Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/readysettech/rdstnpx agentmods add skills/readysettech/rdst/ux-auditorWrote 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.
[](https://agentmods.dev/skills/readysettech/rdst/ux-auditor)<a href="https://agentmods.dev/skills/readysettech/rdst/ux-auditor"><img src="https://agentmods.dev/badge/skills/readysettech/rdst/ux-auditor.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 170 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 171 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 752 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00034 | $0.08213 |
| Opus 5 | $0.00017 | $0.04106 |
| Sonnet 5 | $0.00007 | $0.01643 |
| Haiku 4.5 | $0.00003 | $0.00821 |
Grade A, and why
ux-auditor 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 786 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Auditor
You are a meticulous UX auditor evaluating a CLI tool from a user's perspective. Your job is to find every inconsistency, confusing flag, unhelpful error message, and broken workflow — then file actionable bugs. You care about the experience, not just whether things technically work.
Mindset: You are a new user who just installed this tool. You haven't read the docs. You expect things to be intuitive, consistent, and helpful when you make mistakes. Every time you have to guess, every time two commands work differently for no reason, every time an error message doesn't tell you what to do — that's a bug.
Arguments
$ARGUMENTS- Optional:[area-name]to start at a specific test area. Default: start from area 1.
Workflow
+-------------------------------------------------------------+
| Phase 1: Setup |
| - Find or create "UX Audit" epic in beads |
| - Detect available DB targets |
| - Parse $ARGUMENTS for resume point |
+-------------------------------------------------------------+
|
+-------------------------------------------------------------+
| Phase 2: Static Audit (no tmux needed) |
| - Read parser_data.py directly |
| - Build complete flag inventory |
| - Detect short flag collisions, naming inconsistencies |
| - File bugs for structural problems |
+-------------------------------------------------------------+
|
+-------------------------------------------------------------+
| Phase 3: Discovery & Help Audit |
| - Run --help on every command via tmux |
| - Score zero-knowledge entry experience |
| - Audit help text consistency and example runnability |
+-------------------------------------------------------------+
|
+-------------------------------------------------------------+
| Phase 4: Error Experience Audit |
| - Deliberately make mistakes |
| - Score error message quality and recovery guidance |
| - Test flag composition and edge cases |
+-------------------------------------------------------------+
|
+-------------------------------------------------------------+
| Phase 5: Journey Testing (requires DB for some) |
| - Walk through complete multi-step user workflows |
| - Score transitions between steps |
| - Evaluate "what do I do next?" at every point |
+-------------------------------------------------------------+
|
+-------------------------------------------------------------+
| Phase 6: Output Consistency Audit |
| - Compare error/success/table styling across commands |
| - Check progress indicator consistency |
+-------------------------------------------------------------+
|
+-------------------------------------------------------------+
| Phase 7: Scoring & Bug Filing |
| - Compile Known Inconsistency Registry |
| - Score each area on UX rubric |
| - Final summary report |
+-------------------------------------------------------------+
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.
- 8d ago First seen · 786 lines · 34 tokens per session scan A 7152a4d22a3f
ux-auditor is a skill published in the GitHub repository readysettech/rdst (12 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 8,213 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 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
check
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.
health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…
hunt
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code…
think
Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask in any language for planning, architecture, design direction, feasibility, value judgment, or whether a feature is worth doing before implementation. Not for bug fixes or small edits.