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 | $0.00056 | $0.00564 |
| Sonnet 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 12d 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.
- 12d ago First seen · 123 lines · 111 tokens per session scan A 9f55fa8c3007
dale-visualize is a skill published in the GitHub repository lubluniky/dale (51 stars, last pushed 6d ago), licensed MPL-2.0. It adds 111 tokens to every session and 1,128 once invoked, about $0.0006 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
agent-creation-skill
Procedural guide for creating new agents from templates when project complexity requires delegation.
memory-fabric
Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting. Unifies search results ranked by recency, relevance, and authority. Use when designing memory retrieval, building entity graphs, or optimizing knowledge graph…
loop-graph
Compile one durable loop-graph run into executor, ledger, directives, ops, and supervisor artifacts under a dated .longgraph directory, then present copy-ready host prompts. Use directly for a custom multi-round shape with gated milestones, independent audit, cross-host execution, or durable state; focused sibling…
longgraph
Route and author durable long-horizon loop-graph runs. Use for multi-round work needing durable state, gated milestones, owner boundaries, host switching, or independent audit. Route code cleanup to /loop-converge, feature requirements to /loop-deliver, and evidence-backed solution comparison to /loop-research; use…
loop-converge
Author and optionally direct-launch a two-node loop-graph run whose North Star is code convergence — delete unused code, merge duplicates, reuse, slim. Use when the user invokes /loop-converge, or asks to loop on dead code, duplication, unused exports, DRY cleanup, or merging twin implementations. Starts the owner…
loop-deliver
Author and optionally direct-launch a two-node loop-graph run for implementing a product or engineering requirement through verified vertical slices. Use when a requested feature, integration, migration, or behavior change needs multiple rounds, durable acceptance proof, and independent audit. Not for code cleanup…