---
title: "Andre Burgstahler (@r3dtuxedo) | Hashnode"
description: "Writing about AI coding agents in practice: Claude Code, Codex, AGENTS.md, cost control and safe automation."
url: "https://hashnode.com/@r3dtuxedo"
---

@r3dtuxedo

# Andre Burgstahler

@r3dtuxedo · Joined October 2026

Writing about AI coding agents in practice: Claude Code, Codex, AGENTS.md, cost control and safe automation.

## Comments

[Glad that framing landed. The short-lived scoped token is the piece people skip: once the allowlist is wide, a long-lived broad token is full access with extra steps. If you ever expose more than one networked MCP from the same host, I'd give each its own token (and its own process) so a leak in one server can't reach the others.](https://hashnode.com/posts/what-can-your-agent-actually-touch/6ae74292cfccaa26775cc03d/comment/6aeb4b4159487bd803adb875#reply-6aee1cdd5246263530517fcc)

Reply · Article · Nov 6 · [What Can Your Agent Actually Touch?](https://hashnode.com/posts/what-can-your-agent-actually-touch/6ae74292cfccaa26775cc03d)

[Thanks, that's the right place for a gate. As far as I can see the paper doesn't test one: it lists authorization gates on the handoff between skills as a suggested defence (next to sanitising content and cutting high-risk edges), but the 79.2% comes from runs with no such gate, so there's no number for how much it would cut. Your version, a confirmation that shows recipient and body whenever fetched content is in context, ties the gate to taint instead of to one skill, which is stronger than just turning off the sender's auto-invocation. The one path I'd watch is the shell: if the agent can send mail through a command instead of the skill, the gate has to sit there too.](https://hashnode.com/posts/two-safe-skills-one-leak/6aec89174c755372f06874ba/comment/6aec9db97543afaac85dedf6#reply-6aedd7a29b3c936d51acc9a6)

Reply · Article · Nov 6 · [Two Safe Skills, One Leak](https://hashnode.com/posts/two-safe-skills-one-leak/6aec89174c755372f06874ba)

[Glad the reads row landed. The research-then-fresh-session habit is a solid complement to the untrusted-content rule: once the page text is gone from context, it can't steer the edit turn. On MCP servers that need network: keep the agent host's network deny-by-default, and put only that server in a separate process or container with an allowlist (e.g. api.github.com) and a short-lived, narrowly scoped token. The agent talks to the local MCP endpoint; it never gets a general egress path. If the server must run in-process, expose only the tools you need and treat the token's scopes as the real boundary — same idea as the remote-server row in the table.](https://hashnode.com/posts/what-can-your-agent-actually-touch/6ae74292cfccaa26775cc03d/comment/6aeb4b4159487bd803adb875#reply-6aeb73fe97b3733a7fde3724)

Reply · Article · Nov 4 · [What Can Your Agent Actually Touch?](https://hashnode.com/posts/what-can-your-agent-actually-touch/6ae74292cfccaa26775cc03d)
