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 Cavalry-Collective/visual-stack --skill reviewgit clone --depth 1 https://github.com/Cavalry-Collective/visual-stackWrote 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/cavalry-collective/visual-stack/review)<a href="https://agentmods.dev/skills/cavalry-collective/visual-stack/review"><img src="https://agentmods.dev/badge/skills/cavalry-collective/visual-stack/review/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/cavalry-collective/visual-stack/review"><img src="https://agentmods.dev/badge/skills/cavalry-collective/visual-stack/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00140 | $0.08999 |
| Opus 5.5 | $0.00056 | $0.03600 |
| Sonnet 5.5 | $0.00028 | $0.01800 |
| Haiku 4.5 | $0.00014 | $0.00900 |
Grade A, and why
review 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 7d 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 — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.
0 · Host (do this first)
This skill is tool-agnostic. The loop is defined in
plugins/vstack/contracts/review-loop.md and the ops you need in
plugins/vstack/contracts/host.md. Never invent host-specific tool names in
this file — they live only in the Host adapter.
| You are running under… | Load adapter | Set |
|---|---|---|
| Codex | skills/review/hosts/codex.md |
VSTACK_HOST=codex (or --host codex on serve) |
| Grok Build / Grok CLI | skills/review/hosts/grok.md |
VSTACK_HOST=grok (or --host grok on serve) |
| Claude Code | skills/review/hosts/claude.md |
VSTACK_HOST=claude (default if unset) |
Adapters live in the hosts/ directory beside this SKILL.md. Do not read
plugins/vstack/host-profiles/<id>.json instead: that JSON is UI data with no
tool mapping.
Read the adapter before §3. Every background, watch_stream / watch_next, stop,
share, and browser_capture step is fulfilled exactly as that file says.
A two-way review loop. The user comments on the screen; you apply the comments, ask about anything ambiguous, and publish the next version. Two things can go under it:
| what it is | what you change | |
|---|---|---|
| A page (§1–§3) | a wireframe you just generated, an exported screen, a prototype — any self-contained HTML file | the file |
| A UI that exists (§7) | an app on localhost, or a website on the internet: the real screens, real data, real states | the source code — or, for a site you don't own, a note about it |
requirements ──► page.html ──► review workspace ──► brief.md ─────┐
▲ or a live app (user comments) │
└──────── you apply it, reply, publish v(N+1) ◄──────────────┘
One review is one subject. A page review opens that file and nothing else — several screens means several files and several workspaces, not an invented project structure. A live review opens the whole app, because clicking through it is the point.
Which one? If the thing the user wants to talk about already runs, review it running (§7) — a wireframe of a screen that exists is a copy that drifts. Build a page when the screen does not exist yet, or when they want to change it without changing code.
What ships with it
16 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.
- assets/bundle-artifact.mjs 5.2 KB runs code
- assets/harvest-reference.js 5.7 KB runs code
- assets/review-server.mjs 107 KB runs code
- assets/screen-template.html 2.1 KB
- assets/workspace.html 272 KB
- hosts/claude.md 3.9 KB
- hosts/codex.md 5.5 KB
- hosts/grok.md 5.0 KB
- references/design-sources.md 4.3 KB
- references/workflow.md 17 KB
- tests/design-tokens.mjs 5.9 KB runs code
- tests/host-profiles.mjs 2.7 KB runs code
- tests/review-lifecycle.mjs 22 KB runs code
- tests/round-gate.mjs 9.3 KB runs code
- tests/update-check.mjs 3.8 KB runs code
- tests/workdir.mjs 3.2 KB runs code
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.
- 7d ago Changed · +68 lines 4a6b4a385946
- 1mo ago First seen · 478 lines · 140 tokens per session scan A f2ccd4f18d72
review is a skill published in the GitHub repository Cavalry-Collective/visual-stack (11 stars, last pushed 3d ago), licensed MIT. It adds 140 tokens to every session and 8,999 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 2026-08-30.
Other skills, from other repositories
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
presentation-design
Designs slide decks and one-pagers that carry an argument rather than decorate one — deck structure, headlines that state the takeaway, charts that make a single point, and the different rules board decks and conference talks follow. Use this to build or fix a pitch deck, board deck, or conference talk, to design a…
ux-product-auditor
Audits a website, app, onboarding flow, or design for usability, conversion, and product problems, tying every finding to a business outcome and a severity. Use this to review an interface, diagnose low conversion or activation, find where users drop off, get structured product feedback, or decide which UX fixes to…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…
brand-identity
Defines and applies visual brand — logo usage, palette, typography, imagery direction, and the guidelines that keep expression consistent across product and marketing surfaces. Use this to establish a brand from scratch, audit whether an existing brand is being applied consistently, build brand guidelines, or decide…
design-styles
Applies a deliberate visual direction to an interface — minimalist editorial, industrial utilitarian, or high-polish commercial — each with its own type scale, palette behavior, surface treatment, and motion. Use this when a product needs a point of view rather than defaults, when choosing between visual directions…