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 LiuYihey/Agent-Engineering --skill agent-shell-navigation-uxgit clone --depth 1 https://github.com/LiuYihey/Agent-EngineeringWrote 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/liuyihey/agent-engineering/agent-shell-navigation-ux)<a href="https://agentmods.dev/skills/liuyihey/agent-engineering/agent-shell-navigation-ux"><img src="https://agentmods.dev/badge/skills/liuyihey/agent-engineering/agent-shell-navigation-ux/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/liuyihey/agent-engineering/agent-shell-navigation-ux"><img src="https://agentmods.dev/badge/skills/liuyihey/agent-engineering/agent-shell-navigation-ux.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 | $0.00060 | $0.00949 |
| Opus 5.5 | $0.00024 | $0.00380 |
| Sonnet 5.5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
agent-shell-navigation-ux 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 1mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Shell Navigation UX
Engineering points for apps with a persistent agent conversation beside a main content area that navigates independently.
When to apply
- Main page / route changes while chat stays visible (or remounts for the same session)
- Transcript jumps to top/bottom after navigate, rehydrate, or keep-alive hide
- Async CTAs (launch, submit, dispatch) feel ignored until the network returns
- Designing ownership for chat viewport vs page shell state
1. Page navigation ↔ conversation place
Rule
Transcript scroll belongs to session identity, not to the React instance or the current main page.
Reset (or auto-scroll to end) only when the active session id changes (new chat, history pick, task→linked session). Do not reset because:
- Main content navigated (list ↔ detail ↔ wizard)
- Chat remounted for layout (inline ↔ sidebar)
- Keep-alive toggled
display: none - Same-session server rehydrate replaced the message array
Prefer
- Session-keyed scroll memory (module store or equivalent) shared across mounts
- Capture while the scroll container is visible — before navigate / before hide
- On mount or same-session list replace: restore remembered offset (retry after layout)
- Treat hidden containers as unreliable (
scrollTopreads as0) — never write that back
Avoid
- Binding scroll to page/
routeeffects (“on page change, scroll chat to bottom”) - First-paint “scroll to end” on every remount of the same session
- Auto-scroll driven only by message-array length after a bulk replace
- Saving scroll from a
display:nonepanel (false zero)
Ownership checklist
- Who owns transcript viewport? → session store / chat shell (not the page router)
- Who may clear it? → session switch only
- When does main navigate? → capture first if chat may remount or hide
- After rehydrate of the same session? → preserve, do not follow as “new messages”
2. Click feel + user mental model (async actions)
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.
- 1mo ago First seen · 104 lines · 60 tokens per session scan A 0f480ed26144
agent-shell-navigation-ux is a skill published in the GitHub repository LiuYihey/Agent-Engineering (5 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 949 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.