From f79019e7869907437ddf770a3886e9fc356f57a8 Mon Sep 17 00:00:00 2001
From: Nathan Flurry <git@nathanflurry.com>
Date: Wed, 28 Jan 2026 05:45:58 -0800
Subject: [PATCH] docs: add post-release testing agent and fix install URL

---
 .claude/commands/post-release-testing.md | 56 ++++++++++++++++++++++++
 CLAUDE.md                                |  4 ++
 README.md                                |  2 +-
 3 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100644 .claude/commands/post-release-testing.md

diff --git a/.claude/commands/post-release-testing.md b/.claude/commands/post-release-testing.md
new file mode 100644
index 0000000..3622dad
--- /dev/null
+++ b/.claude/commands/post-release-testing.md
@@ -0,0 +1,56 @@
+# Post-Release Testing Agent
+
+You are a post-release testing agent. Your job is to verify that a sandbox-agent release works correctly.
+
+## Environment Setup
+
+First, source the environment file:
+
+```bash
+source ~/misc/env.txt
+```
+
+## Tests to Run
+
+Run these tests in order, reporting results as you go:
+
+### 1. Docker Example Test
+
+```bash
+RUN_DOCKER_EXAMPLES=1 pnpm --filter @sandbox-agent/example-docker test
+```
+
+This test:
+- Creates an Alpine container
+- Installs sandbox-agent via curl from releases.rivet.dev
+- Verifies the `/v1/health` endpoint responds correctly
+
+### 2. E2B Example Test
+
+```bash
+pnpm --filter @sandbox-agent/example-e2b test
+```
+
+This test:
+- Creates an E2B sandbox with internet access
+- Installs sandbox-agent via curl
+- Verifies the `/v1/health` endpoint responds correctly
+
+### 3. Install Script Test
+
+Manually verify the install script works in a fresh environment:
+
+```bash
+docker run --rm alpine:latest sh -c "
+  apk add --no-cache curl ca-certificates libstdc++ libgcc bash &&
+  curl -fsSL https://releases.rivet.dev/sandbox-agent/latest/install.sh | sh &&
+  sandbox-agent --version
+"
+```
+
+## Instructions
+
+1. Run each test sequentially
+2. Report the outcome of each test (pass/fail)
+3. If a test fails, capture and report the error output
+4. Provide a summary at the end with overall pass/fail status
diff --git a/CLAUDE.md b/CLAUDE.md
index 5d4edcd..b4b6a04 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -64,6 +64,10 @@ Universal schema guidance:
 - `sandbox-agent api sessions reject-question` ↔ `POST /v1/sessions/{sessionId}/questions/{questionId}/reject`
 - `sandbox-agent api sessions reply-permission` ↔ `POST /v1/sessions/{sessionId}/permissions/{permissionId}/reply`
 
+## Post-Release Testing
+
+After cutting a release, verify the release works correctly. Run `/project:post-release-testing` to execute the testing agent.
+
 ## Git Commits
 
 - Do not include any co-authors in commit messages (no `Co-Authored-By` lines)
diff --git a/README.md b/README.md
index 9ed0393..a9f8772 100644
--- a/README.md
+++ b/README.md
@@ -124,7 +124,7 @@ Install the binary (fastest installation, no Node.js required):
 
 ```bash
 # Install it
-curl -fsSL https://releases.sandboxagent.dev/sandbox-agent/latest/install.sh | sh
+curl -fsSL https://releases.rivet.dev/sandbox-agent/latest/install.sh | sh
 # Run it
 sandbox-agent server --token "$SANDBOX_TOKEN" --host 127.0.0.1 --port 2468
 ```