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 Classic298/open-webui-plugins --skill inline-visualizer-v2git clone --depth 1 https://github.com/Classic298/open-webui-pluginsWrote 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/classic298/open-webui-plugins/inline-visualizer-v2)<a href="https://agentmods.dev/skills/classic298/open-webui-plugins/inline-visualizer-v2"><img src="https://agentmods.dev/badge/skills/classic298/open-webui-plugins/inline-visualizer-v2/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/classic298/open-webui-plugins/inline-visualizer-v2"><img src="https://agentmods.dev/badge/skills/classic298/open-webui-plugins/inline-visualizer-v2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 33 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 109 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high System Prompt Leakage · line 124 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00074 | $0.10357 |
| Opus 5.5 | $0.00030 | $0.04143 |
| Sonnet 5.5 | $0.00015 | $0.02071 |
| Haiku 4.5 | $0.00007 | $0.01036 |
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 29d 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 — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inline Visualizer
This is the handbook/tutorial on how to use the visualizer tool. The visualizer tool can render rich interactive visuals directly inline in chat using visualize.
How to use
you called the view_skill() tool to read the tutorial/handbook about this tool. Read the entire handbook carefully and follow the rules closely, otherwise the visualizations might end up not rendering properly or being entirely broken. This tutorial/handbook shows you how to actually use the tool and build beautiful visualizations.
- Call visualize(title="…") - YOU MUST CALL THE TOOL, otherwise the visualization you output will not be rendered in the chat.
- Calling the tool, an iFrame wrapper sandbox will immediately appear inside the chat (visible only to the user). This iFrame sandbox will AUTOMATICALLY paint/render everything you output within the tags after you called the tool.
- After calling the tool, start with the opening tag @@@VIZ-START on its own line
- Next, after the opening tag, emit the HTML/SVG content (no , , , )
- Once you are done writing the code for the visualization, immediately close with @@@VIZ-END on its own line, followed by ONE EMPTY LINE. Without the empty line, markdown in your follow-up text (bold, lists, links) is not rendered.
- Done! The visualization is complete. Continue with any follow-up text to the user.
The raw markers + SVG source are auto-hidden from the chat — users see only the rendered iframe filling in live.
Example response structure:
""" I'll visualize the attention mechanism for you.
@@@VIZ-START
As you can see, each query token attends to all key tokens simultaneously. """
Streaming rules:
- Use the delimiters EXACTLY @@@VIZ-START and @@@VIZ-END — case-sensitive, on their own lines, with an empty line after @@@VIZ-END before any follow-up text. Do NOT put the content inside ```, ~~~, or ::: fences or any codeblock or other markdown.
- Do NOT wrap in HTML tags like or — only the text markers are detected.
- Emit exactly ONE @@@VIZ-START … @@@VIZ-END pair per tool call. For multiple visualizations, call the tool multiple times.
- Structure the content as always: first → visible content → last.
- Do NOT describe the HTML source in prose — users don't see it. Describe what the visualization shows.
- Requires iframe Sandbox Allow Same Origin in Open WebUI Settings → Interface. If disabled, the wrapper shows a notice — and the user won't see the visualization itself, just the notice.
- Any you include runs once, after the full block has streamed in.
What ships with it
2 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.
- 29d ago Changed d7fa8dab49d0
- 1mo ago First seen · 728 lines · 74 tokens per session scan A 550a2f23be3f
visualize is a skill published in the GitHub repository Classic298/open-webui-plugins (589 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 74 tokens to every session and 10,357 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
sc-filter
Load when removing low-quality cells and lowly-detected genes from a single-cell AnnData using QC-derived thresholds or tissue presets. Skip when the full normalize→HVG→PCA→cluster pipeline (use sc-preprocessing); reads are still raw FASTQ (use sc-fastq-qc).
genomics-vcf-operations
Load when summarising / filtering a VCF — variant classification (SNP / MNP / INS / DEL / COMPLEX), Ti/Tv ratio, QUAL / DP threshold filtering, INFO-field parsing. Skip when calling variants from BAM (run an external caller first); adding functional annotations (use genomics-variant-annotation).
tao-train-action-recognition
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO action-recognition model. Trigger phrases include "train action recognition", "video action…
huawei-cloud-functiongraph-function-create
Create and invoke FunctionGraph functions on Huawei Cloud. Supports VPC configuration, environment variables, synchronous and asynchronous function invocation. Use this skill when users ask to create, deploy, upload, or invoke cloud functions, serverless functions, or FunctionGraph functions. Triggered by keywords…
stoic-pragmatism
Distills the Stoic insistence on philosophy as action rather than theory, covering simplicity, efficiency, realism, the primacy of practice over abstraction, and the elimination of unnecessary complexity. Use when founders are overthinking strategy at the expense of execution, when organisations are drowning in…
realestate-screen
Property Screener — searches for properties matching investment criteria with pre-built screens for Cash Flow, Appreciation, BRRRR, First-Time Buyer, and Short-Term Rental strategies plus custom criteria support.