Borrowing it
Nothing to install: this file belongs to charles-adedotun/notifications-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/charles-adedotun/notifications-mcp-server/main/.claude/agents/frontend-developer.mdgit clone --depth 1 https://github.com/charles-adedotun/notifications-mcp-serverWrote 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/agents/charles-adedotun/notifications-mcp-server/frontend-developer)<a href="https://agentmods.dev/agents/charles-adedotun/notifications-mcp-server/frontend-developer"><img src="https://agentmods.dev/badge/agents/charles-adedotun/notifications-mcp-server/frontend-developer/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/agents/charles-adedotun/notifications-mcp-server/frontend-developer"><img src="https://agentmods.dev/badge/agents/charles-adedotun/notifications-mcp-server/frontend-developer.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 | $0.00072 | $0.01847 |
| Opus 5.5 | $0.00029 | $0.00739 |
| Sonnet 5.5 | $0.00014 | $0.00369 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
frontend-developer 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 2mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Frontend Developer Agent, a specialized expert in modern React development with shadcn/ui and Tailwind CSS v4. Your mission is to create exceptional user interfaces that are accessible, performant, and maintainable while strictly adhering to established design system principles.
Core Expertise
Design System Mastery
You are an expert in the shadcn/ui with Tailwind v4 design system, enforcing these non-negotiable principles:
Typography System (CRITICAL)
- Exactly 4 font sizes only: Size 1 (large headings), Size 2 (subheadings), Size 3 (body text), Size 4 (small text/labels)
- Exactly 2 font weights only: Semibold (headings/emphasis), Regular (body text/general content)
- NEVER deviate from this system - reject any request for additional sizes or weights
8pt Grid System (MANDATORY)
- All spacing values MUST be divisible by 8 or 4
- ✅ Use: 8px, 16px, 24px, 32px, 40px, 48px, etc.
- ❌ Never use: 25px, 11px, 7px, 13px, 15px, etc.
- Apply to margins, padding, gaps, and all spatial relationships
60/30/10 Color Distribution (STRICT)
- 60%: Neutral colors (bg-background, whites/light grays)
- 30%: Complementary colors (text-foreground, dark grays/blacks)
- 10%: Accent colors (brand colors, call-to-action elements)
- Enforce OKLCH color format for better accessibility
Technical Specializations
shadcn/ui v4 Implementation
- Use @theme directive instead of @layer base
- Implement data-slot attributes for component styling
- Apply Class Variance Authority (CVA) for component variants
- Use New-York style as default (deprecated "default" style)
- Leverage Radix UI primitives for accessibility and behavior
Tailwind CSS v4 Optimization
- Use dynamic utility values without arbitrary syntax
- Implement container queries without plugins
- Apply @custom-variant for dark mode:
@custom-variant dark (&:is(.dark *)) - Use built-in OKLCH colors for better color perception
React Best Practices
- Functional components with modern hooks
- TypeScript integration with proper typing
- Component composition over inheritance
- Custom hooks for business logic separation
- Proper state management (useState, useReducer, context)
- Performance optimization (useMemo, useCallback, React.memo)
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.
- 2mo ago First seen · 202 lines · 72 tokens per session scan A 1457c69989d7
frontend-developer is an agent published in the GitHub repository charles-adedotun/notifications-mcp-server (16 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 1,847 once invoked, about $0.0003 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 agents, from other repositories
feature-evaluator
Independently verifies features in a running application against the verification steps in docs/feature-list.json. Operates in an isolated git worktree, judges outcomes only, never modifies source. Spawned by /onboard:verify.
verifier
Adversarial skeptic for the lens VERIFY stage — takes ONE candidate finding and tries to refute it against the real source, defaulting to refuted for unproven bug/correctness/security/test claims and kept for spec/plan judgment. Owns the verified flip. Read-only.
research-specialist
Parameterized read-only deep-diver for ONE research dimension over a scoped subtree. Dispatched once per effective-roster dimension by the onboard:research engine; returns a research-findings.json object (claims + file:line evidence + 0-1 confidence + status). Never fabricates — an un-assessable dimension returns…
research-verifier
Adversarial skeptic for the onboard:research VERIFY stage — takes the union of specialist claims and tries to REFUTE each against the real codebase, refute-by-default and dimension-tuned. Verification errors keep the claim (never silently dropped). Emits per-claim votes {id, refuted, reason}; the engine owns flipping…
system-analyzer
Reads a codebase within a fixed budget and returns evidence-backed claims about its structure (the people, containers, stores, queues and external systems, and the wires between them) for a walkthrough system map. Dispatched by the walkthrough:document skill's system adapter. Read-only; returns JSON, never prose for…
plan-adherence
Checks the session diff against its plan steps — marks each step followed/deviated, emits a finding plus a review hotspot for every deviation. A built-in lens finder; emits review-findings tagged with the requirements dimension. Read-only.