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 arcasilesgroup/ai-engineering --skill ai-design-md-plannergit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-design-md-planner)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-design-md-planner"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-design-md-planner/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/arcasilesgroup/ai-engineering/ai-design-md-planner"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-design-md-planner.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 | $0.00157 | $0.03465 |
| Opus 5.5 | $0.00063 | $0.01386 |
| Sonnet 5.5 | $0.00031 | $0.00693 |
| Haiku 4.5 | $0.00016 | $0.00347 |
Grade A, and why
ai-design-md-planner 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 19d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DESIGN.md — design systems that don't look AI-generated
Two jobs, and the second one is the hard one.
Job one is mechanical: produce a valid DESIGN.md (Google's format — YAML token frontmatter + markdown rationale) that passes npx @google/design.md lint clean. The spec is bundled in references/designmd-spec.md; the CLI workflow and every lint rule is in references/cli.md.
Job two is taste: produce a system with an actual point of view. This is where almost every attempt fails, so it's worth understanding why it fails before starting.
Why AI design looks like AI design
When a model is asked for "a modern, clean design," it returns the statistical center of everything it has seen: indigo-violet primary, Inter, rounded-2xl with a soft shadow, a centered hero, a three-column feature grid with icons in tinted rounded squares. Each individual choice is defensible. Together they read as machine-made — not because they're ugly, but because they're unauthored. There is no person behind them, no argument, nothing that could have gone differently.
Real design reads as real because someone decided something and gave up something else in exchange. A design system with no sacrifices in it is slop.
So the working principle for this whole skill:
Every value in the file must trace to a source or an argument. Not "a nice blue" — this blue, because it's the oxide on weathered copper, or because it's the exact ink of a 1968 Braun manual, or because the product is used at 2am in a dark room and this is the only blue that survives at 4% opacity. If a token can't be defended, it was picked from the middle of the distribution and it will look like it.
references/anti-slop.md catalogs the specific defaults to avoid and, more usefully, what to do instead. Read it before writing any tokens — it's the highest-leverage file here.
Step 0 — Pick the mode
Codify-existing — the user points at a repo, a URL, screenshots, an existing brand, or says "match what we have." Their visual language already exists; the job is to extract it, judge it, and write it down.
What ships with it
8 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.
- 19d ago First seen · 171 lines · 157 tokens per session scan A 98369afe57f2
ai-design-md-planner is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 157 tokens to every session and 3,465 once invoked, about $0.0006 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 2026-09-27.
Other skills, from other repositories
skill-pages
AL page design patterns for Business Central. Use when creating Card, List, ListPart, Document pages, implementing page extensions, or designing UX layouts.
apex-python-diagrams
UTILITY SKILL — Python diagram generation for Azure architectures, WAF/cost/compliance charts, ERDs, swimlanes, timelines, and wireframes. WHEN: 'architecture diagram', 'WAF bar chart', 'cost chart', 'ERD', 'swimlane', 'timeline', 'wireframe'. DO NOT USE FOR: inline Mermaid diagrams (apex-mermaid).
figma-code-connect-components
Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For…
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…
design-assessment
WHAT - Evidence-based design-unit assessment orchestrated by project-assessment. Evaluates visual hierarchy, UX friction, interaction, a11y, responsiveness, design-system compliance, and distinctiveness with severity/confidence evidence citations. Reuses project-assessment-evidence semantics — no second framework.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.