From b14f70782d573913ad19894ae048f7d1ea655f23 Mon Sep 17 00:00:00 2001 From: JY Tan Date: Sun, 1 Feb 2026 17:25:12 -0800 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 5878518..34b1b76 100644 --- a/README.md +++ b/README.md @@ -8,8 +8,6 @@ Fence wraps commands in a sandbox that blocks network access by default and restricts filesystem operations based on configurable rules. It's most useful for running semi-trusted code (package installs, build scripts, CI jobs, unfamiliar repos) with controlled side effects, and it can also complement AI coding agents as defense-in-depth. -You can also think of Fence as a permission manager for your CLI agents. - ```bash # Block all network access (default) fence curl https://example.com # → 403 Forbidden @@ -21,6 +19,8 @@ fence -t code npm install # → uses 'code' template with npm/pypi/etc allowed fence -c "rm -rf /" # → blocked by command deny rules ``` +You can also think of Fence as a permission manager for your CLI agents. **Fence works with popular coding agents like Claude Code, Codex, Gemini CLI, Cursor Agent, OpenCode, Factory (Droid) CLI, etc.** See [agents.md](./docs/agents.md) for more details. + ## Install **macOS / Linux:**