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 brcampidelli/chimera-agent --skill do-not-ship-an-empty-surfacegit clone --depth 1 https://github.com/brcampidelli/chimera-agentWrote 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/brcampidelli/chimera-agent/do-not-ship-an-empty-surface)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/do-not-ship-an-empty-surface"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/do-not-ship-an-empty-surface/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/brcampidelli/chimera-agent/do-not-ship-an-empty-surface"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/do-not-ship-an-empty-surface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00598 |
| Opus 5 | $0.00019 | $0.00299 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
do-not-ship-an-empty-surface 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
You are about to ship a navigable destination that will be empty for most users: a tab with no rows, a category with no entries, a dashboard whose data source is not wired up, a page that says "coming soon".
It does not apply to a surface that is empty because the user has not done anything yet. A task list with no tasks is correct, and should say how to add one.
Do
- Decide which kind of empty it is. Empty-because-the-user-is-new needs a good empty state with the next action in it. Empty-because-we-have-not-built-it needs to not be there.
- For the second kind: do not render the destination at all. Generate the route only when there is something behind it.
- If it must exist for development, gate it on a development flag so an installed build cannot reach it.
- Where the emptiness is genuinely the news — a hub with one entry, a feed just started — say so in words, and make the invitation to contribute the main content of the page.
Avoid
"Coming soon", "No data yet" with no explanation, and a nav entry that leads to a blank column. Each one costs the reader a click and returns nothing, and after two of them they stop trusting the navigation — a cost paid by every other page in the product.
Avoid also the version that looks fine: a category page that renders correctly with zero items. It does not look broken, so nobody reports it, and it quietly says the project abandoned that topic.
Check
Load the surface with an empty data source and read what a first-time user would see. If the answer is a heading and whitespace, it should not have shipped.
For generated routes the check is mechanical: assert that the route list is derived from the content, so a category with no entries produces no page at all.
Risk
Hiding a destination until it has content makes navigation shift as data arrives, which can be disorienting — a menu that grows between visits needs a reason the user can infer.
This can also be taken too far, into hiding features that are merely unpopular. The line is whether the surface can ever show something: unbuilt is hidden, unused is shown with a good empty state.
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 · 62 lines · 39 tokens per session scan A c4dbc6291edf
do-not-ship-an-empty-surface is a skill published in the GitHub repository brcampidelli/chimera-agent (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 598 once invoked, about $0.0002 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
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
web-artifacts-builder-v2
Suite of tools for creating elaborate, multi-component claude.ai HTML artefacts using modern frontend web technologies (React 19, Tailwind CSS v4, shadcn/ui). Use for complex artefacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artefacts.
diagrams-as-code
Use only when creating architecture diagrams with Python's diagrams library (mingrammer/diagrams).
mermaid-diagrams
Use the mermaid-diagrams skill whenever you are creating or updating mermaid diagrams. Provides guidance on mermaid best practices.
html-design-examples
Reference gallery of polished single-file HTML artifacts demonstrating effective ways to communicate ideas through HTML. Use when the user wants to explain, showcase, demo, plan, review, or present an idea within an HTML file.
analyse-design
Reverse-engineer an application, website or document's design system from its codebase and screenshots. Use when asked to analyse visual design, extract a colour palette, document UI patterns, identify typography and spacing systems, audit design consistency, or understand the design language of a frontend codebase.