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.
npx agentmods add commands/f0d010c/stark/stark-auditgit clone --depth 1 https://github.com/f0d010c/starkWrote 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/f0d010c/stark/stark-audit)<a href="https://agentmods.dev/commands/f0d010c/stark/stark-audit"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-audit.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00682 |
| Opus 5 | $0.00020 | $0.00341 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
stark-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 4d 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
/stark-audit
Legacy Claude Code command. In Codex, ask:
Audit this file with stark for UX problems and AI design slop.
Audit the file or screenshot at $1 against the appropriate platform's standards from this plugin.
Steps:
-
Detect platform from file extension or screenshot context:
.tsx/.jsx/.html/.svelte/.vue/.astro→ web.xaml/.cs(with WinUI/WPF context) → windows.swift→ apple.kt/.kts→ android- Screenshot → infer from chrome (title bar style, icons, materials)
-
Load UX checks first when the artifact includes a workflow, form, dashboard, onboarding, checkout, settings, or multi-step task:
- UX ->
skills/ux-design/SKILL.mdaudit checklist - UI ->
references/ui-patterns/ui-audit-rubric.md - Assets ->
references/ui-patterns/asset-selection.mdwhen the artifact uses images, screenshots, icons, generated visuals, external references, or brand assets - References ->
references/ui-patterns/reference-analysis.mdwhen the artifact claims to use a real product, Mobbin, Figma, or screenshot reference
- UX ->
-
Load the matching ban list:
- web →
references/web-bans.md - windows →
skills/windows-design/SKILL.mdstep 6 - apple →
skills/apple-design/SKILL.mdstep 6 - android →
skills/android-design/SKILL.mdstep 6
- web →
-
Walk the file and report violations as a table:
Line Violation Severity Fix 42 bg-gradient-to-r from-purple-500 to-pink-500(banned web slop)high Pick a real direction; see web-fonts.md 88 font-family: 'Inter'(banned default)high Replace with a curated pair from assets/font-pairs.md -
Categorize violations:
- High — blocked primary job, missing recovery path, unsafe/destructive action, broken platform idiom, or definitive AI slop tell
- Medium — missing state, weak action hierarchy, generic pattern that hurts distinctiveness, decorative assets that do not support the job, or repeated-use friction
- Low — unclear copy, mild scan-speed issue, or currency issue (using older patterns when newer ones exist)
-
Recommend a fix path: one paragraph, concrete steps, no hedging.
Do not just list violations. Always include the fix. If the entire approach needs rework, say so plainly. Prioritize broken flow, missing states, unclear next actions, and accessibility before visual distinctiveness.
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.
- 4d ago First seen · 51 lines · 40 tokens per session scan A 56114b4c1a20
stark-audit is a command published in the GitHub repository f0d010c/stark (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 682 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 commands, from other repositories
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
accessibility-specialist
Use when a screen might fail WCAG. Unlabeled inputs, no keyboard path, contrast below AA, missing landmarks, broken heading order, screen reader gaps, or a request for an a11y review or EU Accessibility Act check.
design-brief
Use when a design request is broad or unclear and you do not know which specialist it needs. Reads the brief, routes it to the right expertise, and returns structured guidance.