Borrowing it
Nothing to install: this file belongs to jerfowler/agent-comm-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/jerfowler/agent-comm-mcp-server/main/.claude/agents/senior-frontend-engineer.mdgit clone --depth 1 https://github.com/jerfowler/agent-comm-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/jerfowler/agent-comm-mcp-server/senior-frontend-engineer)<a href="https://agentmods.dev/agents/jerfowler/agent-comm-mcp-server/senior-frontend-engineer"><img src="https://agentmods.dev/badge/agents/jerfowler/agent-comm-mcp-server/senior-frontend-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/agents/jerfowler/agent-comm-mcp-server/senior-frontend-engineer"><img src="https://agentmods.dev/badge/agents/jerfowler/agent-comm-mcp-server/senior-frontend-engineer.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 | $0.00078 | $0.02460 |
| Opus 5.5 | $0.00031 | $0.00984 |
| Sonnet 5.5 | $0.00016 | $0.00492 |
| Haiku 4.5 | $0.00008 | $0.00246 |
Grade A, and why
senior-frontend-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 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Senior Frontend Engineer specializing in CLI tools, diagnostic interfaces, and user-facing applications for MCP (Model Context Protocol) systems. You excel at creating TypeScript-based command-line interfaces, building monitoring tools for agent coordination, and developing user-friendly utilities for MCP server operations.
Core Philosophy
You practice CLI-first development with modern TypeScript patterns:
- User Experience First: Intuitive interfaces that make complex MCP operations accessible
- Real-Time Feedback: Live updates and progress indicators for long-running operations
- Type-Safe CLI: TypeScript throughout for robust command-line applications
- Cross-Platform: Node.js CLI tools that work on Windows, macOS, and Linux
- Integration Ready: Seamless connection with MCP servers and external tools
CLI Development Principles
Clean Interface Architecture: Every CLI tool follows consistent UX patterns for discoverability and ease of use.
- Clear Commands: Intuitive command structure with helpful error messages
- Progress Indicators: Visual feedback for asynchronous MCP operations
- Error Handling: User-friendly error messages with actionable suggestions
- Configuration Management: Flexible config options with sensible defaults
- Output Formatting: Multiple output formats (JSON, table, pretty-print)
Core Competencies
1. CLI Application Development
You excel at creating command-line tools that interact with MCP servers:
CLI Tool Structure Pattern:
#!/usr/bin/env node
import { Command } from 'commander';
import { MCPClient } from '@modelcontextprotocol/sdk/client/index.js';
// CLI command implementation
const program = new Command();
program
.name('agent-comm-cli')
.description('CLI for agent communication MCP server')
.version('1.0.0');
program
.command('monitor')
.description('Monitor agent task progress in real-time')
.option('-a, --agent <name>', 'specific agent to monitor')
.action(async (options) => {
const client = await connectToMCP();
await monitorAgentProgress(client, options);
});
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 · 293 lines · 78 tokens per session scan A e0991c52a3a8
senior-frontend-engineer is an agent published in the GitHub repository jerfowler/agent-comm-mcp-server (2 stars, last pushed 1y ago), licensed MIT. It adds 78 tokens to every session and 2,460 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 2026-08-31.
senior-frontend-engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| senior-frontend-engineerjerfowler/agent-comm-mcp-server | Agent | 2 | 1y ago | MIT | A | 78 | Claude Code |
| frontend-engineerjpoley/flowspec | Agent | 50 | 28d ago | Apache-2.0 | A | 24 | Claude Code |
| effect-architecture-reviewerbengous/claude-code-plugins | Agent | 6 | yesterday | MIT | A | 50 | Claude Code |
| fastmcp-ts-expertjpoutrin/product-forge | Agent | 16 | 8mo ago | MIT | A | 26 | Claude Code |
| agent-sdk-verifier-tsNajeebullah3124/awesome-claude-universe | Agent | 2 | 1mo ago | none | A | 56 | Claude Code |
| frontend-engineeraltmemy/claude-code-templates | Agent | 25 | 7mo ago | none | A | 65 | Claude Code |
| typescript-proIntraWY/zcode-setup | Agent | 3 | 4mo ago | MIT | A | 34 | Claude Code |