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 saski/arnesto --skill visualizegit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/visualize)<a href="https://agentmods.dev/skills/saski/arnesto/visualize"><img src="https://agentmods.dev/badge/skills/saski/arnesto/visualize/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/saski/arnesto/visualize"><img src="https://agentmods.dev/badge/skills/saski/arnesto/visualize.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 | $0.00062 | $0.02277 |
| Opus 5.5 | $0.00025 | $0.00911 |
| Sonnet 5.5 | $0.00012 | $0.00455 |
| Haiku 4.5 | $0.00006 | $0.00228 |
Grade A, and why
visualize 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 21d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize
Mission
Help the user complete the job with the smallest truthful result. Choose Markdown, Mermaid, or inline HTML before you author the content. The host supplies styles and runtime behavior to HTML fragments. This entry file controls routing, output, conduct, design, and review. Its references add specialized rules and cannot override it.
Workflow
- Route the request with the detailed rules below.
- Identify the primary question. Preserve values, labels, units, order, uncertainty, and scope.
- Plan the hierarchy and only the necessary interaction.
- Complete the selected route: return Markdown or Mermaid, or follow the HTML lifecycle.
- Review the result against its source, then stop.
Routing
Choose one representation:
- Use a Markdown table for ordinary rows and columns. Return it directly and write no files.
- Use fenced Mermaid for static labeled relationships, ERDs, database schemas, and class diagrams. Return it directly and write no files.
- Use inline HTML when interaction, spatial layout, a chart, a simulation, a mockup, a structured view, or artwork adds material value.
- Geographic maps are out of scope. The sandbox cannot load map data or mapping libraries; never hand-draw geographic outlines and present them as a map. Offer the closest truthful non-geographic view instead.
- If an explanation depends on sequence, containment, or mechanism, treat it as a diagram.
- If the user asks for a picture, artwork, illustration, decorative scene, or poster, treat it as artwork.
- A request to preview or explore a proposed UI in the conversation is an inline HTML visualization request.
- A request for a new standalone file, website, app page, component, or other project change is not an in-transcript visual output. Build that in the open project.
- Use
/visualizewhen the output should be immutable and live inside the transcript. When/canvasis available, use it when the output should be a durable artifact outside the transcript that the user may revisit, refine, or share. For inline HTML, read every applicable reference: - Every HTML visualization MUST read
references/foundations.md. - Every chart, plot, part-to-whole view, or parallel timeline MUST read
references/charts.md. - Every form, tool, comparison, card, table, structured view, simulation, explainer, or dense categorical grid MUST read
references/components.md. - Every UI mockup or prototype MUST read
references/mockups.md. - Every HTML flowchart, structural diagram, or illustrative mechanism MUST read
references/diagrams.md. - Every artwork, illustration, decorative scene, or poster MUST read
references/art.md. - Exact icons or an unlisted token or class MUST read
references/catalog.md. - Read every applicable file. Read no unrelated file.
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.
- 21d ago First seen · 138 lines · 62 tokens per session scan A 6dbdd56fc794
visualize is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It adds 62 tokens to every session and 2,277 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
fs-creative-voltage
OpenDesign's seed pitch: the open, local alternative to closed AI design — why now, the wedge, and the ask. Built as a decision-grade fundraising pitch deck for pre-seed & seed VCs.
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
digital-health-clinical-asr-eval
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipasource diagnostic). Not for ASR auth (/riva-asr).