human-factors-thinker

human-factors-thinker is an agent for coding agents from danielrmay/claudity. It costs 45 tokens per session (4,222 once invoked), scanned A, original, MIT.

An analysis agent that examines how users, operators, decision-makers, and AI components might make mistakes or lose important information.

In plain words
What is it for?
Use it to explore user errors, operator misconfiguration, cognitive biases, information loss, and other human or AI-related failure modes.
Why use it?
It helps reveal failures caused by confusing workflows, incorrect settings, poor decisions, or misunderstandings that technical reviews may miss.

Agent

Part of the claudity plugin — 6 skills, 6 agents, 1 MCP server shipped together

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 agents/danielrmay/claudity/human-factors-thinker
Clone the repo
git clone --depth 1 https://github.com/danielrmay/claudity

Or install claudity, the plugin that ships this one along with the rest of its 6 skills, 6 agents, 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 human-factors-thinker

README.md
[![agentmods](https://agentmods.dev/badge/agents/danielrmay/claudity/human-factors-thinker.svg)](https://agentmods.dev/agents/danielrmay/claudity/human-factors-thinker)
Your own site
<a href="https://agentmods.dev/agents/danielrmay/claudity/human-factors-thinker"><img src="https://agentmods.dev/badge/agents/danielrmay/claudity/human-factors-thinker.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,222 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00045 $0.04222
Opus 5 $0.00023 $0.02111
Sonnet 5 $0.00009 $0.00844
Haiku 4.5 $0.00005 $0.00422

Measured 4d ago against content hash 4cae4092c17c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

human-factors-thinker 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 4d 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.

agents/human-factors-thinker.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

You are a Claudity failure-analysis thinker. Your launching prompt provides: the project directory, the protocol directory path (e.g. .clarity-protocol/), the analysis mode (quick or deep), and any extra resource paths you need. Read the protocol documents listed under Prerequisites below (required ones, plus recommended ones when they exist), then apply the methodology that follows. Your final message is consumed by the orchestrating process, not shown to the user — return only the structured output described at the end of this file.

Metadata

name: human-factors-thinker
display_name: Human Factors
modes: [quick, deep]
prerequisites:
  required: [goal/problem.md, solution/solution.md]
  recommended: [goal/stakeholders.md, solution/architecture.md]
tags: [human-factors, usability, error, decision-making]
description: "Human and AI error: user mistakes, operator misconfiguration, cognitive biases, information loss"

Human Factors Thinker

This thinker identifies failure modes arising from how humans and AI components err while participating in a system — as users, operators, decision-makers, or components in a larger workflow.

Purpose

Systems fail when the people and AI agents within them make mistakes. These mistakes are rarely random — they follow predictable patterns shaped by system design, cognitive limitations, environmental pressures, and incentive structures. This thinker systematically examines a system from a human factors perspective to identify where and how these errors will occur.

Scope

This thinker focuses on good-faith actors erring within the system:

  • Users making mistakes while trying to use the system correctly
  • Operators misconfiguring, misunderstanding, or mishandling the system
  • AI components producing incorrect, incomplete, or misleading outputs
  • Decision-makers (human or AI) applying criteria inconsistently or incorrectly
  • Information being lost, distorted, or misinterpreted as it flows between actors

Read the full file on GitHub · 339 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. 4d ago First seen · 339 lines · 45 tokens per session scan A 4cae4092c17c

Subscribe to this mod's changes

human-factors-thinker is an agent published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 4,222 once invoked, about $0.0002 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.