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 rojim666/SztuCode --skill ardot-design-coregit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/ardot-design-core)<a href="https://agentmods.dev/skills/rojim666/sztucode/ardot-design-core"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/ardot-design-core/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/rojim666/sztucode/ardot-design-core"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/ardot-design-core.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 | $0.00138 | $0.03933 |
| Opus 5.5 | $0.00055 | $0.01573 |
| Sonnet 5.5 | $0.00028 | $0.00787 |
| Haiku 4.5 | $0.00014 | $0.00393 |
Grade A, and why
ardot-design-core scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Style-template shortcut — if `<ardot_design_style>` block is present:** the user picked a style template through the chip. Follow the injected `[style-template]` instruction: `curl` the referenced md URL, use that temp How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ardot Design Core
Foundational workflow and hard rules for completing design tasks on the Ardot canvas via the ardot MCP server. This skill is the shared base — it is injected together with one domain skill (UI design / slides / poster / design-to-code). All canvas manipulation MUST go through ardot MCP tools.
This skill owns how to work the canvas (workflow, schema, rules, effects). The paired domain skill owns what the deliverable should look like (domain guidelines). When the two seem to overlap, follow the domain skill for visual/layout decisions and this skill for tool usage and the step sequence.
Reference Files
Load on demand based on task type:
| File | When to load |
|---|---|
{SKILL_ROOT}/references/ardot-schema.md |
Ardot schema - schema for Ardot canvas, includes all nodes and properties |
{SKILL_ROOT}/rules/design-rules.md |
Single source of truth — editing principles, coordinates, flexbox, text, colors, tables, images, effects, SVG, property schema, troubleshooting, post-generation validation |
{SKILL_ROOT}/rules/style-guide.md |
Visual style guide — typography, color, layout, surface treatment, variance levels, forbidden AI patterns, bento grid |
{SKILL_ROOT}/rules/effects-guide.md |
Composite visual effects: glassmorphism, neon glow, metallic, glow border, iridescent, neumorphism — loaded automatically in Step 7 |
{SKILL_ROOT}/func-rule/component-instance/SKILL.md |
Components, instances, variants — insert/update refs, componentProperties, VARIANT, nested instance overrides, mainComponent swap. MUST load before editing any INSTANCE / COMPONENT / COMPONENT_SET, or when the user asks to switch state / variant |
{SKILL_ROOT}/func-rule/design-variables/SKILL.md |
Bind/unbind variables ($:Set:Var / $<id>), apply_variables, and node variableModes (theme / density). Load when binding tokens or switching modes. |
{SKILL_ROOT}/func-rule/shared-styles/SKILL.md |
Bind/unbind shared styles (textStyleId / fillStyleId / …). Load when applying style ids. |
{SKILL_ROOT}/workflows/ardot-workflow.md |
End-to-end workflow examples (create, modify, global style update, tokens, form) and detailed operation syntax |
{SKILL_ROOT}/tool-usage/batch-edit.md |
batch_edit tool usage guide — load anytime batch_edit is used (applies to every Ardot task) |
{SKILL_ROOT}/tool-usage/apply-variables.md |
apply_variables tool usage guide — load anytime apply_variables is used (applies to every Ardot task) |
What ships with it
10 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.
- func-rule/component-instance/SKILL.md 13 KB
- func-rule/design-variables/SKILL.md 6.9 KB
- func-rule/shared-styles/SKILL.md 1.6 KB
- references/ardot-schema.md 8.5 KB
- rules/design-rules.md 24 KB
- rules/effects-guide.md 7.1 KB
- rules/style-guide.md 12 KB
- tool-usage/apply-variables.md 2.3 KB
- tool-usage/batch-edit.md 18 KB
- workflows/ardot-workflow.md 8.4 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 · 143 lines · 138 tokens per session scan A 85065095f3f1
ardot-design-core is a skill published in the GitHub repository rojim666/SztuCode (110 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 3,933 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…
frontend-design
Designs and builds distinctive, production-quality frontend interfaces in HTML/CSS, React, or Tailwind: websites, landing pages, marketing pages, dashboards, web applications, interface components, and style overhauls. Classifies the surface as expressive, conventional, or governed by an existing design system, then…
ui-reviewer
Review rendered UI screenshots for hierarchy, spacing, readability, states, consistency, and visual slop.
design-system
DESIGN.md integration for Forge — ensures visual consistency across all UI tasks through standardized design specifications.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
iot-ai-web-visual-quality
Bounded visual-quality guidance for websites, dashboards, frontend UI, design systems and graphic prompts.