding constraints, or supplementing guidance
  • Organizes controls into custom groupings
  • Creates baselines like FedRAMP Low/Moderate/High

Common Profiles

Profile Based On Description
FedRAMP Low NIST 800-53 Low-impact cloud systems
FedRAMP Moderate NIST 800-53 Moderate-impact cloud systems
FedRAMP High NIST 800-53 High-impact cloud systems
CMMC Level 2 NIST 800-171 Contractor cybersecurity maturity

Document Structure

profile:
  uuid: <unique-identifier>
  metadata:
    title: "Baseline Profile"
    version: "1.0.0"
    oscal-version: "1.1.2"
  imports:          # Source catalogs/profiles
    - href: "catalog.json"
      include-controls:
        - with-ids:
            - ac-1
            - ac-2
  merge:            # How to combine imports
    combine:
      method: merge
    as-is: true
  modify:           # Tailoring modifications
    set-parameters: []
    alters: []
  back-matter:
    resources: []

Imports

Importing from Catalogs

imports:
  - href: "https://example.com/oscal/nist-800-53-catalog.json"
    include-controls:
      - with-ids:
          - ac-1
          - ac-2
          - ac-3

Importing from Other Profiles

imports:
  - href: "fedramp-moderate-baseline.json"
    include-controls:
      - with-ids:
          - ac-1

Include/Exclude Patterns

Include all controls:

imports:
  - href: "catalog.json"
    include-all: {}

Include by matching:

imports:
  - href: "catalog.json"
    include-controls:
      - matching:
          - pattern: "ac-*"    # All access control
          - pattern: "sc-*"    # All system/comms protection

Read the full file on GitHub · 288 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. 2mo ago First seen · 288 lines · 24 tokens per session scan A 4ae9f726cc4f

Subscribe to this mod's changes

oscal-profile is a skill published in the GitHub repository metaschema-framework/claude-plugins (10 stars, last pushed 8mo ago), licensed CC0-1.0. It adds 24 tokens to every session and 1,942 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Related

oscal-profile compared with skills from other repositories

oscal-profile next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
oscal-profilemetaschema-framework/claude-pluginsSkill108mo agoCC0-1.0A24Claude Code
fto-triageanthropics/claude-for-legalSkill10.0kyesterdayApache-2.0A81Claude Code
legal-holdanthropics/claude-for-legalSkill10.0kyesterdayApache-2.0A68Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA49Claude Code
regulatory-research-fallbackHKUDS/OpenSpaceSkill7.9k3d agoMITA20Claude Code, Codex
terms-of-servicegenspark-ai/genofficeSkill12kyesterdayApache-2.0A32Claude Code, Codex
x-scorecardx-cmd/x-cmdSkill4.7k10d agoApache-2.0A57Claude Code, Codex