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/plugins/agenisea/ai-design-engineering-cc-plugins/ai-design-engineer)<a href="https://agentmods.dev/plugins/agenisea/ai-design-engineering-cc-plugins/ai-design-engineer"><img src="https://agentmods.dev/badge/plugins/agenisea/ai-design-engineering-cc-plugins/ai-design-engineer/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/plugins/agenisea/ai-design-engineering-cc-plugins/ai-design-engineer"><img src="https://agentmods.dev/badge/plugins/agenisea/ai-design-engineering-cc-plugins/ai-design-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ai-design-engineer 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.
What it actually says
{
"name": "ai-design-engineer",
"version": "1.3.0",
"description": "Human-first AI Design Engineer toolkit with 8 specialized personas for resilient agentic systems: Blueprompt (app specs), Brooks (JTBD methodology), Agenisea (multi-agent architecture), Atlas (data & ML architecture), Argus (security), Angel (backend systems), Clarity (human-first UX research & strategy), and Bliss (human-centered UI).",
"author": {
"name": "Patrick Peña"
},
"license": "MIT",
"homepage": "https://github.com/agenisea/ai-design-engineering-cc-plugins",
"repository": "https://github.com/agenisea/ai-design-engineering-cc-plugins",
"keywords": [
"human-first",
"human-centered-design",
"human-ui-ux",
"resilient-ai",
"ai-design-engineer",
"ai-design-engineering",
"ai-engineering",
"frontend-design",
"multi-agent-architecture",
"agentic-applications",
"jtbd",
"accessibility",
"ui-components",
"agentic-systems",
"agentic-system-design",
"agentic",
"agent-security",
"agent-auth",
"backend-architecture",
"backend-systems",
"reliability-engineering",
"ux-research",
"ux-strategy",
"information-architecture",
"user-research",
"wireframing",
"rag-architecture",
"embeddings",
"ml-architecture",
"model-selection",
"evaluation-framework",
"knowledge-systems",
"vector-databases",
"data-pipelines"
],
"commands": [
"./commands/bliss.md",
"./commands/blueprompt.md",
"./commands/agenisea.md",
"./commands/brooks.md",
"./commands/argus.md",
"./commands/angel.md",
"./commands/clarity.md",
"./commands/atlas.md"
],
"agents": [
"./agents/blueprompt.md",
"./agents/brooks.md",
"./agents/agenisea.md",
"./agents/argus.md",
"./agents/clarity.md",
"./agents/bliss.md",
"./agents/angel.md",
"./agents/atlas.md"
]
}
What it installs
The manifest is a name and a version. 8 skills, 8 commands, 8 agents travel with it, and installing the plugin installs all of them — 888 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill blueprompt A 50 tokens
- Skill atlas A 51 tokens
- Skill angel A 52 tokens
- Skill argus A 43 tokens
- Skill bliss A 48 tokens
- Skill clarity A 47 tokens
- Skill agenisea A 47 tokens
- Skill brooks A 45 tokens
- Command blueprompt A 28 tokens
- Command atlas A 21 tokens
- Command angel A 16 tokens
- Command argus A 22 tokens
- Command bliss A 25 tokens
- Command clarity A 33 tokens
- Command agenisea A 21 tokens
- Command brooks A 24 tokens
- Agent clarity A 49 tokens
- Agent atlas A 43 tokens
- Agent agenisea A 39 tokens
- Agent angel A 32 tokens
- Agent argus A 32 tokens
- Agent bliss A 38 tokens
- Agent blueprompt A 46 tokens
- Agent brooks A 36 tokens
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 · 68 lines scan A f8794dab186c
ai-design-engineer is a plugin published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 7mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
accessibility-compliance
WCAG accessibility auditing, compliance validation, UI testing for screen readers, keyboard navigation, and inclusive design.
brand-landingpage
Guides developers from brand discovery through iterative design to deployment-ready HTML via Stitch.
aka-claude-tools
AKA Claude Tools guard hooks (command-guard, leak-guard, mcp-guard, post-guard) for your active profile. Requires bun. If bun is missing, the guards fail OPEN (the tool call proceeds) and announce themselves inactive at session start; with bun present, mcp-guard blocks on its own errors. For the full hardened ISOLATED.
shadcn
UI component and design system framework. Search registries, install components as source code, and audit your project.
clone-team
Clone any website with a team of AI agents — pixel-perfect UI clone plus reverse-engineered architecture docs. Built on Claude Code's dynamic Workflow engine with an unskippable test gate; fully pausable and resumable.
ui-data-skills
Data visualization, tables, and dashboard components for displaying and analyzing data.