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 lossless-group/lossless-agent-skills --skill theme-systemgit clone --depth 1 https://github.com/lossless-group/lossless-agent-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/lossless-group/lossless-agent-skills/theme-system)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/theme-system"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/theme-system/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/lossless-group/lossless-agent-skills/theme-system"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/theme-system.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 | $0.00087 | $0.01066 |
| Opus 5 | $0.00044 | $0.00533 |
| Sonnet 5 | $0.00017 | $0.00213 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
theme-system 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Theme System
The Lossless Group's firm-wide conventions for theme architecture, visual modes, and design token systems.
Status: Initial scaffold (May 2026) — actively developing from astro-knots patterns.
When to use this skill
- Setting up theme/mode architecture for a new site
- Debugging mode toggle issues (light/dark/vibrant not working)
- Implementing two-tier token systems
- Deciding between
theme.cssvsglobal.cssorganization - Creating
/brand-kitor/design-systemreference pages - User mentions "vibrant mode", "two-tier tokens", "mode switcher", "theme architecture"
Core Principles (WIP)
1. Three-Mode Contract (Not Two)
Every Lossless site ships with three modes, not two:
- Light — clean, minimal, high readability
- Dark — code-editor feel, moderate intensity
- Vibrant — neon energy, loud gradients, glassmorphic surfaces
Why three? Stakeholder management. Nerds pick dark, traditionalists pick light, design-forward stakeholders pick vibrant. The toggle ends the "which mode" argument before it starts.
Critical: Vibrant mode is dark-based (like dark mode, not light mode). Common error: vibrant inherits light mode's white background. See references/vibrant-mode-implementation.md (TBD).
2. Two-Tier Token System
Tokens come in two tiers:
- Tier 1: Named tokens (
--color__blue-azure,--font__lato)- Raw values, BEM-ish
__separator - Private to the theme (components don't read these directly)
- Raw values, BEM-ish
- Tier 2: Semantic tokens (
--color-primary,--font-body)- Kebab-case, what Tailwind utilities and components consume
- Reference named tokens via
var()
Why two tiers? Client iteration. When a client wants a different primary color, you add/change a named token and re-point the semantic token. Components don't change.
See references/two-tier-tokens.md (TBD).
3. File Organization
theme.css— all token definitions (named + semantic), mode blocksglobal.css— imports@tailwindcss, importstheme.css, base resets
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 96 lines · 87 tokens per session scan A f4490dece027
theme-system is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 16d ago), licensed MIT. It adds 87 tokens to every session and 1,066 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
gsd-sketch
Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode).
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases.
gsd-ui-review
Retroactive 6-pillar visual audit of implemented frontend code.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…
userinterface-wiki
UI/UX best practices for web interfaces. Use when reviewing animations, CSS, audio, typography, UX patterns, prefetching, or icon implementations. Covers 11 categories from animation principles to typography. Outputs file:line findings.