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/proyecto26/sherlock-ai-plugin/visual-architectnpx skills add proyecto26/sherlock-ai-plugin --skill visual-architectgit clone --depth 1 https://github.com/proyecto26/sherlock-ai-pluginWrote 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/proyecto26/sherlock-ai-plugin/visual-architect)<a href="https://agentmods.dev/skills/proyecto26/sherlock-ai-plugin/visual-architect"><img src="https://agentmods.dev/badge/skills/proyecto26/sherlock-ai-plugin/visual-architect.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 | $0.00032 | $0.01026 |
| Opus 5 | $0.00016 | $0.00513 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
visual-architect 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- paper-visualizer — 89% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Visualizer Skill
Top-tier Scientific Visual Architect. Transforms text into geometric, structural visual instructions.
1. What This Skill Does
Takes research paper content (Methodology/Abstract) and produces a Structured Visual Schema—a high-precision prompt optimized for DALL-E 3, Midjourney v6, or Stable Diffusion.
2. Execution Logic (The Brain)
Phase 1: Layout Pattern Recognition
You must analyze the text and enforce one of these strictly:
- Linear Pipeline: Left→Right flow (Data Processing, Encoding-Decoding).
- Cyclic/Iterative: Center loop (Optimization, RL, Feedback Loops).
- Hierarchical Stack: Vertical stack (Multiscale features, Tree structures).
- Parallel Dual-Stream: Parallel rows (Multi-modal fusion, Contrastive Learning).
- Central Hub: Core connecting peripherals (Agent-Environment).
- Matrix Grid: Comparison studies or ablation components.
Phase 2: Schema Generation Rules
- Dynamic Zoning: Define 2-5 physical zones based on layout.
- Internal Visualization: Use concrete objects (Icons, Grids, Stacks), NOT abstract concepts.
- Explicit Connections: Describe physics of flow (e.g., "Curved arrow looping back").
3. Output Format (The Golden Schema)
You MUST respond strictly using this Markdown template. Use the examples in brackets [...] as a guide for the level of detail required, but replace them with your generated content.
---BEGIN PROMPT---
[Style & Meta-Instructions]
High-fidelity scientific schematic, technical vector illustration, clean white background, distinct boundaries, academic textbook style. High resolution 4k, strictly 2D flat design with subtle isometric elements.
**[TEXT RENDERING RULES]**
* **Typography**: Use bold, sans-serif font (e.g., Helvetica/Roboto style) for maximum legibility.
* **Hierarchy**: Prioritize correct spelling for MAIN HEADERS (Zone Titles). For small sub-labels, if space is tight, use numeric annotations (1, 2, 3) or clear abstract lines rather than gibberish text.
* **Contrast**: Text must be dark grey/black on light backgrounds. Avoid overlapping text on complex textures.
[LAYOUT CONFIGURATION]
* **Selected Layout**: [e.g., Cyclic Iterative Process with 3 Nodes]
* **Composition Logic**: [e.g., A central triangular feedback loop surrounded by input/output panels]
* **Color Palette**: [e.g., Professional Pastel (Azure Blue, Slate Grey, Coral Orange, Mint Green)]
[ZONE 1: LOCATION - LABEL]
* **Container**: [Shape description, e.g., Top-Left Rectangular Panel]
* **Visual Structure**: [Concrete objects, e.g., A stack of 3 layered documents with binary code patterns]
* **Key Text Labels**: "[Text 1]"
[ZONE 2: LOCATION - LABEL]
* **Container**: [Shape description, e.g., Central Circular Engine]
* **Visual Structure**: [Concrete objects, e.g., A clockwise loop connecting 3 internal modules: A (Gear), B (Graph), C (Filter)]
* **Key Text Labels**: "[Text 2]", "[Text 3]"
[ZONE 3: LOCATION - LABEL]
... (Add Zone 4 or 5 if necessary based on the selected layout)
[CONNECTIONS]
1. [Connection description, e.g., A curved dotted arrow looping from Zone 2 back to Zone 1 labeled "Feedback"]
2. [Connection description, e.g., A wide flow arrow branching from Zone 2 to Zone 3]
---END PROMPT---
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.
- 5d ago First seen · 88 lines · 32 tokens per session scan A 16fce9947933
visual-architect is a skill published in the GitHub repository proyecto26/sherlock-ai-plugin (35 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,026 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 2026-08-30.
Other skills, from other repositories
paper2code
Analyzes research papers (PDF/arXiv URL) and converts them into executable code. Automatically activated upon requests for paper replication, algorithm implementation, or research reproduction. Responds to requests like "Implement this paper", "paper2code", "Convert paper to code".
deep-research
Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section…
genimg-gemini-web
Image generation skill using Gemini Web. Generates images from text prompts via Google Gemini. Also supports text generation. Use as the image generation backend for other skills like cover-image, xhs-images, article-illustrator.
paper-comic
Generate educational comics from academic papers, using visual storytelling to explain core ideas and innovations. Supports 4 art styles: classic (clean lines), tech (futuristic), warm (friendly), chalk (blackboard). Uses genimg-gemini-web to generate images.
paper-visualizer
Transform research papers into professional visual schemas. Analyzes paper logic, selects optimal layout patterns, and generates detailed prompts for AI image generation.
paper-analyzer
Transform academic papers into in-depth technical articles with multiple writing style options. Use the MinerU Cloud API for high-precision PDF parsing, automatically extracting images, tables, and formulas. Optional formula explanations and GitHub code analysis, generating Markdown and HTML formats.