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 vmobifystudio/app-dev-team --skill content-designgit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/content-design)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/content-design"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/content-design/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/vmobifystudio/app-dev-team/content-design"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/content-design.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 | $0.00069 | $0.00632 |
| Opus 5.5 | $0.00028 | $0.00253 |
| Sonnet 5.5 | $0.00014 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
content-design 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 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.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content design
The interface is mostly words. Words written last, by whoever was implementing, are the ones users actually read.
Buttons and labels
- A button says what happens when you press it.
Save changes, notOK.Delete 3 photos, notConfirm. - A destructive button names what is destroyed and whether it comes back. "This cannot be undone" belongs in the dialog, not in the button.
- Sentence case throughout. Never end a button label with a full stop.
Cancelmeans "nothing happens". Never label a buttonCancelwhen something happens.
Errors — three parts, always
- What happened, in the user's terms, not the system's.
- Whether their data is safe. This is the question they are actually asking.
- What to do next, as an action they can take right now.
Something went wrong fails all three. Couldn't save — your note is still here. Retry when you're back online. passes all three in one line. Never show an error code without also showing prose,
and never show raw exception text.
Empty states
An empty state is not a blank screen with an apology. It says what belongs here, why it is empty (new, filtered, or failed — three different states, three different messages), and the one action that fills it.
Permission prompts
Ask at the moment of need, never at launch. The prompt says what the user gets, not what the app
wants. The system string (NSCameraUsageDescription etc.) is written by you, not by an engineer at
build time — and a denied permission needs a working path, not a dead end.
The rules
- Every user-visible string goes into the localisation file from the moment it is written.
Retrofitting is far more expensive and is where hardcoded strings survive to ship (
localisation). - No placeholder text reaches a build.
Lorem ipsum,TODO,Testin a screenshot is an ASO and a review failure at once. - One term per concept, product-wide. A record is not an "item" here and an "entry" there. Keep
the list in
docs/14-components.md. - Numbers, dates, currencies and plurals are formatted by the platform's locale-aware API — never by string concatenation.
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 · 57 lines · 69 tokens per session scan A 74fdc33e865e
content-design is a skill published in the GitHub repository vmobifystudio/app-dev-team (5 stars, last pushed 13d ago), licensed MIT. It adds 69 tokens to every session and 632 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
wireframe
Produce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframes.
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
fidelity-gate
Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
ux-grill
Use when a running web app's UX has to be audited reproducibly rather than by feel — a deterministic mechanical pass over routes and viewports (axe, target size, horizontal overflow, page title, scripted journeys) followed by a screenshot-grounded interrogation of the operator, journey by journey, with two persona…