Is the SafeAgentDB skill free?

Yes. The skill itself is free from Aidan945/SafeAgentDB. SkillProof publishes the install command and an independent test verdict at no cost.

What is the SafeAgentDB SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install SafeAgentDB?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use SafeAgentDB with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

SafeAgentDB

Sets up branch-isolated Supabase/Vercel/GitHub Actions preview databases for AFK agent workflows.

by Aidan945 · Aidan945/SafeAgentDB

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4f39e03

The bundled provision-preview-branch.ts script for real implements every capability the docs claim (auth-user copy, public-table copy with include/exclude lists, storage-bucket copy, --dry-run plan, preview-branch-summary.md) rather than just describing them, and every credential-touching step in the skill body is gated behind explicit user permission and cost confirmation before it acts.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What SafeAgentDB does

Installs or adapts SafeAgentDB-style database safety infrastructure: production/develop/preview/local database separation, Supabase branch provisioning, Vercel branch-scoped env vars, and GitHub Actions cleanup workflows. Triggers when a user wants isolated database environments per branch, migration guardrails so agent feature branches never touch shared or production data, or wants this pattern adapted to a non-Supabase stack.

How to install SafeAgentDB

git clone https://github.com/Aidan945/SafeAgentDB.git
mkdir -p ~/.claude/skills
cp -r SafeAgentDB/skills/safeagentdb ~/.claude/skills/safeagentdb

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger SafeAgentDB

/safeagentdb Sets up branch-isolated Supabase/Vercel/GitHub Actions preview databases for AFK agent workflows.

It also activates on plain-language prompts like these:

give each feature branch its own isolated Supabase preview database
set up Vercel env vars scoped to my Supabase branch previews
make sure agent branches can never touch our production database

Frequently asked questions

Is the SafeAgentDB skill free?: Yes. The skill itself is free from Aidan945/SafeAgentDB. SkillProof publishes the install command and an independent test verdict at no cost.
Does SafeAgentDB work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. The bundled provision-preview-branch.ts script for real implements every capability the docs claim (auth-user copy, public-table copy with include/exclude lists, storage-bucket copy, --dry-run plan, preview-branch-summary.md) rather than just describing them, and every credential-touching step in the skill body is gated behind explicit user permission and cost confirmation before it acts.
What is the SafeAgentDB SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install SafeAgentDB?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use SafeAgentDB with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.