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/kensaurus/cursor-kenji/thirdparty-web-interface-guidelinesgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWhat 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 | $0.00015 | $0.01811 |
| Opus 5 | $0.00008 | $0.00905 |
| Sonnet 5 | $0.00003 | $0.00362 |
| Haiku 4.5 | $0.00002 | $0.00181 |
Grade A, and why
thirdparty-web-interface-guidelines 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 2d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Interface Guidelines
Third-party command from Vercel Web Interface Guidelines.
Upstream: vercel-labs/web-interface-guidelines
Companion skill:thirdparty-web-interface-guidelines· Seeskills/thirdparty-web-interface-guidelines/ATTRIBUTION.md
Review these files for compliance: $ARGUMENTS
Read files, check against rules below. Output concise but comprehensive—sacrifice grammar for brevity. High signal-to-noise.
Rules
Accessibility
- Icon-only buttons need
aria-label - Form controls need
<label>oraria-label - Interactive elements need keyboard handlers (
onKeyDown/onKeyUp) <button>for actions,<a>/<Link>for navigation (not<div onClick>)- Images need
alt(oralt=""if decorative) - Decorative icons need
aria-hidden="true" - Async updates (toasts, validation) need
aria-live="polite" - Use semantic HTML (
<button>,<a>,<label>,<table>) before ARIA - Headings hierarchical
<h1>–<h6>; include skip link for main content scroll-margin-topon heading anchors
Focus States
- Interactive elements need visible focus:
focus-visible:ring-*or equivalent - Never
outline-none/outline: nonewithout focus replacement - Use
:focus-visibleover:focus(avoid focus ring on click) - Group focus with
:focus-withinfor compound controls
Forms
- Inputs need
autocompleteand meaningfulname - Use correct
type(email,tel,url,number) andinputmode - Never block paste (
onPaste+preventDefault) - Labels clickable (
htmlForor wrapping control) - Disable spellcheck on emails, codes, usernames (
spellCheck={false}) - Checkboxes/radios: label + control share single hit target (no dead zones)
- Submit button stays enabled until request starts; spinner during request
- Errors inline next to fields; focus first error on submit
- Placeholders end with
…and show example pattern autocomplete="off"on non-auth fields to avoid password manager triggers- Warn before navigation with unsaved changes (
beforeunloador router guard)
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.
- 2d ago First seen · 185 lines · 15 tokens per session scan A 42b59a89a80d
thirdparty-web-interface-guidelines is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 1,811 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
commit-msg
Cursor tooling: skills, rules, subagents.
boot
Initialize agent, verify setup, and load rules.
code-review
Confidence-based code review checklist.
prp-new
Create new Product Requirement Prompt from scratch.
clean
Repository hygiene — clean temp files, organize execution folders.
context
Dynamic context management — status, clean, log, save, read.