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 jamiemill/layers-skills --skill layers-surfacegit clone --depth 1 https://github.com/jamiemill/layers-skillsWrote 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/jamiemill/layers-skills/layers-surface)<a href="https://agentmods.dev/skills/jamiemill/layers-skills/layers-surface"><img src="https://agentmods.dev/badge/skills/jamiemill/layers-skills/layers-surface.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk 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 | $0.00029 | $0.01140 |
| Opus 5 | $0.00015 | $0.00570 |
| Sonnet 5 | $0.00006 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
layers-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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/layers-surface
Assumes /layers-intro has been loaded. This skill is a library of techniques, not a script — see "How to use these skills" there.
The surface layer is where everything decided below becomes something a person actually encounters: words, sounds, visuals, physical affordances, motion, feedback. It's the most medium-specific layer, but the decisions that matter most first are universal — they hold whether the surface is a screen, voice interface, physical device, or service touchpoint.
Surface problems are often symptoms of deeper ones. The central discipline here is telling apart issues you can fix at the surface from issues that need a lower layer revisited.
The decisions this layer makes
- Whether the surface honours the vocabulary and objects from the conceptual model
- Whether every affordance from the breadboard is present — and whether any surface element has no model behind it
- Whether the emotional register fits the jobs users are doing
- How the user knows what happened, what's in progress, and what went wrong
- What's most prominent, and whether it should be
- Whether everything is accessible to the users who need it
Disciplines — what keeps the surface honest
- Surface fix vs deeper-layer issue. The key judgement: is this something to fix in the copy/layout, or a symptom whose root is in the conceptual model or interaction flow? Wrong vocabulary may be a rewrite — or a model that never settled the term. Route deeper issues back to the relevant skill rather than patching the symptom.
- Terms match the ubiquitous language. Flag direct violations (a model term used inconsistently), unlisted terms (surface words not in the model — add to model, or remove as noise), and tone misalignments.
- Object consistency. No shapeshifters (same object in significantly different forms across contexts), no masked objects (a form where the user can't recognise the object type).
- Completeness both ways. Every breadboard affordance is present; no surface element exists with no model or flow behind it (those are interaction decisions that slipped through — route to
/layers-interaction-flow). - Errors diagnose, explain, recover. "Something went wrong" fails all three. Flag every error state that doesn't do all three.
- Prominence reflects importance. What the flow needs the user to notice is what stands out; nothing prominent that shouldn't be.
- Accessibility is decided, not defaulted.
- Emotional register matches the emotional and social jobs from user needs — not the product's benefit framed as the user's.
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.
- 8d ago First seen · 67 lines · 29 tokens per session scan A 2ffa29c0466b
layers-surface is a skill published in the GitHub repository jamiemill/layers-skills (299 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 1,140 once invoked, about $0.0001 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.