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 hani-q/qstack --skill qstack-ui-prototypegit clone --depth 1 https://github.com/hani-q/qstackWrote 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/hani-q/qstack/qstack-ui-prototype)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-ui-prototype"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-ui-prototype/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/hani-q/qstack/qstack-ui-prototype"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-ui-prototype.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 Excessive Agency · line 84 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00143 | $0.03500 |
| Opus 5.5 | $0.00057 | $0.01400 |
| Sonnet 5.5 | $0.00029 | $0.00700 |
| Haiku 4.5 | $0.00014 | $0.00350 |
Grade A, and why
qstack-ui-prototype 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-ui-prototype
Give an idea a picture before anyone builds it. A clickable mock of one or two screens settles layout, hierarchy, copy, and states faster than a page of prose, and it is cheap enough to throw away and redo.
The prototype is evidence, not a contract. On its own it records a
direction. Attached to a plan, it illustrates numbered clauses and is stamped
Reference so nobody mistakes it for a decision. A pixel in the mock is never
a requirement.
Resolve the target
Work out which mode you are in before reading anything else.
Plan mode when any of these holds:
- a
plan.htmlpath was supplied, or--into <plan.html>was passed; /qstack-plan-to-htmlinvoked this skill during a conversion;- the conversation is clearly about one specific plan.
Standalone mode otherwise. Do not go looking through
qstack/compound_engineering/plans/ for a plan to attach to. If exactly one
plan in that folder is unfrozen and its title plainly names the same screen
the user asked for, ask once, in plain words:
There is a plan for this at
<path>. Attach the prototype to it, or keep it standalone?
Any other case is standalone, and the report tells the user how to attach it later.
Never select .template/. Never write a prototype for a Markdown draft: the
renderer runs this skill after the HTML exists.
Frozen plans
Plan mode only. Before editing, check the plan directory for execution.md,
legacy implementation-notes.md, outcome.md, the retired board.jsonl, or
a board-events.js containing any call after its required
{"event":"board","format":1} header. If any exists, stop: execution has
started and the plan is frozen. Say so and name the file. A prototype for a
plan in flight belongs in the execution record through the loop, not in the
plan. A header-only event stream is the pre-board placeholder and does not
freeze the plan.
Decide whether one is warranted
In standalone mode the user has already decided. Build it.
In plan mode, read the whole plan first. A prototype is warranted when the plan adds or changes something a person sees: a page, a screen, a component, a form, a dashboard, a CLI's output layout, an email, a document template.
What ships with it
7 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.
- 1mo ago Changed fccb5f47085e
- 1mo ago First seen · 320 lines · 143 tokens per session scan A f252d64bacaf
qstack-ui-prototype is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 143 tokens to every session and 3,500 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
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.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
open-design-setup
Prepare or repair a project's prototyping environment so open-design can build prototypes with the project's own component library and render them through the project's toolchain. Use when the library target is needed and docs/design/prototyping.md is missing, stale, or failing; excludes HTML-only design work and…
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…