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 skills add kensaurus/cursor-kenji --skill enhance-web-instant-navgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/enhance-web-instant-nav)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/enhance-web-instant-nav"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/enhance-web-instant-nav/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/skills/kensaurus/cursor-kenji/enhance-web-instant-nav"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/enhance-web-instant-nav.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 MCP Rug Pull · line 54 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00080 | $0.01709 |
| Opus 5 | $0.00040 | $0.00855 |
| Sonnet 5 | $0.00016 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade A, and why
enhance-web-instant-nav scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl -sv <url> 2>&1 | grep "< HTTP"` — is a `103` emitted today? 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.
Surface router:
/uiux. You are here:enhance-web-instant-nav.
enhance-web-instant-nav — Instant Navigations
Degree of freedom: MIXED. Which pages to speculate [HIGH freedom];
the exclusion list, Sec-Purpose handling, and re-measure [LOW freedom — run exactly].
Applies to MPAs and Next.js App Router (server-rendered routes). Pure SPA routing → use the framework's prefetch API; Speculation Rules are per-document.
How to reason
- Observe — quote 2nd-page LCP p75, bfcache test result, and the top 5 next-click paths
- Rank — probability × page cost. Prefetch broadly; prerender only ≥ ~50% likely next pages
- Guard — list every URL with GET side effects or per-user state; exclude or downgrade to prefetch
- Ship — rules + server guard + analytics guard in the same PR
- Re-measure — if 2nd-page LCP didn't drop, the rule isn't firing (DevTools → Application → Speculative loads)
Worked example
Observe: blog; first-page LCP 1.9 s, next-article LCP 2.8 s; back button reloads (
unloadin analytics). Rank: "next article" 61% of sessions → prerender moderate; category links → prefetch moderate. Guard:/logout,/account/*,?utm_*excluded; server returns early onSec-Purpose. Ship: rules block +pagehideswap +document.prerenderingguard in the GA loader. Re-measure: next-article LCP 0.3 s (activation), bfcache green, no analytics double-count.
Safety contract [LOW freedom — run exactly]
- Never prerender: logout, cart/checkout, payment, auth, anything whose GET mutates state
- Server: if
Sec-Purposecontainsprefetch, skip counters/side effects; return normal HTML - Client: analytics, ads, consent, A/B run only after
document.prerendering === falseor onprerenderingchange - Never add
unloadlisteners; never setCache-Control: no-storeon HTML unless legally required - Cross-origin / cross-site prerender is not attempted
Phase 1 — Measure [LOW freedom — run exactly]
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 139 lines · 80 tokens per session scan A 0f0c40a02d68
enhance-web-instant-nav is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,709 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ui-design
Create distinctive, production-grade web interfaces with high design quality using Tailwind CSS. Use for building UI components, pages, dashboards, apps, and web applications. Generates crafted, polished code that avoids generic AI aesthetics.
react-dev
React frontend conventions for this project. Use when building or modifying React components, hooks, state management, styling, or frontend tests.
component-creation
Step-by-step workflow for creating accessible, tested UI components. Use when the user asks to create a new UI component.
state-management
Workflow for choosing and implementing the right state management approach. Use when the user needs to manage state for a new feature or refactor.
page-health-check
A procedure for checking a web page from a URL for data, visual, interaction, console, and performance problems, then fixing or documenting them.
employee-selector
A reusable employee-picker interface that shows departments as a tree and lets people select one or more employees, with search and department-wide selection.