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/undertone0809/rudder/visualizenpx skills add Undertone0809/rudder --skill visualizegit clone --depth 1 https://github.com/Undertone0809/rudderWhat 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 | $0.00104 | $0.01623 |
| Opus 5 | $0.00052 | $0.00812 |
| Sonnet 5 | $0.00021 | $0.00325 |
| Haiku 4.5 | $0.00010 | $0.00162 |
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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize
Create a visual only when it materially improves what the user can understand, compare, or decide. The Rudder inline runtime is scriptless and has no network access, so design for a useful first render with declarative HTML, SVG, and CSS.
Choose The Output
- Use a normal fenced Mermaid block when labeled nodes and edges fully explain a static structure or flow. Do not create an HTML artifact for that case.
- Use an inline visual for charts, timelines, comparisons, spatial layouts, static scenario views, or compact reports that benefit from custom geometry.
- Use the v1 message envelope only in Rudder Chat. It is a Rudder protocol, independent of Codex, Claude, Gemini, Cursor, OpenCode, Pi, Hermes, process, HTTP, or gateway filesystem conventions.
- Outside Rudder Chat, fall back to Mermaid, Markdown tables, or concise prose. Do not emit a Rudder envelope on a surface that cannot render it.
Message Envelope
- Write only an HTML fragment. Do not include a doctype or
html,head, orbodyelements. - Keep every fragment at or below 64 KiB UTF-8, all fragments together at or below 128 KiB, and the complete visual-bearing final reply at or below 256 KiB. Emit at most three visuals in one assistant message.
- Give the fragment one top-level markup root,
<div id="widget">. Bounded<style>blocks may precede that root. - Put any custom CSS in bounded
<style>elements. Inlinestyleattributes are removed. - Check the fragment before replying. Fix escaped markup such as literal
\"or\n, missing labels, clipped content, and malformed SVG. - Put this exact opening marker on its own line where the visual should render, then the fragment, then the exact closing marker on its own line:
:::rudder-inline-visual:v1
<style>#widget .series { color: var(--viz-series-1); }</style>
<div id="widget">...</div>
:::rudder-inline-visual:end
The markers must have no indentation, attributes, or trailing text. Keep any
necessary explanation outside the envelope. Never emit
::codex-inline-vis{...}, ::rudder-inline-vis{...}, a file path, an iframe,
or a second link to source HTML; Rudder owns capture, trusted placement,
persistence, sandboxing, and rendering.
What ships with it
3 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.
- 2d ago First seen · 135 lines · 104 tokens per session scan A 0e30c853b700
visualize is a skill published in the GitHub repository Undertone0809/rudder (287 stars, last pushed 2d ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,623 once invoked, about $0.0005 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
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者:就绪检查(skills 是否最新 → Runtime 是否配套)、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用;业务 Skill(剪口播/字幕/画面/导出)第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
cap_llm_inspect_image
How to inspect a local image with inspectimage.