ai-bias-audit

ai-bias-audit is a skill for Claude Code from komunite/kalfa. It costs 17 tokens per session (1,401 once invoked), scanned A, a copy of agent-evaluation, MIT.

A structured process for examining whether an AI system treats people or groups unfairly. An AI bias audit looks for unequal or distorted outcomes in an AI system.

In plain words
What is it for?
Use it to review existing audit documents, identify requirements and stakeholders, and produce a checked AI bias-audit analysis.
Why use it?
It helps organize an assessment of possible bias instead of relying on an informal review.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review existing audit documents, identify requirements and stakeholders, and produce a checked AI bias-audit analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/komunite/kalfa/ai-bias-audit
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 komunite/kalfa --skill ai-bias-audit
Clone the repo
git clone --depth 1 https://github.com/komunite/kalfa

Made for: Claude Code.

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 ai-bias-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/komunite/kalfa/ai-bias-audit/github.svg)](https://agentmods.dev/skills/komunite/kalfa/ai-bias-audit)
Your own site
<a href="https://agentmods.dev/skills/komunite/kalfa/ai-bias-audit"><img src="https://agentmods.dev/badge/skills/komunite/kalfa/ai-bias-audit/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 ai-bias-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/komunite/kalfa/ai-bias-audit"><img src="https://agentmods.dev/badge/skills/komunite/kalfa/ai-bias-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,401 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 83% copy Near-identical to another mod 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 $0.00017 $0.01401
Opus 5 $0.00009 $0.00700
Sonnet 5 $0.00003 $0.00280
Haiku 4.5 $0.00002 $0.00140

Measured 11d ago against content hash 49d25289079a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-bias-audit 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.

Origin

This is a copy

83% identical to agent-evaluation — 54 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/ai-automation/ai-bias-audit/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ai Bias Audit

Amaç

Eyleme dönüştürülebilir, ölçülebilir sonuçlar sunan kapsamlı bir ai bias audit analiz edin ve üretin. Bu beceri, her seferinde profesyonel düzeyde çıktı sağlayan, kalite doğrulamalı yapılandırılmış bir süreç sunar.

Kategori: Yapay Zeka ve Otomasyon

Girdiler

Zorunlu

  • Hedef: Bu çıktı ile neyi başarmak istiyorsunuz
  • Bağlam: İlgili arka plan bilgileri

İsteğe Bağlı

  • Kısıtlamalar: Dikkate alınması gereken sınırlamalar veya gereksinimler
  • Mevcut Çalışma: Üzerine inşa edilecek önceki belgeler veya veriler

Sistem Bağlamı

Başlamadan önce:

  • Mevcut proje bağlamı ve öncelikleri için memory.md'yi oku
  • İlgili öğrenilmiş kurallar veya kısıtlamalar için knowledge-base.md'yi kontrol et
  • Projedeki mevcut ilgili belgeleri gözden geçir
  • Bu çıktı ile ilgili .claude/workspace/TaskBoard.md'deki aktif görevleri not et

Süreç

Adım 1: Bağlam ve Araştırma

  • Projedeki mevcut ai bias audit belgelerini gözden geçir
  • İlgili öğrenilmiş kurallar veya kısıtlamalar için knowledge-base.md'yi kontrol et
  • Mevcut proje bağlamı ve öncelikleri için memory.md'yi kontrol et
  • Kilit paydaşları ve gereksinimlerini belirle
  • En uygun çerçeveyi seç: AI Readiness Assessment, Automation ROI Calculator, Human-in-the-Loop Design

Adım 2: Analiz ve Çerçeve Uygulaması

  • ai bias audit yapılandırmak için seçilen çerçeveyi uygula
  • Boşlukları, fırsatları ve riskleri belirle
  • Başarı metriklerini tanımla: Time Saved Per Task, Automation Rate, Error Reduction %, Cost Per AI Operation
  • Varsayımları ve bağımlılıkları belgele
  • Yaklaşımı sektör en iyi uygulamalarına göre doğrula

Adım 3: Çıktıyı Oluştur

  • ai bias audit aşağıdaki çıktı formatını kullanarak yapılandır
  • Genel tavsiyeler değil, spesifik ve eyleme dönüştürülebilir öneriler ekle
  • Uygulanabilir yerlerde somut rakamlar, zaman çizelgeleri ve kıyaslamalar ekle
  • Tutarlılık için mevcut proje belgeleriyle çapraz referans yap
  • Her bölümün değer kattığından emin ol — dolgu içeriği çıkar

Read the full file on GitHub · 133 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 · 133 lines · 17 tokens per session scan A 49d25289079a

Subscribe to this mod's changes

ai-bias-audit is a skill published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,401 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to agent-evaluation, differing in 54 lines, and is treated as a copy.

Related

Other skills, from other repositories

play-policy-insights

Automated auditor designed to verify Android applications against Google Play Policy domains. It cross-references static code analysis with Play Store declarations to generate deterministic compliance reports, identifying undeclared data collection, architectural risks, and missing disclosures across Permissions and…

android/skills · 66 tokens

commissaire-aux-comptes

Commissaire aux comptes IA pour l'audit des comptes annuels d'entreprises françaises. Applique la démarche NEP en 7 phases : prise de connaissance, contrôle du FEC, vérification du bilan, du compte de résultat, de la balance, de la liasse fiscale, et contrôles transversaux. Émet une opinion motivée sur la fiabilité…

romainsimon/paperasse · 123 tokens

2026-legal-research-agent

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic…

majiayu000/claude-skill-registry · 103 tokens

crisis-holding

Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).

elvisun/newsjack · 67 tokens

patent-write

A Chinese-language patent-writing skill for turning a technical proposal, draft, or reference patent into invention-patent documents. It covers sections such as the title, abstract, background, claims, figures, and implementation details.

xstongxue/best-skills · 95 tokens

eu-ai-act-reviewer

Review user journeys, public content, and codebases for potentially relevant EU AI Act provisions, with exact official citations, evidence gaps, application dates, and plain-language next actions. Use for EU AI Act issue-spotting, not final legal or compliance decisions.

bencium/bencium-marketplace · 58 tokens