<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>OpenMoat blog</title><description>News and notes from the people building OpenMoat.</description><link>https://openmoat.dev/</link><item><title>One set of rules for Claude Code, Codex and Cursor on your team</title><link>https://openmoat.dev/blog/one-policy-for-your-team/</link><guid isPermaLink="true">https://openmoat.dev/blog/one-policy-for-your-team/</guid><description>Every agent has its own settings format, and every developer configures it differently. How to commit one policy to a repository, what a repository may and may not change, and how to check what the agents did.</description><pubDate>Thu, 15 Oct 2026 13:00:00 GMT</pubDate></item><item><title>What a hook can&apos;t see inside npm test</title><link>https://openmoat.dev/blog/what-a-hook-cannot-see/</link><guid isPermaLink="true">https://openmoat.dev/blog/what-a-hook-cannot-see/</guid><description>Agent hooks check the command, not the code it starts. How OpenMoat uses the operating system to bound what a test script can do, and where that stops.</description><pubDate>Thu, 15 Oct 2026 12:00:00 GMT</pubDate></item><item><title>Keep .env files and API tokens away from your AI agent</title><link>https://openmoat.dev/blog/keep-secrets-from-your-agent/</link><guid isPermaLink="true">https://openmoat.dev/blog/keep-secrets-from-your-agent/</guid><description>An agent that can read a token can send it anywhere. How OpenMoat keeps secrets out of reach, and how the agent can still use an API without ever holding the token.</description><pubDate>Thu, 15 Oct 2026 11:00:00 GMT</pubDate></item><item><title>Your agent&apos;s prompt shows the command, not what it does</title><link>https://openmoat.dev/blog/the-prompt-shows-the-command/</link><guid isPermaLink="true">https://openmoat.dev/blog/the-prompt-shows-the-command/</guid><description>An approval prompt shows you text. Here is how a command can hide what it reads, and how OpenMoat checks what it actually opens.</description><pubDate>Thu, 15 Oct 2026 10:00:00 GMT</pubDate></item><item><title>What still stops a bad command when your agent runs without prompts</title><link>https://openmoat.dev/blog/auto-approve-mode/</link><guid isPermaLink="true">https://openmoat.dev/blog/auto-approve-mode/</guid><description>Auto-approve modes remove the one moment you could say no. Here is what OpenMoat still blocks there, and what it does not.</description><pubDate>Thu, 15 Oct 2026 09:00:00 GMT</pubDate></item><item><title>Introducing OpenMoat</title><link>https://openmoat.dev/blog/introducing-openmoat/</link><guid isPermaLink="true">https://openmoat.dev/blog/introducing-openmoat/</guid><description>OpenMoat checks each action an AI coding agent takes on your computer and stops the dangerous ones before they run.</description><pubDate>Thu, 15 Oct 2026 08:00:00 GMT</pubDate></item></channel></rss>