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 tdimino/claude-code-minoan --skill gemini-forgegit clone --depth 1 https://github.com/tdimino/claude-code-minoanWrote 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/tdimino/claude-code-minoan/gemini-forge)<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/gemini-forge"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/gemini-forge/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/tdimino/claude-code-minoan/gemini-forge"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/gemini-forge.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 | $0.00124 | $0.00799 |
| Opus 5 | $0.00062 | $0.00400 |
| Sonnet 5 | $0.00025 | $0.00160 |
| Haiku 4.5 | $0.00012 | $0.00080 |
Grade A, and why
gemini-forge 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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Forge
Generate frontend code with Gemini 3.1 Pro, polish with Claude. Gemini handles structure and scaffolding at $2/MTok; Claude handles craft, aesthetic conviction, and production hardening at $15/MTok.
Model: gemini-3.1-pro-preview (text-only, 1M context, 64K output)
Auth: GEMINI_API_KEY env var (same key as nano-banana-pro)
Quick Draft
Generate React or HTML/CSS from a task description.
# Simple component
uv run scripts/generate_ui.py "dark dashboard with real-time metrics" --mode react --thinking medium
# Full multi-file app
uv run scripts/generate_ui.py "SaaS pricing page with three tiers" --mode react --thinking high --app
# With design system context
uv run scripts/load_design_system.py --tokens tokens.css --brief brand.md --output context.txt
uv run scripts/generate_ui.py "hero section" --design-context context.txt --thinking high
Thinking levels: low (single components), medium (multi-component layouts), high (full apps, complex state). See references/thinking-levels.md.
Screenshot-to-Code
Convert a screenshot or mockup to code using the describe-first pipeline. Two API calls prevent layout hallucination—Gemini analyzes first, then generates from the verified spec.
# Full pipeline: screenshot → spec → code
uv run scripts/screenshot_to_code.py screenshot.png --framework react --output ./output
# Step 1 only: get the spec, inspect it before generating
uv run scripts/screenshot_to_code.py screenshot.png --analyze-only
# Step 2 only: generate from an existing or corrected spec
uv run scripts/screenshot_to_code.py --from-spec spec.md --framework html --output ./output
Use --analyze-only to inspect the spec. Claude can correct misreadings before passing to generation.
SVG Animation
Generate or animate SVGs with physics-based reasoning.
# Animate existing SVG
uv run scripts/generate_svg.py --mode animate logo.svg --description "draw-on stroke, 1.2s"
# Create animated SVG from description
uv run scripts/generate_svg.py --mode create --description "orbiting dots with spring connections"
# Physics simulation
uv run scripts/generate_svg.py --mode physics --description "particle system, 20 nodes, gravity"
# Animated logo
uv run scripts/generate_svg.py --mode logo --description "Minoan double-axe labrys, slow rotation"
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.
- 9d ago First seen · 84 lines · 124 tokens per session scan A af78c608b17f
gemini-forge is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 799 once invoked, about $0.0006 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
html-draft
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…
canvas-app
Creates or edits a Power Apps Canvas App through the Canvas Authoring MCP coauthoring session. Handles new app generation, direct targeted edits, complex multi-screen changes, responsive layout, per-screen self-QA, and compile-error convergence. Trigger on requests to create, build, generate, modify, update, change…
component-composition
How to combine fundamental-styles components correctly - required wrappers, nesting rules, and common composition patterns.
layout-patterns
Common UI layout patterns using fundamental-styles - login forms, dashboards, master-detail, wizards, and more.
bem-naming
BEM (Block Element Modifier) methodology and naming conventions used in fundamental-styles with real examples.
component-docs
Browse fundamental-styles component documentation with complete HTML examples from 140+ auto-generated markdown files. Use this when the user asks about component examples, modifiers, variants, HTML structure, or wants to see working code for any fundamental-styles component (button, table, input, dialog, etc.). Also…