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 agentmods add skills/carbeneai/forge/artnpx skills add CarbeneAI/Forge --skill artgit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/art)<a href="https://agentmods.dev/skills/carbeneai/forge/art"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/art.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01080 |
| Opus 5 | $0.00016 | $0.00540 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
art 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 4d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Art Skill
Complete visual content system using the PAI Visual Aesthetic.
Core Aesthetic
Tron-meets-Excalidraw - Digital warmth combining:
- Hand-drawn Excalidraw-style sketch lines (NOT clean vectors)
- Dark slate backgrounds for modern contrast
- Neon orange (warmth) + cyan (tech) accents
- Subtle glows on key elements
Full aesthetic documentation: ${PAI_DIR}/skills/CORE/aesthetic.md
This is the SINGLE SOURCE OF TRUTH for all visual styling.
Workflow Routing
| Content Type | Workflow |
|---|---|
| Blog headers / Editorial | workflows/workflow.md |
| Adaptive orchestrator | workflows/visualize.md |
| Flowcharts / Sequences | workflows/mermaid.md |
| Architecture diagrams | workflows/technical-diagrams.md |
| Classification grids | workflows/taxonomies.md |
| Chronological | workflows/timelines.md |
| 2x2 matrices | workflows/frameworks.md |
| X vs Y | workflows/comparisons.md |
| Screenshot markup | workflows/annotated-screenshots.md |
| Step-by-step | workflows/recipe-cards.md |
| Quote cards | workflows/aphorisms.md |
| Idea territories | workflows/maps.md |
| Big numbers | workflows/stats.md |
| Sequential panels | workflows/comics.md |
Image Generation
Default model: nano-banana-pro (Gemini 3 Pro)
bun run ${PAI_DIR}/skills/art/tools/generate-ulart-image.ts \
--model nano-banana-pro \
--prompt "[PROMPT]" \
--size 2K \
--aspect-ratio 1:1 \
--output /path/to/output.png
Alternative Models
| Model | When to Use |
|---|---|
| flux | Maximum quality |
| gpt-image-1 | Different interpretation |
API keys in: ${PAI_DIR}/.env
REPLICATE_API_TOKEN- Flux and Nano BananaOPENAI_API_KEY- GPT-image-1GOOGLE_API_KEY- Nano Banana ProREMOVEBG_API_KEY- Background removal
Quick Decision Tree
What does user need?
├─ Unsure which approach? → VISUALIZE (analyzes & orchestrates)
├─ Flowchart/sequence/state diagram? → MERMAID
├─ Abstract metaphor for article? → Editorial (workflow.md)
├─ System/architecture with labels? → Technical Diagram
├─ Categories in grid? → Taxonomy
├─ Change over time? → Timeline
├─ 2x2 matrix or mental model? → Framework
├─ Side-by-side contrast? → Comparison
├─ Markup existing screenshot? → Annotated Screenshot
├─ Step-by-step process? → Recipe Card
├─ Quote as social visual? → Aphorism
├─ Idea territories as map? → Conceptual Map
├─ Single striking number? → Stat Card
└─ Multi-panel story? → Comic
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.
- tools/generate-prompt.ts 15 KB runs code
- tools/generate-ulart-image.ts 21 KB runs code
- workflows/AnnotatedScreenshots.md 10 KB
- workflows/Aphorisms.md 9.8 KB
- workflows/Comics.md 12 KB
- workflows/Comparisons.md 11 KB
- workflows/Frameworks.md 11 KB
- workflows/Maps.md 13 KB
- workflows/Mermaid.md 28 KB
- workflows/RecipeCards.md 11 KB
- workflows/Stats.md 11 KB
- workflows/Taxonomies.md 10.0 KB
- workflows/TechnicalDiagrams.md 18 KB
- workflows/Timelines.md 11 KB
- workflows/Visualize.md 23 KB
- workflows/Workflow.md 14 KB
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.
- 4d ago First seen · 124 lines · 33 tokens per session scan A 503f26491fb0
art is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,080 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
data-security-classification
USAP agent skill for Data Security & Classification. Classify data sensitivity and assign appropriate protection requirements, handling controls, and retention policies.
sql-injection
Hunt SQL injection (CWE-89) via source-level taint tracking. Covers string concat, format-string, ORM raw queries, second-order injection, and NoSQL injection in MongoDB/DynamoDB.
nosqli
Skill "nosqli" from tr4m0ryp/shor, covering nosqli — nosql injection scanner, when to reach for it, key flags, safe invocation and scan a login endpoint for nosql operator injection.
sqlmap
Skill "sqlmap" from tr4m0ryp/shor, covering sqlmap — sql injection exploitation, when to reach for it, key flags, safe invocation and then, scoped extraction (one table, capped rows).
nosqli
NoSQL injection — MongoDB operator injection ($ne, $gt, $where, $regex), CouchDB / Firebase / Redis attack patterns, auth bypass, blind extraction.
sqli
SQL Injection — automated and manual exploitation of unsanitized SQL queries. Covers Union-based, Error-based, Blind (Boolean/Time-based), and Stacked queries. Includes sqlmap automation with WAF bypass tamper scripts.