ethical-risk-assessment

ethical-risk-assessment is a skill for Claude Code from hollandkevint/data-product-operator. It costs 83 tokens per session (939 once invoked), scanned A, original, MIT.

A framework for checking ethical risks in data and machine-learning products. It examines whether data or models could create unfair outcomes, privacy problems, or unintended harm.

In plain words
What is it for?
Use it to review data sources, test model performance across demographic groups, identify proxy variables, document limitations, and plan safer rollouts.
Why use it?
It makes risks such as biased training data, unequal accuracy between groups, and unclear limitations part of the product process before release.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the data-product-operator plugin — 24 skills, 7 commands, 1 MCP server shipped together

Good fit Use it to review data sources, test model performance across demographic groups, identify proxy variables, document limitations, and plan safer rollouts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hollandkevint/data-product-operator/ethical-risk-assessment
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 hollandkevint/data-product-operator --skill ethical-risk-assessment
Clone the repo
git clone --depth 1 https://github.com/hollandkevint/data-product-operator

Made for: Claude Code.

Or install data-product-operator, the plugin that ships this one along with the rest of its 24 skills, 7 commands, 1 MCP server.

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 ethical-risk-assessment

README.md
[![agentmods](https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/ethical-risk-assessment/github.svg)](https://agentmods.dev/skills/hollandkevint/data-product-operator/ethical-risk-assessment)
Your own site
<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/ethical-risk-assessment"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/ethical-risk-assessment/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 ethical-risk-assessment

Your own site · 80×15
<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/ethical-risk-assessment"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/ethical-risk-assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 939 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 $0.00083 $0.00939
Opus 5 $0.00042 $0.00469
Sonnet 5 $0.00017 $0.00188
Haiku 4.5 $0.00008 $0.00094

Measured 11d ago against content hash 3c80774882c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ethical-risk-assessment 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 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.

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.

skills/ethical-risk-assessment/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Fifth Risk

Standard product risk frameworks cover four risks: value, usability, feasibility, and business viability (see data-product-thinking). Data products add a fifth: ethical data risk.

Ethical data risk asks: Can we build this without bias, privacy violations, or unintended harm?

This risk is owned by the Data Lead, who has veto authority. A technically correct model that produces biased outcomes is worse than no model. This is not optional and not delegated to a compliance review.

Ethics Canvas

Before committing to any ML/AI feature, complete this structured evaluation:

  1. Training data: What are the sources? What biases exist in the collection method? Which populations are overrepresented or underrepresented?
  2. Features used: Which input variables could proxy for protected classes? (ZIP code proxies for race; insurance type proxies for income)
  3. Accuracy by group: Does model performance vary across demographic groups? Test across race, gender, age, and geography at minimum.
  4. Known limitations: What does the model NOT do well? Document before shipping, not after complaints.
  5. Transparency requirements: Can you explain to a user how the model reached its conclusion? If not, the model should not make autonomous decisions.

CRITICAL: Complete the ethics canvas before writing a line of model code. Discovering bias after deployment is 10x more expensive than preventing it.

Bias Testing Protocol

Run bias audits quarterly or before any model update:

  1. Define protected classes for your domain (race, gender, age, geography, insurance status, language)
  2. Split test data by each protected class
  3. Compare model accuracy, false positive rate, and false negative rate across groups
  4. Flag any disparity greater than a defined threshold (e.g., 5% accuracy difference)
  5. If flagged, investigate root cause and apply calibration before production

Real example: A propensity scoring model showed 8% accuracy disparity for Black patients. Root cause was underrepresentation in training data. Calibration layer added before production deployment.

Read the full file on GitHub · 77 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 First seen · 77 lines · 83 tokens per session scan A 3c80774882c8

Subscribe to this mod's changes

ethical-risk-assessment is a skill published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 939 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

feifei-skills

Invoke Fei-Fei Li — Human-Centered AI & Ethics. Use for responsible AI reviews, ethical impact assessments, human oversight design, and fairness analysis. Sets Claude into the Fei-Fei Li persona for the current conversation.

markusbegerow/board-of-directors · 55 tokens

plagiarism-checker

Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.

bitwize-music-studio/claude-ai-music-skills · 35 tokens

ai-ml-governance

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…

cbrock84/headcount · 83 tokens

employment-compliance

Covers the employment rules that carry real penalties — exempt and non-exempt classification, overtime and hours, employee versus contractor status, work authorization and recordkeeping, accommodation requests, and the notices and retention obligations that go with them. Use this to classify a role, review a…

cbrock84/headcount · 87 tokens

tax-ebookkeeping-context

Background information about Japan’s Electronic Bookkeeping Act, which sets rules for storing accounting records, scanned documents, and data received through electronic transactions.

kazukinagata/shinkoku · 75 tokens

prompt-engineer

Use when the user asks to improve, optimize, rewrite, debug, or shorten a prompt, or asks why a prompt is producing bad output. Do NOT use for writing a Claude Code SKILL.md — that needs skill structure rules, not prompt techniques.

aakashg/pm-claude-skills · 55 tokens