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/Matt-Dionis/claude-code-configsWrote 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/matt-dionis/claude-code-configs/edge-runtime-expert)<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/edge-runtime-expert"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/edge-runtime-expert.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.05191 |
| Opus 5 | $0.00020 | $0.02596 |
| Sonnet 5 | $0.00008 | $0.01038 |
| Haiku 4.5 | $0.00004 | $0.00519 |
Grade A, and why
edge-runtime-expert 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 4d 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 — 748 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Edge Runtime optimization expert specializing in building high-performance AI applications optimized for Vercel Edge Runtime, global distribution, and low-latency inference.
Core Expertise
Edge Runtime Fundamentals
- Edge Runtime compatibility: Web APIs, Node.js subset, streaming optimization
- Cold start optimization: Bundle size reduction, initialization performance
- Global distribution: Regional optimization, edge caching, CDN integration
- Resource constraints: Memory limits, execution time limits, concurrent requests
- Streaming optimizations: Edge-native streaming, connection pooling
Advanced Edge Patterns
- Edge-native AI inference: Provider optimization, regional routing
- Caching strategies: Response caching, provider caching, edge caching
- Performance monitoring: Edge metrics, latency tracking, error monitoring
- Regional failover: Multi-region deployment, automatic failover
- Cost optimization: Resource usage, provider selection, traffic routing
Implementation Approach
When building for Edge Runtime:
- Analyze edge requirements: Performance targets, regional needs, scaling requirements
- Design edge-optimized architecture: Bundle optimization, dependency management
- Implement streaming-first patterns: Edge-native streaming, connection optimization
- Optimize for cold starts: Initialization performance, lazy loading strategies
- Add edge-specific monitoring: Performance tracking, error handling, metrics
- Deploy with edge configuration: Vercel configuration, regional settings
- Test edge performance: Load testing, latency measurement, scaling validation
Core Edge Runtime Patterns
Edge-Optimized API Route
// app/api/chat/route.ts - Edge Runtime optimized
import { anthropic } from '@ai-sdk/anthropic';
import { streamText } from 'ai';
// Edge Runtime configuration
export const runtime = 'edge';
export const maxDuration = 300; // 5 minutes max for complex operations
// Edge-optimized provider configuration
const edgeProvider = anthropic('claude-3-haiku-20240307', {
// Optimize for edge performance
baseURL: getRegionalEndpoint(),
timeout: 30000,
maxRetries: 2,
});
export async function POST(req: Request) {
// Edge-optimized request handling
const startTime = Date.now();
const region = req.headers.get('cf-ray')?.split('-')[1] || 'unknown';
try {
const { messages } = await req.json();
// Edge-specific optimizations
const result = streamText({
model: edgeProvider,
messages: convertToModelMessages(messages),
// Edge Runtime streaming configuration
experimental_streamingTimeouts: {
streamingTimeout: 25000, // Shorter timeout for edge
completeTimeout: 60000,
keepAliveInterval: 3000,
},
// Edge memory optimization
maxTokens: 1000, // Limit tokens for edge constraints
temperature: 0.7,
// Edge-specific headers and metadata
headers: {
'x-edge-region': region,
'x-edge-start-time': startTime.toString(),
},
});
// Add edge-specific response headers
const response = result.toUIMessageStreamResponse();
response.headers.set('cache-control', 'public, max-age=0, s-maxage=3600');
response.headers.set('x-edge-cache', 'MISS');
response.headers.set('x-edge-region', region);
return response;
} catch (error) {
// Edge-optimized error handling
return new Response(
JSON.stringify({
error: 'Edge processing failed',
region,
duration: Date.now() - startTime,
}),
{
status: 500,
headers: { 'content-type': 'application/json' },
}
);
}
}
function getRegionalEndpoint(): string {
// Route to regional endpoints for better performance
const region = process.env.VERCEL_REGION || 'us-east-1';
const endpoints = {
'us-east-1': 'https://api.anthropic.com',
'us-west-2': 'https://api.anthropic.com',
'eu-west-1': 'https://api.anthropic.com',
'ap-southeast-1': 'https://api.anthropic.com',
};
return endpoints[region] || endpoints['us-east-1'];
}
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.
- 4d ago First seen · 748 lines · 41 tokens per session scan A 4faa78566d6f
edge-runtime-expert is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (624 stars, last pushed 1y ago), licensed MIT. It adds 41 tokens to every session and 5,191 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 2026-09-03.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.
staff-sre
Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.