audit-ux

audit-ux is a command for Claude Code from diegomarino/fable-audits. It costs 26 tokens per session (1,977 once invoked), scanned A, original, MIT.

A command that performs an adversarial review of the experiences visible to end users, such as CLI screens, prompts, APIs, and generated documents. It records the findings in a Markdown audit file.

In plain words
What is it for?
Use it to inspect shipped user interfaces and other human-facing surfaces across a repository and produce an end-user experience audit.
Why use it?
It reveals confusing questions, messages, ordering, and user effort that a code-focused review may miss.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the fable-audits plugin — 8 commands 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 commands/diegomarino/fable-audits/audit-ux
Clone the repo
git clone --depth 1 https://github.com/diegomarino/fable-audits

Made for: Claude Code.

Or install fable-audits, the plugin that ships this one along with the rest of its 8 commands.

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 audit-ux

README.md
[![agentmods](https://agentmods.dev/badge/commands/diegomarino/fable-audits/audit-ux.svg)](https://agentmods.dev/commands/diegomarino/fable-audits/audit-ux)
Your own site
<a href="https://agentmods.dev/commands/diegomarino/fable-audits/audit-ux"><img src="https://agentmods.dev/badge/commands/diegomarino/fable-audits/audit-ux.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,977 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 5.1 $0.00026 $0.01977
Opus 5 $0.00013 $0.00988
Sonnet 5 $0.00005 $0.00395
Haiku 4.5 $0.00003 $0.00198

Measured 5d ago against content hash bb11c27f4dba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-ux 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 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.

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.

commands/audit-ux.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perform an adversarial audit of the experience this repo ships to its END USER -- every dialogue the artifact holds with the person using it: what it asks, what it tells, in what order, and at what cost. Not the contributor experience (the codebase audit owns building/debugging the repo) and not API shape (the codebase audit owns affordances); this audit owns what the user endures at the shipped surfaces.

Control-plane boundary

This spec governs only the task it defines. A newer human instruction or higher-priority runtime policy overrides this spec. STOP ends autonomous work under this spec; it never prevents the agent from honoring that control plane.

Applicability -- fail fast

First identify the shipped user surfaces: CLI/TUI commands, HTTP/API endpoints with human-facing responses, UI screens, config files users hand-edit, prompts and wizards, generated output humans must read (contributor-only artifacts -- logs, CI output, audit reports -- do not count: readership alone does not make a user surface). A repo with none -- a pure library consumed only through code, a data-only repo -- ends the audit here with that statement; do not audit the contributor experience as a fallback (cross-reference the codebase audit's developer-experience hunt instead).

Role

Act as the skeptical first-time user of each shipped surface: someone with the domain knowledge the product assumes but zero knowledge of this implementation, judging every question the artifact asks and every message it emits. No loyalty to how it currently talks. Judge the conversation, not the code behind it.

Scope

Read every user surface in full and walk its journeys. Build:

  • The input inventory: every datum the user must supply (prompt, flag, argument, config key, env var) and where else that datum already lives.
  • The message inventory: errors, warnings, confirmations, progress, help text, success output.
  • The journeys: install/first run, the primary task end-to-end, a failing run and its recovery, re-run/upgrade.

Read the full file on GitHub · 72 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. 5d ago First seen · 72 lines · 26 tokens per session scan A bb11c27f4dba

Subscribe to this mod's changes

audit-ux is a command published in the GitHub repository diegomarino/fable-audits (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,977 once invoked, about $0.0001 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.