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 rtazima/claude-proj-blueprint --skill frontend-agentgit clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/frontend-agent)<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/frontend-agent"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/frontend-agent/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/rtazima/claude-proj-blueprint/frontend-agent"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/frontend-agent.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 | $0.00031 | $0.00565 |
| Opus 5 | $0.00015 | $0.00282 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
frontend-agent 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Agent — Design-to-Code without Figma
When this skill activates
- User runs
/implementon a PRD that has no Figma link - User asks to build UI, create a page, or implement a component
- PRD contains frontend requirements but no design reference
Workflow
- Load design tokens from
docs/specs/design-system/README.md - Identify component library — read which library the project uses
- Scan existing UI — grep for existing pages/components to match visual patterns
- Read PRD requirements — extract user stories, screens, interactions
- Generate UI following the rules below
- Self-review — verify tokens are used, no hardcoded values, responsive, accessible
Generation rules
Tokens first
- ALWAYS read
docs/specs/design-system/README.mdbefore generating any UI - Use CSS variables / theme tokens — never hardcode
#hex,pxspacing, or font names - If a token is missing, flag it and suggest adding to the design system
Consistency
- Before creating a new component, search for similar existing ones
- Match the layout patterns, spacing rhythm, and interaction patterns of existing screens
- Reuse existing components — don't create duplicates
Component structure
- One component per file
- Props interface defined (TypeScript)
- Default to the project's component library (shadcn, Radix, etc.)
- Include variants: default, loading, empty, error states
- Responsive by default (mobile-first)
Accessibility
- Semantic HTML elements
- ARIA labels on interactive elements
- Keyboard navigable
- Color contrast meets WCAG AA (4.5:1 text, 3:1 large text)
- Focus indicators visible
What NOT to do
- Never generate pixel-perfect mockup replicas without tokens
- Never hardcode colors, spacing, or typography
- Never skip empty/error/loading states
- Never create a component that duplicates an existing one
- Never ignore the project's component library choice
Output format
When generating a new page or component:
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 · 68 lines · 31 tokens per session scan A 3a3e4109b0b4
frontend-agent is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 565 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
mandu-composition
React composition patterns for Mandu applications. Use when designing Island components, managing shared state, or building reusable component APIs. Triggers on compound components, context providers, boolean props, or component architecture tasks.
Mandu Styling
Tailwind CSS v4 integration and Island styling patterns for Mandu Framework.
mandu-hydration
Island Hydration pattern for Mandu. Use when creating interactive components, client-side state, or partial hydration. Triggers on tasks involving "use client", client.tsx, useState, useEffect, Island, or hydration.
Mandu UI
UI component library integration and accessibility patterns.
mandu-fs-routes
File-system based routing for Mandu. Use when creating pages, API routes, layouts, or dynamic routes. Triggers on tasks involving app/ folder, page.tsx, route.ts, layout.tsx, [id], [...slug], or URL patterns.
screenshot-studio
Regenerate the Pisper product screenshots under docs/shots/ against the current UI. Starts an isolated dev instance, seeds fictional demo data through the real runtime APIs, captures every referenced page at the exact 2558x1380 asset size, and replaces the files. Use only when the user asks to refresh product…