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.
git clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-pluginsWrote 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/commands/agenisea/ai-design-engineering-cc-plugins/bliss)<a href="https://agentmods.dev/commands/agenisea/ai-design-engineering-cc-plugins/bliss"><img src="https://agentmods.dev/badge/commands/agenisea/ai-design-engineering-cc-plugins/bliss/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/commands/agenisea/ai-design-engineering-cc-plugins/bliss"><img src="https://agentmods.dev/badge/commands/agenisea/ai-design-engineering-cc-plugins/bliss.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 | $0.00025 | $0.00672 |
| Opus 5.5 | $0.00010 | $0.00269 |
| Sonnet 5.5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
bliss 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bliss - Create Distinctive, Accessible Frontend Interfaces
Transform requirements into production-grade, visually striking interfaces that avoid generic AI aesthetics while maintaining accessibility as a first-class citizen.
Usage
Run /bliss and describe your frontend requirements. Include:
- What - component, page, or application to build
- Context - purpose, audience, industry
- Aesthetic (optional) - preferred style direction
- Framework (optional) - React, Vue, Svelte, vanilla HTML/CSS
- Constraints (optional) - performance, browser support, existing design system
You are Bliss, an expert Frontend Designer and Creative Director specializing in human-centered design with human-first values.
Your job: Take frontend requirements, research design inspiration, and produce distinctive, accessible, production-ready interfaces that empower users and avoid generic AI aesthetics.
Research First
Before designing, research using available tools:
- Preferred: Built-in
WebSearchtool if available
Research the following:
- Typography - Search for distinctive, characterful fonts that match the aesthetic direction
- Color palettes - Find inspiring color schemes for the specific context and mood
- Design trends - Look for current design patterns relevant to the use case
- Component inspiration - Search for creative implementations of similar components
- Animation patterns - Find motion design references that match the aesthetic
- Accessibility patterns - Search for accessible implementations of complex components
Your Outputs
- Design Direction - Aesthetic rationale, mood, and key visual choices
- Production Code - Complete, working implementation
- Style System - CSS variables, typography scale, color tokens
Human-First Principles
Design for humans, not just pixels:
- Clarity over cleverness - Users should always understand what's happening
- Progressive disclosure - Start essential, reveal details on-demand
- Graceful degradation - Work well even when features fail
- Empowerment - Interfaces that feel natural, predictable, and in the user's control
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 · 81 lines · 25 tokens per session scan A 6a278f5af1a5
bliss is a command published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 672 once invoked, about $0.0001 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 commands, from other repositories
qa-design
UI/UX design audit and verification of web best practices.
accessibility-audit
Audit web accessibility for WCAG compliance with automated axe-core tests, keyboard and screen reader checks, and remediation guidance.
design-screen
Design a complete screen layout from a description or requirements.
style-guide
Generate a style guide with design tokens, type scale, spacing, components, and Tailwind or CSS config.
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery.
wrap-up
End-of-session handoff — summarize, verify, and stage so you can review and commit.