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.
git clone --depth 1 https://github.com/TimboGP/timbogp-marketplaceWrote 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/commands/timbogp/timbogp-marketplace/ux-audit)<a href="https://agentmods.dev/commands/timbogp/timbogp-marketplace/ux-audit"><img src="https://agentmods.dev/badge/commands/timbogp/timbogp-marketplace/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.
<a href="https://agentmods.dev/commands/timbogp/timbogp-marketplace/ux-audit"><img src="https://agentmods.dev/badge/commands/timbogp/timbogp-marketplace/ux-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.00435 |
| Opus 5 | $0.00011 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
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 11d 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.
What it actually says
/ux-audit
Audit the target for both usability and accessibility, then produce one consolidated, scored report.
Target: $ARGUMENTS (a file path, a URL, a screenshot, or — if empty — ask what to audit, defaulting to the current project's entry HTML/page if obvious).
Procedure
- Identify the target. Resolve
$ARGUMENTS. If it is source code or a project, locate the relevant view(s). If a URL/file, prefer running automated checks. - Usability pass. Apply the
ux-auditskill: evaluate against Nielsen's 10 heuristics + IA/navigation + task flow + content hierarchy + consistency. Rate each finding on the 0–4 severity scale. - Accessibility pass. Apply the
accessibility-auditskill: WCAG 2.2 AA via POUR. Run the bundledcontrast.mjson key color pairs and, for a live URL/HTML file,axe-scan.mjsif its deps are available. Assign Critical/Serious/Moderate/Minor severities mapped to success criteria. - Consolidate & score. Merge into one report:
- A summary scorecard: usability verdict + heuristic scores, accessibility verdict (Fail/Conditional/Pass for AA) + counts by severity.
- Top issues ranked by severity × frequency × impact.
- Findings grouped by area, each with location, impact, and a concrete fix.
- A Quick wins vs. larger investments split.
- Offer next steps. Where fixes mean code, offer to apply them via
accessible-components,interaction-feedback,design-tokens, orux-copy.
Keep the report skimmable. Lead with the verdict and the top issues.
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.
- 11d ago First seen · 26 lines · 22 tokens per session scan A f4d7eea3bbf2
ux-audit is a command published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 435 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.
Other commands, from other repositories
dataviz
Define chart types, color encoding, and data display conventions.
design
Interview-driven design. Extracts requirements, writes spec, suggests new session.
qec-code-inspect
Inspect quantum code family properties, parity check matrices, transversals, and distance bounds.
qec-dem
Inspect and parse Detector Error Models (DEM), Stim circuit definitions, and parallel fault collapse rules.
uw-cmd-brainstorm
Transform a rough game idea into structured design document sections.
uw-cmd-plan
Break a feature or sprint into actionable tasks with clear acceptance criteria.