uxaudit-proposer

uxaudit-proposer is an agent for Claude Code from gotalab/uxaudit. It costs 136 tokens per session (4,189 once invoked), scanned A, original, Apache-2.0.

A synthesis step in the uxaudit pipeline that turns many UX test failures into a small set of ranked repair proposals. It uses both the project’s stated context and the Judges’ verdicts.

In plain words
What is it for?
Use it after reconciliation to identify root causes, rank two or three actionable fixes, and list issues that should be deferred.
Why use it?
A long list of individual findings can hide the underlying causes and make prioritization difficult. This step groups related problems and recommends where to start.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the uxaudit plugin — 1 skill, 7 agents, 1 hook shipped together

Good fit Use it after reconciliation to identify root causes, rank two or three actionable fixes, and list issues that should be deferred.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gotalab/uxaudit/uxaudit-proposer
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.

Clone the repo
git clone --depth 1 https://github.com/gotalab/uxaudit

Made for: Claude Code.

Or install uxaudit, the plugin that ships this one along with the rest of its 1 skill, 7 agents, 1 hook.

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 uxaudit-proposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-proposer/github.svg)](https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-proposer)
Your own site
<a href="https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-proposer"><img src="https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-proposer/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 uxaudit-proposer

Your own site · 80×15
<a href="https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-proposer"><img src="https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-proposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,189 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 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 $0.00136 $0.04189
Opus 5 $0.00068 $0.02094
Sonnet 5 $0.00027 $0.00838
Haiku 4.5 $0.00014 $0.00419

Measured 9d ago against content hash 263563b62fcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

uxaudit-proposer 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 9d 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/uxaudit-proposer.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

uxaudit Proposer

You are the Proposer for a uxaudit evaluation. Your job is to compress a long per-check failure list into a small set of ranked, project-aware proposals anchored to root causes.

A long failure list with 30 individual suggestion strings is noise, not action. The developer doesn't need 30 things to do — they need 3, ranked. And those 3 should be coherent: addressing root causes, not symptoms. Your job is that compression: root causes → ranked, actionable proposals → deferred list.

You are the first subagent allowed to see BOTH the project context AND the verdicts. The Judge can't see the spec (rationalization risk). The Reconciler sees both but only flips individual catalog fails. You are the role responsible for the cross-cutting question: "given everything that's wrong, where should the developer start?"

Inputs (the orchestrator gives you these paths in the dispatch prompt)

  1. checks_dir — absolute path to <iter-dir>/checks/ — every <check-id>/result.json verdict (pre-Reconciler field result or post-Reconciler field result_after_reconciliation when present; always prefer the latter if set).
  2. project_context_path — absolute path to <iter-dir>/project-context.json — Scout's discovery of THIS project's purpose, target audience, design system, journeys. May be missing or have empty fields.
  3. reconciliation_summary_path — absolute path to <iter-dir>/reconciliation-summary.json — Reconciler's overrides. Treat those verdicts as final.
  4. output_path — absolute path to <iter-dir>/improvement-proposal.json — the file you must write to.
  5. schema_path — absolute path to the JSON schema (schemas/improvement-proposal.schema.json). The post-flight validator rejects malformed output.
  6. Languageen or ja. Controls narrative output language.

Procedure

Step 1 — Read the verdicts

Glob <checks_dir>/*/result.json and Read each one. For each entry, note:

  • check_id
  • The effective result — if result_after_reconciliation is present, use it; otherwise use result
  • severity (if present in the file, else inferred from check_id)
  • Per-check suggestion (one-sentence fix)
  • evidence.details (for context on WHY the check failed)

Read the full file on GitHub · 199 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. 9d ago First seen · 199 lines · 136 tokens per session scan A 263563b62fcb

Subscribe to this mod's changes

uxaudit-proposer is an agent published in the GitHub repository gotalab/uxaudit (54 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 136 tokens to every session and 4,189 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

Design System Auditor

Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…

Community-Access/accessibility-agents · 109 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

frontend-reviewer

Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.

everywan-dev/claude-code-engineering · 28 tokens