BiasCheck

BiasCheck is a skill for Claude Code, Codex from danielmiessler/LifeOS. It costs 109 tokens per session (1,785 once invoked), scanned A, original, MIT.

A three-part review of possible bias in a URL, file, or piece of text, including the underlying data, the source organization, and the reporting around it.

In plain words
What is it for?
It helps fetch a source and any study it cites, then examine data-level bias, organizational interests, and distortions added by journalism.
Why use it?
It separates what evidence supports from conflicts of interest and editorial changes that may influence how the evidence is presented.

Skill for Claude CodeCodex

About the project

LifeOS is an AI-assisted personal operating system that records a person’s goals, values, context, and current situation to help move them toward a desired future state. It supports work such as building applications, starting businesses, and creative projects. Its catalogue entries extend the system through skills, hooks, agents, and commands.

danielmiessler/LifeOS · 18,885 stars · on GitHub

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 skills/danielmiessler/lifeos/biascheck
Any agent
npx skills add danielmiessler/LifeOS --skill biascheck
Clone the repo
git clone --depth 1 https://github.com/danielmiessler/LifeOS

Made for: Claude Code, Codex.

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 BiasCheck

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielmiessler/lifeos/biascheck.svg)](https://agentmods.dev/skills/danielmiessler/lifeos/biascheck)
Your own site
<a href="https://agentmods.dev/skills/danielmiessler/lifeos/biascheck"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/biascheck.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,785 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00109 $0.01785
Opus 5 $0.00055 $0.00892
Sonnet 5 $0.00022 $0.00357
Haiku 4.5 $0.00011 $0.00178

Measured 5d ago against content hash 8d3d4a2f4224, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

BiasCheck 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 5d 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.

curl -s -X POST http://localhost:31337/notify \
LifeOS/install/skills/BiasCheck/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customization

Before executing, check for user customizations at: ~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/BiasCheck/

If this directory exists, load and apply any PREFERENCES.md or additional reference files found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

BiasCheck

Voice Notification

When executing a workflow, do BOTH:

  1. Send voice notification:

    curl -s -X POST http://localhost:31337/notify \
      -H "Content-Type: application/json" \
      -d '{"message": "Running the Check workflow in the BiasCheck skill to audit the source"}' \
      > /dev/null 2>&1 &
    
  2. Output text notification:

    Running the **Check** workflow in the **BiasCheck** skill to audit the source...
    

What It Does

Runs a three-layer bias audit on any source — a URL, a file path, or raw text. It fetches the content plus any study it cites, then checks (1) biases inside the data, (2) conflicts of interest in the source organization, and (3) distortions the journalism added on top. The output separates what the data actually supports from what got editorialized.

The Problem

Most "this is biased" arguments are vibes — a feeling about a source, with nothing concrete underneath. They're not repeatable and they don't tell you where the distortion lives. The other failure is analyzing an article without ever reaching the study it cites, so you critique the headline and never see that the underlying data was fine (or that it was junk). A fixed taxonomy and a fixed output shape fix both: the analysis is repeatable, the gaps are visible, and every claim ties to a specific tell.

How It Works

The skill operates on three layers:

  1. The data itself — biases inside the underlying study, paper, or dataset (funding, sampling, instrument design, demand characteristics, self-report distance from behavior, causal inflation, missing benchmark, publication availability)
  2. The source organization — who paid for or produced the work, what they sell, what conclusion would be inconvenient
  3. The journalism on top — what the reporter/commentator added: headline-to-source distortion, frame escalation, echo-chain amplification, causal claims layered over correlational data

Read the full file on GitHub · 120 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 120 lines · 109 tokens per session scan A 8d3d4a2f4224

Subscribe to this mod's changes

BiasCheck is a skill published in the GitHub repository danielmiessler/LifeOS (18,885 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,785 once invoked, about $0.0005 per session on Opus 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

maaslalani-cli-style

Build CLIs and terminal tools in the style of maaslalani (slides, nap, sheets, gambit, typer, invoice, gum). Use when designing or building a new CLI/TUI tool, restructuring an existing one, or reviewing a terminal tool's UX, layout, keybindings, or README.

Zfinix/aster · 70 tokens

i-have-adhd

Action-first, zero-filler replies for a reader who loses the thread in prose. Use when the user asks for terse or direct answers, says too long, get to the point, tldr, stop rambling, or when replies keep getting cut off or ignored.

Zfinix/aster · 60 tokens

plan-devex-review

Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to…

Global-mindee/WAY · 156 tokens

plan-tune

Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and…

Global-mindee/WAY · 170 tokens

tabw

Use when the user asks to "continue every session", "send this to all windows", "/ar:tabw". Acts on Claude sessions across tmux windows; destructive to in-flight work, so it states what it will do before doing it.

ahundt/autorun · 53 tokens

tabs

Use when the user asks to "list my claude sessions", "which windows are waiting", "/ar:tabs". Discovers Claude sessions across tmux windows and reports which need attention.

ahundt/autorun · 40 tokens