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/commands/matt-dionis/claude-code-configs/deploy-local)<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/deploy-local"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/deploy-local/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/commands/matt-dionis/claude-code-configs/deploy-local"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/deploy-local.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 | $0.00012 | $0.00584 |
| Opus 5.5 | $0.00005 | $0.00234 |
| Sonnet 5.5 | $0.00002 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
deploy-local 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Locally with ngrok
Set up and deploy your token-gated MCP server locally with ngrok for testing with claude.ai.
Deployment Steps
-
Pre-deployment Checks
- Verify all dependencies installed: !
npm list fastmcp @radiustechsystems/mcp-sdk zod 2>/dev/null | grep -E "fastmcp|radius|zod" - Check TypeScript compilation: !
npx tsc --noEmit - Validate environment configuration
- Verify all dependencies installed: !
-
Start the MCP Server
# Start server in development mode npm run devServer should start on port 3000 (or configured PORT)
-
Set Up ngrok Tunnel
# Install ngrok if needed # brew install ngrok (macOS) # or download from https://ngrok.com # Start ngrok tunnel ngrok http 3000 -
Configure claude.ai
- Copy the HTTPS URL from ngrok (e.g., https://abc123.ngrok.io)
- In claude.ai:
- Click the 🔌 connection icon
- Add MCP server
- Enter URL:
https://abc123.ngrok.io/mcp - Test connection
-
Verify Token Protection
- Try calling a protected tool
- Should receive EVMAUTH_PROOF_MISSING error
- Error should guide to authenticate_and_purchase
Testing Checklist
- Server starts without errors
- ngrok tunnel established
- claude.ai can connect
- Tools appear in claude.ai
- Token protection working
- Error messages are helpful
- Authentication flow completes
Troubleshooting
Server Won't Start
- Check port not already in use: !
lsof -i :3000 - Verify dependencies installed
- Check for TypeScript errors
ngrok Issues
- Ensure ngrok installed and authenticated
- Check firewall settings
- Try different port if 3000 blocked
claude.ai Connection Failed
- Verify URL includes
/mcpendpoint - Check CORS settings in server
- Ensure server is running
Authentication Errors
- Verify contract address configured
- Check chain ID matches (1223953)
- Ensure RPC URL accessible
Generate Deployment Summary
Create a summary including:
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 · 94 lines · 12 tokens per session scan A 37d5da7aece7
deploy-local is a command published in the GitHub repository Matt-Dionis/claude-code-configs (619 stars, last pushed 1y ago), licensed MIT. It adds 12 tokens to every session and 584 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
deploy
Deploy a program to devnet, or to mainnet after the user's explicit go-ahead.
connect-vybe
Connect and authenticate the Vybe Solana MCP server over OAuth.
invariant
Generate Foundry invariant tests for property-based fuzzing. The high-value command for serious teams.
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
docs-remove
Remove a user-defined source alias from sources.yaml, optionally deleting its cached Markdown.
checklist
Generate a custom checklist for the current feature based on user requirements.