orca-custom-framework

orca-custom-framework is a skill for Claude Code from orcasecurity/orca-skills. It costs 65 tokens per session (4,217 once invoked), scanned A, original, MIT.

A tool for building a compliance checklist tailored to an organization's security topic, existing framework, or selected alerts. A compliance framework is a structured set of security requirements used for review.

In plain words
What is it for?
Use it to create frameworks for topics such as supply-chain security, combine controls from existing frameworks, or organize selected failing alerts into review sections.
Why use it?
It organizes scattered requirements and alerts into one framework and highlights gaps that existing rules do not cover.

Skill for Claude Code

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

Part of the orca-skills plugin — 20 skills, 1 plugin shipped together

Good fit Use it to create frameworks for topics such as supply-chain security, combine controls from existing frameworks, or organize selected failing alerts into review sections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcasecurity/orca-skills/orca-custom-framework
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 orcasecurity/orca-skills --skill orca-custom-framework
Clone the repo
git clone --depth 1 https://github.com/orcasecurity/orca-skills

Made for: Claude Code.

Or install orca-skills, the plugin that ships this one along with the rest of its 20 skills, 1 plugin.

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 orca-custom-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-custom-framework/github.svg)](https://agentmods.dev/skills/orcasecurity/orca-skills/orca-custom-framework)
Your own site
<a href="https://agentmods.dev/skills/orcasecurity/orca-skills/orca-custom-framework"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-custom-framework/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 orca-custom-framework

Your own site · 80×15
<a href="https://agentmods.dev/skills/orcasecurity/orca-skills/orca-custom-framework"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-custom-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 152
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Data Exfiltration · line 55
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 193
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 193
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00065 $0.04217
Opus 5.5 $0.00026 $0.01687
Sonnet 5.5 $0.00013 $0.00843
Haiku 4.5 $0.00006 $0.00422

Measured 11d ago against content hash e12143f11e43, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

orca-custom-framework scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

### Phase 3: Create (Orca REST API — via curl)
skills/orca-custom-framework/SKILL.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orca Custom Framework Skill

Answers the question: "How do I create a custom compliance framework tailored to my organization's specific security requirements?"

Given a source (existing framework, list of alert IDs, or a security theme), this skill gathers relevant controls and alerts, organizes them into a structured custom compliance framework with logical sections, and creates it in Orca Security. When gaps exist — controls the user wants but Orca doesn't have a built-in rule for — the skill suggests creating custom discovery alerts to fill them.

Usage

/orca-custom-framework Supply Chain Security Controls
/orca-custom-framework from:cis_docker_v.1.3.1
/orca-custom-framework alerts:orca-1234,orca-5678,orca-9012
/orca-custom-framework "Zero Trust Architecture"

Or natural language:

  • "create a custom compliance framework for supply chain security"
  • "build a framework based on CIS Docker + EKS controls"
  • "generate a custom framework from these alerts: orca-1234, orca-5678"
  • "create a supply chain security framework"
  • "build custom compliance from our failing container controls"

How It Works

The skill operates in three phases, using different tools at each stage:

Phase 1: Read (Orca MCP tools — read-only)

Queries the Orca environment to gather existing controls and alerts:

  • get_enabled_compliance_frameworks — lists all frameworks and their IDs
  • get_compliance_framework_control_tests — pulls controls from relevant source frameworks, each containing a rule_id
  • discovery_search — finds alerts matching the theme (e.g., "container registry", "image scanning")
  • get_alert — gets full alert details when working from alert IDs

These are read-only MCP queries. They provide the rule_id values needed for the framework.

Phase 2: Organize (assistant logic — no API calls)

Groups the gathered rule_id values into logical sections based on alert categories, asset types, and the requested theme. Assigns priority weights (high/medium/low) and dotted-notation IDs (e.g., 1.1, 2.3).

Read the full file on GitHub · 433 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. 11d ago Changed e12143f11e43
  2. 1mo ago First seen · 433 lines · 65 tokens per session scan A 2bb0d96984b2

Subscribe to this mod's changes

orca-custom-framework is a skill published in the GitHub repository orcasecurity/orca-skills (56 stars, last pushed 11d ago), licensed MIT. It adds 65 tokens to every session and 4,217 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

2026-legal-research-agent

This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.

majiayu000/claude-skill-registry · 0 tokens

hr-payroll

Help HR operations specialists, payroll administrators, and compensation teams understand, design, and run payroll processing, compliance, and payroll-related HR operations. Use when asked to set up a payroll process, run a payroll compliance audit, design a payroll calendar, handle a payroll discrepancy, build a…

tuanductran/hr-skills · 88 tokens

hr-vietnam-context

Vietnam-specific HR guidance covering Labor Code 2019 compliance, Social Insurance (SI/HI/UI) enrollment, PIT registration, work permit and visa management for foreign employees, 2% trade union contributions, and Vietnamese workplace culture. Use when setting up employment contracts, handling labor discipline or…

tuanductran/hr-skills · 77 tokens

hr-agentic-ai

Help HR leaders, HR technology teams, and People Ops professionals understand, evaluate, and govern agentic AI systems deployed in HR contexts, including autonomous HR agents, multi-agent workflows, and AI-driven HR process automation. Use when asked to use AI agents for HR, build an HR automation agent, govern…

tuanductran/hr-skills · 85 tokens

hr-ai-ethics

Help HR and compliance teams govern the ethical use of AI in HR processes, including algorithmic fairness in hiring, bias auditing, AI transparency, accountability frameworks, and ethical AI policy design. Use when asked to audit AI bias in hiring, design ethical AI guidelines for HR, assess algorithmic fairness…

tuanductran/hr-skills · 86 tokens

hr-ai-privacy

Help HR and compliance teams protect employee data privacy in AI-driven HR systems, including GDPR compliance, data minimization, employee consent design, and privacy risk assessment for HR AI tools. Use when asked to protect employee data in AI systems, design HR AI privacy policies, assess privacy risks of AI tools…

tuanductran/hr-skills · 84 tokens