ux-fix

ux-fix is a command for coding agents from Laith0003/ux-skill. It costs 129 tokens per session (3,544 once invoked), scanned A, original, MIT.

A command that applies fixes listed in the latest user-experience report stored in the project’s .ux/ folder, then checks the result again.

In plain words
What is it for?
Use it after a UX, copy, accessibility, motion, or polish review when you want those findings applied. You can choose a report, include cosmetic issues, or limit the number of fixes.
Why use it?
It removes the manual work of turning audit findings into code changes while keeping each fix separately recorded. It also prevents running without a report to guide the changes.

Command

Part of the ux-skill plugin — 25 commands, 5 agents 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/laith0003/ux-skill/ux-fix
Clone the repo
git clone --depth 1 https://github.com/Laith0003/ux-skill

Or install ux-skill, the plugin that ships this one along with the rest of its 25 commands, 5 agents.

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 ux-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-fix.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-fix)
Your own site
<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-fix"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,544 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 $0.00129 $0.03544
Opus 5 $0.00064 $0.01772
Sonnet 5 $0.00026 $0.00709
Haiku 4.5 $0.00013 $0.00354

Measured 5d ago against content hash df03774e3aca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-fix 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/ux-fix.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-fix

You are running the /ux-fix command from the ux plugin. The job is to take a report already produced by another ux-* command, apply its findings as atomic commits via the right sub-agents, and re-verify by re-running the originating command.

When to use

Triggers: "fix the findings", "apply the fixes", "run the fix loop", "patch the surface", "make the changes", "go fix it".

Use after running /ux-audit, /ux-copy, /ux-a11y, /ux-motion, or /ux-polish and reviewing the findings. The user has decided to act; this command is the act.

Do not use without an existing report. If .ux/ has no last-*.json file, return an error and direct the user to run an audit command first.

Input

Optional: which report to act on (--from audit | copy | a11y | motion | polish). If unspecified, auto-detect by reading every .ux/last-*.json file and picking the most recent timestamp.

Optional: --include-cosmetic to include Cosmetic-severity findings (default skips them).

Optional: --max <n> to cap the number of fixes per run (default: all eligible findings).

Process

1. Locate the source report

If --from is set, read .ux/last-<name>.json directly.

If not, list every .ux/last-*.json, parse timestamps, pick the most recent. Surface to the user which report is being acted on:

Acting on .ux/last-<name>.json (timestamp: <ISO>)
<n> findings — <Critical>/<High>/<Medium>/<Cosmetic>

If the latest report is older than 24 hours, warn the user — the surface may have changed since the report was generated. Ask for confirmation to proceed, or recommend re-running the originating command first.

2. Validate clean working tree

Run git status --short. If the tree is dirty:

  1. Show the user what is dirty.
  2. Offer three options:
    • Commit — let the user commit the existing changes first before starting the fix loop.
    • Stashgit stash push -m "ux-fix pre-loop stash" and proceed; restore at the end.
    • Abort — exit without applying any fixes.
  3. Wait for the user's choice. Do NOT proceed silently with a dirty tree.

Read the full file on GitHub · 310 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 · 310 lines · 129 tokens per session scan A df03774e3aca

Subscribe to this mod's changes

ux-fix is a command published in the GitHub repository Laith0003/ux-skill (66 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 3,544 once invoked, about $0.0006 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 2026-08-30.