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 lubluniky/dale --skill dale-visualizegit clone --depth 1 https://github.com/lubluniky/daleWrote 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/lubluniky/dale/dale-visualize)<a href="https://agentmods.dev/skills/lubluniky/dale/dale-visualize"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-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/lubluniky/dale/dale-visualize"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-visualize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.01128 |
| Opus 5.5 | $0.00044 | $0.00451 |
| Sonnet 5.5 | $0.00022 | $0.00226 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
dale-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 1mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dale Visualize
Turn material into a standalone HTML artifact that makes an important relationship easier to see, inspect, compare, or manipulate. Adapt patterns to the task; never replace the task with a generic dashboard.
Frame the visual question
Before writing HTML, identify:
- the one question the artifact should answer;
- the audience and the decision or understanding it should enable;
- the verified facts, code, data, and uncertainties available;
- the relationship best expressed spatially: comparison, hierarchy, sequence, dependency, change over time, state, or direct manipulation;
- whether interaction materially improves comprehension.
Do not invent metrics, events, citations, product behavior, or source evidence. Never embed secrets, credentials, private environment values, or unrelated user data. Label unknown or inferred material honestly.
If a compact table, short prose, or an existing repository-native component is clearer than HTML, say so and use the simpler form unless the user explicitly requires an HTML artifact.
Select examples deliberately
Read references/example-catalog.md before implementation. Select one primary
example whose information shape matches the task, then at most two secondary
examples for a specific interaction or visual device. Inspect only those HTML
files under assets/examples/.
Borrow structure, interaction ideas, and implementation techniques—not the fictional Acme content, arbitrary palette, or entire page composition. Generate the final hierarchy from the user's material and the owning project's visual language when one exists.
Choose the artifact form
- Use a static explainer when the reader mainly needs to scan and understand.
- Use inline SVG for flows, architecture, timelines, call graphs, and custom figures whose geometry carries meaning.
- Use side-by-side cards or matrices for genuine alternatives and variants.
- Use controls only when changing an input teaches something or enables a real decision.
- Use a small editor when the output must be reordered, tuned, toggled, or exported back into the user's workflow.
- Use a slide deck only when pacing and sequential presentation matter.
What ships with it
24 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.
- agents/openai.yaml 219 B
- assets/examples/01-exploration-code-approaches.html 14 KB
- assets/examples/02-exploration-visual-designs.html 14 KB
- assets/examples/03-code-review-pr.html 26 KB
- assets/examples/04-code-understanding.html 17 KB
- assets/examples/05-design-system.html 18 KB
- assets/examples/06-component-variants.html 16 KB
- assets/examples/07-prototype-animation.html 12 KB
- assets/examples/08-prototype-interaction.html 11 KB
- assets/examples/09-slide-deck.html 16 KB
- assets/examples/10-svg-illustrations.html 18 KB
- assets/examples/11-status-report.html 16 KB
- assets/examples/12-incident-report.html 15 KB
- assets/examples/13-flowchart-diagram.html 15 KB
- assets/examples/14-research-feature-explainer.html 12 KB
- assets/examples/15-research-concept-explainer.html 13 KB
- assets/examples/16-implementation-plan.html 28 KB
- assets/examples/17-pr-writeup.html 24 KB
- assets/examples/18-editor-triage-board.html 18 KB
- assets/examples/19-editor-feature-flags.html 18 KB
- assets/examples/20-editor-prompt-tuner.html 21 KB
- assets/examples/index.html 38 KB
- assets/examples/LICENSE 1.0 KB
- references/example-catalog.md 4.0 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.
- 1mo ago First seen · 123 lines · 111 tokens per session scan A 9f55fa8c3007
dale-visualize is a skill published in the GitHub repository lubluniky/dale (54 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 111 tokens to every session and 1,128 once invoked, about $0.0004 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
loop-graph
Use only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained.
loop-research
Use only when the user explicitly invokes /loop-research or names this skill. Authors a loop-research run. Do not use unless named. Do not execute or resume generated runtime node files.
longgraph
Use only when the user explicitly invokes /longgraph or names this skill. Routes and authors a durable longgraph run. Do not use unless named. Do not execute or resume generated runtime node files.
loop-converge
Use only when the user explicitly invokes /loop-converge or names this skill. Authors a loop-converge run. Do not use unless named. Do not execute or resume generated runtime node files.
loop-deliver
Use only when the user explicitly invokes /loop-deliver or names this skill. Authors a loop-deliver run. Do not use unless named. Do not execute or resume generated runtime node files.
atelier
Atelier design intelligence (El DT + Impeccable). Use for UI/UX design, craft, critique, audit, polish, anti-slop, tokens, decks, and frontend iteration. Invoke /atelier [target]. Covers landing, dashboard, product UI, components, motion, a11y, and design system alignment.