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 mhrsdev/AI-Agent-Skills-Library --skill static-project-gallery-uploadgit clone --depth 1 https://github.com/mhrsdev/AI-Agent-Skills-LibraryWrote 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/mhrsdev/ai-agent-skills-library/static-project-gallery-upload)<a href="https://agentmods.dev/skills/mhrsdev/ai-agent-skills-library/static-project-gallery-upload"><img src="https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/static-project-gallery-upload/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/mhrsdev/ai-agent-skills-library/static-project-gallery-upload"><img src="https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/static-project-gallery-upload.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 | $0.00095 | $0.01748 |
| Opus 5 | $0.00048 | $0.00874 |
| Sonnet 5 | $0.00019 | $0.00350 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade A, and why
static-project-gallery-upload 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Static Project Gallery Upload
Turn a loose folder of project images into a production-ready static-site gallery and upload package.
Core rule
Remove only exact duplicates unless the user explicitly asks for visual deduplication.
- Exact duplicate = same file bytes / same cryptographic hash, even if filenames differ.
- Similar image, same building, different angle, crop, lighting, render alternative, or facade view = keep it.
- If multiple views belong to the same building or design alternative, place them near each other in the gallery order.
- Do not delete the user's original source images unless explicitly instructed; create a clean derived output instead.
Workflow
1. Discover the project shape
Inspect the root before editing.
Check:
- Is the site static HTML/CSS/JS, Astro, React, Next, or another stack?
- Where are current gallery/project images referenced?
- Where are public assets served from?
- Does the project already have an upload/output folder convention such as
UP FILE? - Are image tools already available, e.g.
sharpinpackage.json?
Completion criterion: you know which files must be edited, which folders are source-only, and which files must be copied to the host package.
2. Inventory and exact-dedupe the source images
List every image in the user-provided folder and compute SHA256 hashes.
Use exact-hash grouping as the authoritative duplicate test:
Get-ChildItem "<source-image-folder>" -File |
Get-FileHash -Algorithm SHA256 |
Group-Object Hash |
Where-Object { $_.Count -gt 1 }
For each exact duplicate group, keep one representative. Prefer:
- The filename without copy suffixes like
(1),(2). - The filename already referenced by the site.
- Otherwise the earliest/cleanest name.
Completion criterion: you have a source-to-output mapping where every exact hash appears once, and no visually distinct angle was removed.
3. Preserve visual families in gallery order
Sort the kept images intentionally.
What ships with it
1 file 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.
- 7d ago First seen · 202 lines · 95 tokens per session scan A 46501b9e9877
static-project-gallery-upload is a skill published in the GitHub repository mhrsdev/AI-Agent-Skills-Library (6 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,748 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
mockup-extraction
Extract reusable components from approved HTML mockups during implementation. Identifies patterns, maps CSS to Tailwind, and populates prototype-patterns.md for visual fidelity. Use at start of /implement for UI-first features.
shadcn-integration
Integration guide for shadcn/ui components with OKLCH design tokens. Use when setting up shadcn, customizing themes, or adding components to Next.js projects. Auto-trigger on /init --tokens --shadcn flag.
web-clone
URL-driven website cloning with visual + functional verification.
skill-premium-web-experience
Use for creating, redesigning, or transforming websites into premium, cinematic, conversion-focused web experiences with visual research, storytelling, scroll-driven interaction, responsive design, motion, performance, accessibility, and visual QA.
skill-frontend-ux-guardrails
Use as a frontend UX quality gate for responsive behavior, overflow, accessibility, interaction usability, touch targets, typography, layout stability, mobile behavior, focus states, reduced motion, and final visual validation.
skill-impeccable
Orquestra melhorias de frontend inspiradas no Impeccable a partir de pedidos conversacionais de design, UX, acessibilidade, responsividade, tipografia, layout, cor, motion, clareza, hardening e polish.