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 renmengwen/MuseDock --skill tech-minimal-productgit clone --depth 1 https://github.com/renmengwen/MuseDockWrote 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/renmengwen/musedock/tech-minimal-product)<a href="https://agentmods.dev/skills/renmengwen/musedock/tech-minimal-product"><img src="https://agentmods.dev/badge/skills/renmengwen/musedock/tech-minimal-product/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/renmengwen/musedock/tech-minimal-product"><img src="https://agentmods.dev/badge/skills/renmengwen/musedock/tech-minimal-product.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 | $0.00018 | $0.00677 |
| Opus 5 | $0.00009 | $0.00338 |
| Sonnet 5 | $0.00004 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
tech-minimal-product 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 12d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this design system for MuseDock product surfaces: /creative, /creative/:workflowId, /editor/:workflowId, and /settings.
Rules
- Keep the first screen functional. Do not replace the creative homepage with a marketing hero.
- Use the original MuseDock light console shell for navigation and task history.
- Navigation: there is no global top bar. The creative sidebar is the global navigation (sidebar-as-navigation); the settings entry stays at the sidebar bottom, and secondary pages (editor, settings) must provide an explicit way back.
- Use light panels for forms, long text, settings, and task details.
- Do not rely on red/cyan as the page skeleton. Use neutral gray/white/ink surfaces first; reserve red only for destructive or failure states, and cyan only for tiny focus/status signals.
- Primary actions use ink (
--accent-primary#111827, pressed/hover--accent-primary-strong). Never introduce blue as an action, link, or selected-state color. - Implementation colors must go through tokens: use the Tailwind semantic classes registered in
frontend-react/tailwind.config.js(ink,signal,page,surface-*,fg-*,line-*,warn,danger,success) or CSS variables. Do not add new arbitrary hex values. - Confirmation flows use the shared
ConfirmDialog(Radix); neverwindow.confirm/window.alertor hand-rolled fixed overlays. - Keep common card radii at 4-8px. The homepage prompt composer may keep the original larger rounded input shape.
- Prefer dense but readable grids, sticky sidebars, compact toolbars, and clear loading states.
- Preserve the current homepage and task-detail information architecture unless a workflow requires structural change; prefer color, density, hierarchy, and spacing adjustments over page rewrites.
- Use dialogs for low-frequency, field-heavy configuration details, especially settings provider forms. Keep settings pages scannable with compact summary rows and open details on demand.
- Make the product feel technology-forward: crisp geometry, compact data density, precise controls, subtle grid/terminal cues, and confident dark editor chrome are welcome.
- Avoid generic AI-product styling: no glowing orbs, magic-gradient hero sections, excessive sparkle effects, chatbot mascots, or vague "AI brain" visuals.
- Keep all visible user copy in Chinese unless it is a product name, API field, file name, or environment variable.
- Do not use bluish-purple gradients, decorative orbs, emoji icons, or nested cards.
What ships with it
4 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.
- 12d ago First seen · 37 lines · 18 tokens per session scan A 6a1676391843
tech-minimal-product is a skill published in the GitHub repository renmengwen/MuseDock (113 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 677 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 2026-08-30.
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.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.