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/murphytrueman/design-system-ops/engineering-onboardingnpx skills add murphytrueman/design-system-ops --skill engineering-onboardinggit clone --depth 1 https://github.com/murphytrueman/design-system-opsWrote 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/murphytrueman/design-system-ops/engineering-onboarding)<a href="https://agentmods.dev/skills/murphytrueman/design-system-ops/engineering-onboarding"><img src="https://agentmods.dev/badge/skills/murphytrueman/design-system-ops/engineering-onboarding.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.03264 |
| Opus 5 | $0.00034 | $0.01632 |
| Sonnet 5 | $0.00014 | $0.00653 |
| Haiku 4.5 | $0.00007 | $0.00326 |
Grade A, and why
engineering-onboarding 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 5d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Engineering onboarding is genuinely different from designer onboarding. The mental model is different (consuming an API vs composing with a library), the first tasks are different (install and import vs connect Figma library), the tooling is different (package manager, TypeScript types, test harness vs Figma, documentation platform). Most importantly, engineers are where component drift originates — wrapping system components in local styled wrappers, hardcoding token values, reimplementing components locally. Proper onboarding from day one is the highest-leverage adoption intervention.
Key principles
From design-to-code-contract: Engineers and designers operate on opposite sides of the contract. Designers compose with a library (Figma, Storybook). Engineers consume an API (imports, props, types). The contract is the component signature: what props it accepts, what slots it exposes, what variants are possible. Component drift begins when an engineer builds a local wrapper because "the system component is close but not quite right" — escalating to designers too late means the system lost control. Onboarding embeds the contract from day one.
Key principle for engineers: Do not wrap system components. Do not hardcode values. Do not copy source code. Ask first.
Configuration
Before writing the guide, gather these inputs:
- Framework: React, Vue, Web Components, Svelte, Angular, etc.
- Package manager: npm, yarn, pnpm (include install command)
- Token consumption: CSS custom properties, JavaScript imports, Tailwind theme config, Sass variables
- Component API patterns: Props, slots, composition style, controlled vs uncontrolled patterns
- TypeScript: Are component types exported? Import pattern for types?
- Testing: Visual regression tool (Chromatic, Percy), unit testing patterns, accessibility testing expectations
- Contribution path: How does an engineer propose a fix or new component? PR process, code review, approval gates
- Known rough edges: Documented workarounds, temporary incompatibilities, or known limitations
- Team contacts: Slack channel, primary system maintainer, office hours schedule
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.
- 5d ago First seen · 376 lines · 68 tokens per session scan A 1f995ef1934c
engineering-onboarding is a skill published in the GitHub repository murphytrueman/design-system-ops (174 stars, last pushed 13d ago), licensed MIT. It adds 68 tokens to every session and 3,264 once invoked, about $0.0003 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
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
roast-my-design-system
Roast the current repo's design system with real data. Runs a deterministic scanner (no tokens, 1s) that counts everything that betrays a design system, from colours and their near-identical twins to greys, spacing values, typefaces, duplicated and never-imported components, inline styles, !important and arbitrary…
presentation-video
This skill should be used when the user asks to "make an animated presentation", "turn a pitch deck into a video", "convert slides/a deck to video", "make a presentation video", "build a deck video", "narrate a slide deck as a video", or "auto-advance slides synced to a voiceover". Covers rebuilding slides as motion…
manim
This skill should be used when the user asks to "make a math animation", "animate an equation", "use Manim", "make a 3Blue1Brown-style video", "plot or animate a graph/function", "visualize a math/physics/CS concept", "morph one formula into another", "animate a geometric proof", or "render a math explainer". Covers…