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 contribution-workflowgit 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/contribution-workflow)<a href="https://agentmods.dev/skills/murphytrueman/design-system-ops/contribution-workflow"><img src="https://agentmods.dev/badge/skills/murphytrueman/design-system-ops/contribution-workflow/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/contribution-workflow"><img src="https://agentmods.dev/badge/skills/murphytrueman/design-system-ops/contribution-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 242 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00060 | $0.03229 |
| Opus 5.5 | $0.00024 | $0.01292 |
| Sonnet 5.5 | $0.00012 | $0.00646 |
| Haiku 4.5 | $0.00006 | $0.00323 |
Grade A, and why
contribution-workflow 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 24d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribution workflow
A skill for creating a structured contribution workflow covering the full journey from proposal to release. Output is a document teams can actually follow — not a policy statement, but a process with named stages, decision criteria, and clear ownership at each gate.
Before you begin: verify references
Confirm that every path in this skill's frontmatter references: exists relative to this SKILL.md. If any is missing, stop: the install is incomplete, usually because a flattening installer (for example npx skills install) dropped the repo-root knowledge-notes/ directory. Tell the user to reinstall by a method in 1-INSTALL.md and run verify-install.sh from the install root. Proceed without the references only if the user explicitly says to, and then say in the output that it was produced without the pack's reference material.
Context
Most design systems have one of two contribution problems. Either there is no process, so contributions arrive inconsistently and the design systems team becomes a bottleneck because every request is a negotiation. Or there is a process that is so heavy it discourages contribution entirely, and teams build locally rather than bother.
The goal here is a workflow that is lightweight enough to not be a burden, structured enough to produce consistent quality, and honest enough to tell contributors what will and will not make it into the system.
The six-stage structure below reflects the full lifecycle of a contribution; it is the shape most published contribution models share (Nathan Curtis and Brad Frost have both written it up), not this pack's invention. Not every contribution needs all six stages at the same depth — a small enhancement to an existing component is lighter than a new foundational component. The workflow scales accordingly, and the output notes where the path diverges by contribution type.
Step 1: Understand the current state
Ask for or confirm:
- Does a contribution process already exist? If so, what is working and what is not?
- Who is responsible for design system maintenance — a dedicated team, shared responsibility, or a single person?
- What types of contributions are most common? (New components, enhancements, token changes, documentation, bug fixes)
- What is the team's capacity for reviewing and integrating contributions?
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.
- 24d ago Changed · -13 lines b03ef850a8c3
- 25d ago Changed · +7 lines · -39 tokens per session 07b221b66272
- 1mo ago First seen · 268 lines · 99 tokens per session scan A 6ffba34d8f42
contribution-workflow is a skill published in the GitHub repository murphytrueman/design-system-ops (208 stars, last pushed 25d ago), licensed MIT. It adds 60 tokens to every session and 3,229 once invoked, about $0.0002 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 2026-08-30.
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.
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…
generate-figma-screen
Kod veya açıklamadan Figma'da tam ekran/sayfa oluşturur. Yayınlanmış design system bileşenlerini arayıp instance olarak yerleştirir; hardcode değer yerine DS token'larını kullanır. "Figma'da ekran oluştur", "kodu Figma'ya çevir", "landing page çiz", "ekran tasarla", "generate screen", "UI'ı Figma'ya aktar"…
fmcp-intent-router
F-MCP ile ilgili herhangi bir kullanıcı talebinin ilk giriş noktası. Kullanıcının niyetini analiz eder, hangi hedef SKILL'in çalıştırılacağına karar verir, o SKILL için gereken eksik input'ları tek turda toplar, özet+onay alır ve ondan sonra hedef SKILL'i çalıştırır. "figma", "ekran oluştur", "tasarım yap", "component…
fmcp-screen-recipes
Fast path cookbook — standart ekran tipleri (login/payment/profile/list/detail/form/onboarding/dashboard/settings) için 5 mega-adımlı recipe. Max 15 op/execute, cache-first discovery, her adımda Türkçe micro-report.