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 murphytrueman/design-system-ops --skill designer-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/designer-onboarding)<a href="https://agentmods.dev/skills/murphytrueman/design-system-ops/designer-onboarding"><img src="https://agentmods.dev/badge/skills/murphytrueman/design-system-ops/designer-onboarding/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/murphytrueman/design-system-ops/designer-onboarding"><img src="https://agentmods.dev/badge/skills/murphytrueman/design-system-ops/designer-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 63 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00070 | $0.02325 |
| Opus 5 | $0.00035 | $0.01162 |
| Sonnet 5 | $0.00014 | $0.00465 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
designer-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 9d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designer onboarding
A skill for creating a practical onboarding guide for a designer joining a team that uses a design system. Output covers system philosophy, tooling setup, contribution norms, and a first contribution path — structured so a new team member can follow it without additional help.
Context
Onboarding documentation has a failure mode: it gets written for the person creating it, not the person reading it. It assumes context, skips steps that feel obvious to anyone who already knows the system, and leaves the new team member with a list of things to read rather than a path to follow.
The goal is an onboarding guide that a new designer could follow alone on their first day and feel oriented rather than overwhelmed. That means it has to be honest about what the system is and what it is not, explicit about where to get help, and structured so that early wins come before deep context.
Step 1: Gather the system context
Ask for or confirm:
- The design system name and the organisation or product context it serves
- The tooling stack: Figma library, documentation platform, component package, contribution tools
- The team structure: who owns the system, who the new designer's main contacts are
- The key contribution norms: what the process is for using components, raising gaps, and contributing new work
- Any known rough edges or caveats a new designer should know upfront
If specific details are not available (e.g. specific Figma library link), use placeholders clearly marked for the team to complete before the guide is published.
Small-system note (fewer than 5 components): For systems with fewer than 5 components, the onboarding guide should be shorter and more personal. The "what the system covers" section can be a brief list rather than a conceptual overview — with 3 components, name them. The "your first two weeks" timeline can compress to a first week, since there is less to explore. Replace the "when the system does not have what you need" section with a more prominent one: "what the system covers and what it does not" — at this size, the gaps are as important as the coverage, and a new designer should know both from day one. Emphasise human relationships over documentation: "Ask [name] to pair with you on your first task using the system" is more effective than "explore the documentation platform" when the documentation platform has three entries.
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.
- 9d ago First seen · 203 lines · 70 tokens per session scan A 5c8b13be0458
designer-onboarding is a skill published in the GitHub repository murphytrueman/design-system-ops (178 stars, last pushed 17d ago), licensed MIT. It adds 70 tokens to every session and 2,325 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…
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…
sheleg-design
A design skill for planning how websites, dashboards, mobile screens, and agent interfaces look and move, including cinematic pages with layered motion.