A pre-launch user-experience audit that reviews specified feature areas using personas, browser tests, and an HTML report. A persona is a representative type of user; the audit does not infer its scope by scanning the project.

It helps assess feature areas before launch, test them in a browser, compare them across personas, and produce a report of findings.

It prevents an audit from silently covering the wrong features and separates findings from permission to change the application.

ux-audit — Skill for Claude Code by nikolamin/claude-coordinator-kit

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.

Any agent

npx skills add nikolamin/claude-coordinator-kit --skill ux-audit

Clone the repo

git clone --depth 1 https://github.com/nikolamin/claude-coordinator-kit

Made for: Claude Code.

Or install coordinator-kit, the plugin that ships this one along with the rest of its 15 skills, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/ux-audit/github.svg)](https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/ux-audit)

Your own site

<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/ux-audit"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/ux-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/ux-audit"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/ux-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,895 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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.01895
Opus 5.5	$0.00025	$0.00758
Sonnet 5.5	$0.00013	$0.00379
Haiku 4.5	$0.00006	$0.00189

Measured 1mo ago against content hash 00704548a0d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ux-audit 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 1mo 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.

plugins/coordinator-kit/skills/ux-audit/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-launch UX audit

First response gate: if the invocation/current request supplies no clear feature scope, ask which feature areas to cover and stop the turn. Reading this skill is sufficient for that response. Do not batch loading it with project commands or discovery; do not inspect the working directory to infer scope. Read the runtime adapter and follow the remaining stages only after scope is supplied. An empty invocation never means "everything".

In Codex, invoke this skill with $ux-audit; in Claude Code use /coordinator-kit:ux-audit. Follow the runtime adapter.

Coordinate the five-stage workflow below for the current project. This is an audit of a pre-launch product with derived personas, not observed user research. Create audit artifacts; application changes and implementation of recommendations need their own authorization.

Scope and saved progress

Use the explicit scope supplied with this invocation or in the user's current request, preserving its exact wording. If absent or ambiguous, immediately ask: "Which feature areas should this audit cover? You can name specific areas or say 'everything'." Then wait for the answer before inspecting the project, initializing records or dispatching. Do not substitute "everything" for an empty argument or stop at promising to ask later.
Run coordinator-kit:bootstrap's database ensure/reconciliation as needed. Honor existing holds and guardrails. Create or resume one canonical audit task with the source request, scope, acceptance criteria, stage, artifact paths and run ledger. A repeat invocation is not permission to duplicate an active fleet; check its agents and saved progress first.
Allocate a unique .coordinator-scratch/ux-audit/<audit-id>/ directory. Give each agent its own report path. Keep scope/count approvals and execution status in database records and events, with links to these artifacts; the reports are evidence, not another backlog. On retry, preserve every previous report and evidence file; allocate a new attempt id and path and append its result to the run ledger instead of overwriting the previous attempt. Preserve the final HTML and evidence under docs/validation/ux-audit/<audit-id>/ or the project's recorded deliverable directory, and record that location in the audit task.

Read the full file on GitHub · 139 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.

1mo ago First seen · 139 lines · 63 tokens per session scan A 00704548a0d5

Subscribe to this mod's changes

ux-audit is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 29d ago), licensed MIT. It adds 63 tokens to every session and 1,895 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-26.

Browser automation Design and UX

ux-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ux-auditnikolamin/claude-coordinator-kit	Skill	2	29d ago	MIT	A	63	Claude Code
add-vector-iconchromium/chromium	Skill	25k	today	BSD-3-Clause	A	72	Claude Code, Codex
webui-codechromium/chromium	Skill	25k	today	BSD-3-Clause	A	33	Claude Code, Codex
browserwing-executorMemTensor/MemOS	Skill	12k	3d ago	Apache-2.0	A	42	Claude Code, Codex
figma-design-reviewchromium/chromium	Skill	25k	today	BSD-3-Clause	A	59	Claude Code, Codex
figma-to-webuichromium/chromium	Skill	25k	today	BSD-3-Clause	A	44	Claude Code, Codex
figma-to-views-jsonchromium/chromium	Skill	25k	today	BSD-3-Clause	A	55	Claude Code, Codex